From: Kefeng Wang <wangkefeng.wang@huawei.com> mainline inclusion from mainline-v5.13-rc1 commit 39ddb991fc45abcdcddbec7fcdfe28795d0133d7 category: bugfix issue: #I3ZXZF 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. Link: https://lkml.kernel.org/r/20210323131215.934472-1-liushixin2@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Liu Shixin <liushixin2@huawei.com> Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Yu Changchun <yuchangchun1@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 81cc7fdc9c8f..423f97a1120c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2363,19 +2363,21 @@ 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 @@ -2385,8 +2387,7 @@ static int move_freepages(struct zone *zone, if (num_movable && (PageLRU(page) || __PageMovable(page))) (*num_movable)++; - - page++; + pfn++; continue; } @@ -2396,7 +2397,7 @@ 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; } @@ -2406,25 +2407,22 @@ 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); } -- 2.22.0

From: Li Bin <huawei.libin@huawei.com> ohos inclusion category: bugfix bugzilla: NA issue: #I3ZXZF CVE: NA --------------------------- push_dl_task() pick the first pushable task and find an eligible lowest_rq, then double_lock_balance(rq, lowest_rq). So if double_lock_balance() unlock the rq (when double_lock_balance() return 1), we have to check if this task is still on the rq. The problem is that the check conditions are not sufficient: if (unlikely(task_rq(task) != rq || !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { cpu2 cpu1 cpu0 push_dl_task(rq1) pick task_A on rq1 find rq0 double_lock_balance(rq1, rq0) unlock(rq1) rq1 __schedule pick task_A run task_A sleep (dequeued) lock(rq0) lock(rq1) do_above_check(task_A) task_rq(task_A) == rq1 cpus_allowed unchanged task_running == false dl_task(task_A) == true try_to_wake_up(task_A) select_cpu = cpu3 enqueue(rq3, task_A) task_A->on_rq = 1 task_on_rq_queued(task_A) above_check passed, return rq0 ... migrate task_A from rq1 to rq0 So we can't rely on these checks of task_A to make sure the task_A is still on the rq1, even though we hold the rq1->lock. This patch will repick the first pushable task to be sure the task is still on the rq. Signed-off-by: Li Bin <huawei.libin@huawei.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [XQ: - backport to 4.4, adjusted context, - use tsk_cpus_allowed() instead of task->cpus_allowed] Link: https://lkml.org/lkml/2017/9/11/26 Link: https://lkml.org/lkml/2018/4/12/246 Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> (cherry picked from commit bf781024558706a7097840a18ca246f29506c89a) Signed-off-by: Li Ming <limingming.li@huawei.com> Conflicts: kernel/sched/deadline.c Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- kernel/sched/deadline.c | 55 ++++++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 25 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 8d06d1f4e2f7..576b4f6d9f07 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2038,6 +2038,26 @@ static int find_later_rq(struct task_struct *task) return -1; } +static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_dl_tasks(rq)) + return NULL; + + p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost, + struct task_struct, pushable_dl_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!dl_task(p)); + + return p; +} + /* Locks the rq it finds */ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) { @@ -2067,11 +2087,16 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { - if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || - task_running(rq, task) || - !dl_task(task) || - !task_on_rq_queued(task))) { + struct task_struct *next_task; + /* + * We had to unlock the run queue. In + * the mean time, task could have + * migrated already or had its affinity changed. + * Also make sure that it wasn't scheduled on its rq. + */ + next_task = pick_next_pushable_dl_task(rq); + if (unlikely(next_task != task || + !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr))) { double_unlock_balance(rq, later_rq); later_rq = NULL; break; @@ -2096,26 +2121,6 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) return later_rq; } -static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) -{ - struct task_struct *p; - - if (!has_pushable_dl_tasks(rq)) - return NULL; - - p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost, - struct task_struct, pushable_dl_tasks); - - BUG_ON(rq->cpu != task_cpu(p)); - BUG_ON(task_current(rq, p)); - BUG_ON(p->nr_cpus_allowed <= 1); - - BUG_ON(!task_on_rq_queued(p)); - BUG_ON(!dl_task(p)); - - return p; -} - /* * See if the non running -deadline tasks on this rq * can be sent to some other CPU where they can preempt -- 2.22.0

From: Arnd Bergmann <arnd@arndb.de> maillist inclusion category: bugfix issue: #I3ZXZF CVE: NA Reference: https://lore.kernel.org/patchwork/patch/877882/ ------------------------------------------------- Recent versions of binutils always warn about test-arm.s: arch/arm/probes/kprobes/test-arm.s:18262: Warning: using r15 results in unpredictable behaviour arch/arm/probes/kprobes/test-arm.s:18337: Warning: using r15 results in unpredictable behaviour We could work around this using the __inst_arm() macro for passing the two instruction as a hexadecimal literal number, but as Ard pointed out, there is no reason to leave the warnings enabled for this file in general, we intentionally test for an instruction that is not recommended to be used. For consistency, this turns off the warning in both the ARM and Thumb2 versions of this file. Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Arnd Bergmann <arnd@arndb.de> [KF: from https://lore.kernel.org/patchwork/patch/877882/] Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Reviewed-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/probes/kprobes/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/probes/kprobes/Makefile b/arch/arm/probes/kprobes/Makefile index 14db56f49f0a..6432578fc74b 100644 --- a/arch/arm/probes/kprobes/Makefile +++ b/arch/arm/probes/kprobes/Makefile @@ -11,3 +11,7 @@ obj-$(CONFIG_KPROBES) += actions-arm.o checkers-arm.o obj-$(CONFIG_OPTPROBES) += opt-arm.o test-kprobes-objs += test-arm.o endif + +# don't warn about intentionally bogus instructions +CFLAGS_test-arm.o += -Wa,--no-warn +CFLAGS_test-thumb.o += -Wa,--no-warn -- 2.22.0

From: Gu Zheng <guzheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ----------------------------------------------- add the new functions mtd_table_mutex_lock/unlock to instead the mutex_lock(&mtd_table_mutex)/mutex_unlock(&mtd_table_mutex),this modification can avoid the deadlock when insmod ftl.ko the deadlock is caused by the commit 857814ee65db ("mtd: fix: avoid race condition when accessing mtd->usecount") the process is as follows: init_ftl register_mtd_blktrans mutex_lock(&mtd_table_mutex) //mtd_table_mutex locked ftl_add_mtd add_mtd_blktrans_dev device_add_disk register_disk blkdev_get __blkdev_get blktrans_open mutex_lock(&mtd_table_mutex) //dead lock so we add the mtd_table_mutex_owner to record current process. if the lock is locked before , it can jump the lock where will deadlock. it solved the above issue,also can prevent some mtd_table_mutex deadlock undiscovered. Signed-off-by: Gu Zheng <guzheng1@huawei.com> Acked-by: Miao Xie <miaoxie@huawei.com> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Reviewed-by: Hou Tao <houta1@huawei.com> conflict: drivers/mtd/mtdcore.c drivers/mtd/mtdcore.h Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/mtd/mtd_blkdevs.c | 31 +++++++--------- drivers/mtd/mtdcore.c | 75 ++++++++++++++++++++++++++++----------- drivers/mtd/mtdcore.h | 4 ++- 3 files changed, 70 insertions(+), 40 deletions(-) diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 0c05f77f9b21..37f4e169d305 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -209,7 +209,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) if (!dev) return -ERESTARTSYS; /* FIXME: busy loop! -arnd*/ - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); mutex_lock(&dev->lock); if (dev->open) @@ -235,7 +235,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) unlock: dev->open++; mutex_unlock(&dev->lock); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); blktrans_dev_put(dev); return ret; @@ -246,7 +246,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) module_put(dev->tr->owner); kref_put(&dev->ref, blktrans_dev_release); mutex_unlock(&dev->lock); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); blktrans_dev_put(dev); return ret; } @@ -258,7 +258,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode) if (!dev) return; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); mutex_lock(&dev->lock); if (--dev->open) @@ -274,7 +274,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode) } unlock: mutex_unlock(&dev->lock); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); blktrans_dev_put(dev); } @@ -345,10 +345,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) struct gendisk *gd; int ret; - if (mutex_trylock(&mtd_table_mutex)) { - mutex_unlock(&mtd_table_mutex); - BUG(); - } + mtd_table_assert_mutex_locked(); mutex_lock(&blktrans_ref_mutex); list_for_each_entry(d, &tr->devs, list) { @@ -479,11 +476,7 @@ int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old) { unsigned long flags; - if (mutex_trylock(&mtd_table_mutex)) { - mutex_unlock(&mtd_table_mutex); - BUG(); - } - + mtd_table_assert_mutex_locked(); if (old->disk_attributes) sysfs_remove_group(&disk_to_dev(old->disk)->kobj, old->disk_attributes); @@ -557,13 +550,13 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) register_mtd_user(&blktrans_notifier); - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); ret = register_blkdev(tr->major, tr->name); if (ret < 0) { printk(KERN_WARNING "Unable to register %s block device on major %d: %d\n", tr->name, tr->major, ret); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return ret; } @@ -579,7 +572,7 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) if (mtd->type != MTD_ABSENT) tr->add_mtd(tr, mtd); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return 0; } @@ -587,7 +580,7 @@ int deregister_mtd_blktrans(struct mtd_blktrans_ops *tr) { struct mtd_blktrans_dev *dev, *next; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); /* Remove it from the list of active majors */ list_del(&tr->list); @@ -596,7 +589,7 @@ int deregister_mtd_blktrans(struct mtd_blktrans_ops *tr) tr->remove_dev(dev); unregister_blkdev(tr->major, tr->name); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); BUG_ON(!list_empty(&tr->devs)); return 0; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 1c8c40728678..37bd3171157a 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -70,8 +70,9 @@ static DEFINE_IDR(mtd_idr); /* These are exported solely for the purpose of mtd_blkdevs.c. You should not use them for _anything_ else */ -DEFINE_MUTEX(mtd_table_mutex); -EXPORT_SYMBOL_GPL(mtd_table_mutex); +static DEFINE_MUTEX(mtd_table_mutex); +static int mtd_table_mutex_depth; +static struct task_struct *mtd_table_mutex_owner; struct mtd_info *__mtd_next_device(int i) { @@ -84,6 +85,40 @@ static LIST_HEAD(mtd_notifiers); #define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2) +void mtd_table_mutex_lock(void) +{ + if (mtd_table_mutex_owner != current) { + mutex_lock(&mtd_table_mutex); + mtd_table_mutex_owner = current; + } + mtd_table_mutex_depth++; +} +EXPORT_SYMBOL_GPL(mtd_table_mutex_lock); + + +void mtd_table_mutex_unlock(void) +{ + if (mtd_table_mutex_owner != current) { + pr_err("MTD:lock_owner is %s, but current is %s\n", + mtd_table_mutex_owner->comm, current->comm); + BUG(); + } + if (--mtd_table_mutex_depth == 0) { + mtd_table_mutex_owner = NULL; + mutex_unlock(&mtd_table_mutex); + } +} +EXPORT_SYMBOL_GPL(mtd_table_mutex_unlock); + +void mtd_table_assert_mutex_locked(void) +{ + if (mtd_table_mutex_owner != current) { + pr_err("MTD:lock_owner is %s, but current is %s\n", + mtd_table_mutex_owner->comm, current->comm); + BUG(); + } +} +EXPORT_SYMBOL_GPL(mtd_table_assert_mutex_locked); /* REVISIT once MTD uses the driver model better, whoever allocates * the mtd_info will probably want to use the release() hook... */ @@ -610,7 +645,7 @@ int add_mtd_device(struct mtd_info *mtd) !master->pairing || master->_writev)) return -EINVAL; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL); if (i < 0) { @@ -686,7 +721,7 @@ int add_mtd_device(struct mtd_info *mtd) list_for_each_entry(not, &mtd_notifiers, list) not->add(mtd); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); /* We _know_ we aren't being removed, because our caller is still holding us here. So none of this try_ nonsense, and no bitching about it @@ -700,7 +735,7 @@ int add_mtd_device(struct mtd_info *mtd) of_node_put(mtd_get_of_node(mtd)); idr_remove(&mtd_idr, i); fail_locked: - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return error; } @@ -719,7 +754,7 @@ int del_mtd_device(struct mtd_info *mtd) int ret; struct mtd_notifier *not; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); debugfs_remove_recursive(mtd->dbg.dfs_dir); @@ -752,7 +787,7 @@ int del_mtd_device(struct mtd_info *mtd) } out_error: - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return ret; } @@ -894,7 +929,7 @@ void register_mtd_user (struct mtd_notifier *new) { struct mtd_info *mtd; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); list_add(&new->list, &mtd_notifiers); @@ -903,7 +938,7 @@ void register_mtd_user (struct mtd_notifier *new) mtd_for_each_device(mtd) new->add(mtd); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); } EXPORT_SYMBOL_GPL(register_mtd_user); @@ -920,7 +955,7 @@ int unregister_mtd_user (struct mtd_notifier *old) { struct mtd_info *mtd; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); module_put(THIS_MODULE); @@ -928,7 +963,7 @@ int unregister_mtd_user (struct mtd_notifier *old) old->remove(mtd); list_del(&old->list); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return 0; } EXPORT_SYMBOL_GPL(unregister_mtd_user); @@ -949,7 +984,7 @@ struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num) struct mtd_info *ret = NULL, *other; int err = -ENODEV; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); if (num == -1) { mtd_for_each_device(other) { @@ -973,7 +1008,7 @@ struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num) if (err) ret = ERR_PTR(err); out: - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return ret; } EXPORT_SYMBOL_GPL(get_mtd_device); @@ -1020,7 +1055,7 @@ struct mtd_info *get_mtd_device_nm(const char *name) int err = -ENODEV; struct mtd_info *mtd = NULL, *other; - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); mtd_for_each_device(other) { if (!strcmp(name, other->name)) { @@ -1036,20 +1071,20 @@ struct mtd_info *get_mtd_device_nm(const char *name) if (err) goto out_unlock; - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return mtd; out_unlock: - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(get_mtd_device_nm); void put_mtd_device(struct mtd_info *mtd) { - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); __put_mtd_device(mtd); - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); } EXPORT_SYMBOL_GPL(put_mtd_device); @@ -2161,13 +2196,13 @@ static int mtd_proc_show(struct seq_file *m, void *v) struct mtd_info *mtd; seq_puts(m, "dev: size erasesize name\n"); - mutex_lock(&mtd_table_mutex); + mtd_table_mutex_lock(); mtd_for_each_device(mtd) { seq_printf(m, "mtd%d: %8.8llx %8.8x \"%s\"\n", mtd->index, (unsigned long long)mtd->size, mtd->erasesize, mtd->name); } - mutex_unlock(&mtd_table_mutex); + mtd_table_mutex_unlock(); return 0; } #endif /* CONFIG_PROC_FS */ diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h index b5eefeabf310..40c5f104794c 100644 --- a/drivers/mtd/mtdcore.h +++ b/drivers/mtd/mtdcore.h @@ -4,7 +4,6 @@ * You should not use them for _anything_ else. */ -extern struct mutex mtd_table_mutex; extern struct backing_dev_info *mtd_bdi; struct mtd_info *__mtd_next_device(int i); @@ -22,6 +21,9 @@ void mtd_part_parser_cleanup(struct mtd_partitions *parts); int __init init_mtdchar(void); void __exit cleanup_mtdchar(void); +extern void mtd_table_mutex_lock(void); +extern void mtd_table_mutex_unlock(void); +extern void mtd_table_assert_mutex_locked(void); #define mtd_for_each_device(mtd) \ for ((mtd) = __mtd_next_device(0); \ -- 2.22.0

From: Zefan Li <lizefan@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------- Since commit 3c606d35fe97 ("cgroup: prevent mount hang due to memory controller lifetime"), a cgroup root won't be destroyed if there are any child cgroups, dead or alive. This introduced a small regression. # cat test.sh mount -t cgroup -o cpuset xxx /cgroup mkdir /cgroup/tmp rmdir /cgroup/tmp umount /cgroup After running this script, you'll probably find the cgroup hierarchy is still active. # cat /proc/cgroups | grep cpuset #subsys_name hierarchy num_cgroups enabled cpuset 1 1 1 ... Fix this by waiting for a while when umount. Now run the script again and you'll see: # cat /proc/cgroups | grep cpuset #subsys_name hierarchy num_cgroups enabled cpuset 0 1 1 ... Cc: stable@vger.kernel.org # 3.19+ Signed-off-by: Zefan Li <lizefan@huawei.com> Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org> Signed-off-by: Changchun Yu <yuchangchun1@huawei.com> Reviewed-by: Zefan Li <lizefan@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Lu Jialin <lujialin4@huawei.com> conflict: kernel/cgroup/cgroup.c Reviewed-by: xiu jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- include/linux/cgroup-defs.h | 3 +++ kernel/cgroup/cgroup.c | 16 +++++++++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index fee0b5547cd0..ffec16930b00 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -509,6 +509,9 @@ struct cgroup_root { /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; + /* Wait while cgroups are being destroyed */ + wait_queue_head_t wait; + /* A list running through the active hierarchies */ struct list_head root_list; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c8b811e039cc..416bec1428d0 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1914,6 +1914,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); + init_waitqueue_head(&root->wait); root->flags = ctx->flags; if (ctx->release_agent) @@ -2139,6 +2140,17 @@ static void cgroup_kill_sb(struct super_block *sb) struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); + /* + * Wait if there are cgroups being destroyed, because the destruction + * is asynchronous. On the other hand some controllers like memcg + * may pin cgroups for a very long time, so don't wait forever. + */ + if (root != &cgrp_dfl_root) { + wait_event_timeout(root->wait, + list_empty(&root->cgrp.self.children), + msecs_to_jiffies(500)); + } + /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). @@ -5025,8 +5037,10 @@ static void css_release_work_fn(struct work_struct *work) if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); + if (css->parent && !css->parent->parent && + list_empty(&css->parent->children)) + wake_up(&cgrp->root->wait); } - mutex_unlock(&cgroup_mutex); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); -- 2.22.0

From: Xiongfeng Wang <wangxiongfeng2@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------------------------------- When I test 'aer-inject' with the following procedures: 1. inject a fatal error into a upstream PCI bridge 2. remove the upstream bridge by sysfs 3. rescan the PCI tree by 'echo 1 > /sys/bus/pci/rescan' 4. execute command 'rmmod aer-inject' 5. remove the upstream bridge by sysfs again I came across the following Oops. [ 799.713238] Internal error: Oops: 96000007 [#1] SMP [ 799.718099] Process bash (pid: 10683, stack limit = 0x00000000125a3b1b) [ 799.724686] CPU: 108 PID: 10683 Comm: bash Kdump: loaded Not tainted 4.19.36 #2 [ 799.731962] Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 1.05 09/18/2019 [ 799.739325] pstate: 40400009 (nZcv daif +PAN -UAO) [ 799.744104] pc : pci_remove_bus+0xc0/0x1c0 [ 799.748182] lr : pci_remove_bus+0x94/0x1c0 [ 799.752260] sp : ffffa02e335df940 [ 799.755560] x29: ffffa02e335df940 x28: ffff2000088216a8 [ 799.760849] x27: 1ffff405c66bbfbc x26: ffff20000a9518c0 [ 799.766139] x25: ffffa02dea6ec418 x24: 1ffff405bd4dd883 [ 799.771427] x23: ffffa02e72576628 x22: 1ffff405ce4aecc0 [ 799.776715] x21: ffffa02e72576608 x20: ffff200002e75080 [ 799.782003] x19: ffffa02e72576600 x18: 0000000000000000 [ 799.787291] x17: 0000000000000000 x16: 0000000000000000 [ 799.792578] x15: 0000000000000001 x14: dfff200000000000 [ 799.797866] x13: ffff20000a6dfaf0 x12: 0000000000000000 [ 799.803154] x11: 1fffe4000159b217 x10: ffff04000159b217 [ 799.808442] x9 : dfff200000000000 x8 : ffff20000acd90bf [ 799.813730] x7 : 0000000000000000 x6 : 0000000000000000 [ 799.819017] x5 : 0000000000000001 x4 : 0000000000000000 [ 799.824306] x3 : 1ffff405dbe62603 x2 : 1fffe400005cea11 [ 799.829593] x1 : dfff200000000000 x0 : ffff200002e75088 [ 799.834882] Call trace: [ 799.837323] pci_remove_bus+0xc0/0x1c0 [ 799.841056] pci_remove_bus_device+0xd0/0x2f0 [ 799.845392] pci_stop_and_remove_bus_device_locked+0x2c/0x40 [ 799.851028] remove_store+0x1b8/0x1d0 [ 799.854679] dev_attr_store+0x60/0x80 [ 799.858330] sysfs_kf_write+0x104/0x170 [ 799.862149] kernfs_fop_write+0x23c/0x430 [ 799.866143] __vfs_write+0xec/0x4e0 [ 799.869615] vfs_write+0x12c/0x3d0 [ 799.873001] ksys_write+0xd0/0x190 [ 799.876389] __arm64_sys_write+0x70/0xa0 [ 799.880298] el0_svc_common+0xfc/0x278 [ 799.884030] el0_svc_handler+0x50/0xc0 [ 799.887764] el0_svc+0x8/0xc [ 799.890634] Code: d2c40001 f2fbffe1 91002280 d343fc02 (38e16841) [ 799.896700] kernel fault(0x1) notification starting on CPU 108 It is because when we alloc a new bus in rescanning process, the 'pci_ops' of the newly allocced 'pci_bus' is inherited from its parent pci bus. Whereas, the 'pci_ops' of the parent bus may be changed to 'aer_inj_pci_ops' in 'aer_inject()'. When we unload the module 'aer_inject', we only restore the 'pci_ops' for the pci bus of the error-injected device and the root port in 'aer_inject_exit'. After we have unloaded the module, the 'pci_ops' of the newly allocced pci bus is still 'aer_inj_pci_ops'. When we access it, an Oops happened. This patch add a member 'backup_ops' in 'struct pci_bus' to record the original 'ops'. When we alloc a child pci bus, we assign the 'backup_ops' of the parent bus to the 'ops' of the child bus. Maybe the best way is to not modify the 'pci_ops' in 'struct pci_bus', but this will refactor the 'aer_inject' framework a lot. I haven't found a better way to handle it. Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: yangerkun <yangerkun@huawei.com> Conflicts: drivers/pci/probe.c include/linux/pci.h Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/pci/probe.c | 12 +++++++++--- include/linux/pci.h | 1 + 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ece90a23936d..0187fe60b7d8 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -896,6 +896,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge) bus->sysdata = bridge->sysdata; bus->msi = bridge->msi; bus->ops = bridge->ops; + bus->backup_ops = bus->ops; bus->number = bus->busn_res.start = bridge->busnr; #ifdef CONFIG_PCI_DOMAINS_GENERIC bus->domain_nr = pci_bus_find_domain_nr(bus, parent); @@ -1057,10 +1058,15 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, child->bus_flags = parent->bus_flags; host = pci_find_host_bridge(parent); - if (host->child_ops) + if (host->child_ops) { child->ops = host->child_ops; - else - child->ops = parent->ops; + } else { + if (parent->backup_ops) + child->ops = parent->backup_ops; + else + child->ops = parent->ops; + } + child->backup_ops = child->ops; /* * Initialize some portions of the bus device, but don't register diff --git a/include/linux/pci.h b/include/linux/pci.h index 22207a79762c..936da8925d68 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -615,6 +615,7 @@ struct pci_bus { struct resource busn_res; /* Bus numbers routed to this bus */ struct pci_ops *ops; /* Configuration access functions */ + struct pci_ops *backup_ops; struct msi_controller *msi; /* MSI controller */ void *sysdata; /* Hook for sys-specific extension */ struct proc_dir_entry *procdir; /* Directory entry in /proc/bus/pci */ -- 2.22.0

From: Yang Yingliang <yangyingliang@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: CVE-2019-16230 ------------------------------------------------- check the alloc_workqueue return value in radeon_crtc_init() to avoid null-ptr-deref. Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/gpu/drm/radeon/radeon_display.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index e0ae911ef427..b709836fe3d3 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -689,11 +689,16 @@ static void radeon_crtc_init(struct drm_device *dev, int index) if (radeon_crtc == NULL) return; + radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); + if (!radeon_crtc->flip_queue) { + kfree(radeon_crtc); + return; + } + drm_crtc_init(dev, &radeon_crtc->base, &radeon_crtc_funcs); drm_mode_crtc_set_gamma_size(&radeon_crtc->base, 256); radeon_crtc->crtc_id = index; - radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0); rdev->mode_info.crtcs[index] = radeon_crtc; if (rdev->family >= CHIP_BONAIRE) { -- 2.22.0

From: liujian <liujian56@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA --------------------------- syzkaller triggered a UBSAN warning: [ 196.188950] UBSAN: Undefined behaviour in drivers/input/input.c:62:23 [ 196.188958] signed integer overflow: [ 196.188964] -2147483647 - 104 cannot be represented in type 'int [2]' [ 196.188973] CPU: 7 PID: 4763 Comm: syz-executor Not tainted 4.19.0-514.55.6.9.x86_64+ #7 [ 196.188977] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 196.188979] Call Trace: [ 196.189001] dump_stack+0x91/0xeb [ 196.189014] ubsan_epilogue+0x9/0x7c [ 196.189020] handle_overflow+0x1d7/0x22c [ 196.189028] ? __ubsan_handle_negate_overflow+0x18f/0x18f [ 196.189038] ? __mutex_lock+0x213/0x13f0 [ 196.189053] ? drop_futex_key_refs+0xa0/0xa0 [ 196.189070] ? __might_fault+0xef/0x1b0 [ 196.189096] input_handle_event+0xe1b/0x1290 [ 196.189108] input_inject_event+0x1d7/0x27e [ 196.189119] evdev_write+0x2cf/0x3f0 [ 196.189129] ? evdev_pass_values+0xd40/0xd40 [ 196.189157] ? mark_held_locks+0x160/0x160 [ 196.189171] ? __vfs_write+0xe0/0x6c0 [ 196.189175] ? evdev_pass_values+0xd40/0xd40 [ 196.189179] __vfs_write+0xe0/0x6c0 [ 196.189186] ? kernel_read+0x130/0x130 [ 196.189204] ? _cond_resched+0x15/0x30 [ 196.189214] ? __inode_security_revalidate+0xb8/0xe0 [ 196.189222] ? selinux_file_permission+0x354/0x430 [ 196.189233] vfs_write+0x160/0x440 [ 196.189242] ksys_write+0xc1/0x190 [ 196.189248] ? __ia32_sys_read+0xb0/0xb0 [ 196.189259] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 196.189267] ? do_syscall_64+0x22/0x4a0 [ 196.189276] do_syscall_64+0xa5/0x4a0 [ 196.189287] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 196.189293] RIP: 0033:0x44e7c9 [ 196.189299] Code: fc ff 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 the syzkaller reproduce script(but can't reproduce it every time): r0 = syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) write$binfmt_elf64(r0, &(0x7f0000000240)={{0x7f, 0x45, 0x4c, 0x46, 0x40, 0x2, 0x2, 0xffffffff, 0xffffffffffff374c, 0x3, 0x0, 0x80000001, 0x103, 0x40, 0x22e, 0x26, 0x1, 0x38, 0x2, 0xa23, 0x1, 0x2}, [{0x6474e557, 0x5, 0x6, 0x2, 0x9, 0x9, 0x6c3, 0x1ff}], "", [[], [], [], []]}, 0x478) ioctl$EVIOCGSW(0xffffffffffffffff, 0x8040451b, &(0x7f0000000040)=""/7) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) r1 = syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) openat$smack_task_current(0xffffffffffffff9c, &(0x7f0000000040)='/proc/self/attr/current\x00', 0x2, 0x0) ioctl$EVIOCSABS0(r1, 0x401845c0, &(0x7f0000000000)={0x4, 0x10000, 0x4, 0xd1, 0x81, 0x3}) eventfd(0x1ff) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x200) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) syz_open_dev$evdev(&(0x7f0000000100)='/dev/input/event#\x00', 0x2, 0x1) Typecast int to long to fix the issue. Signed-off-by: liujian <liujian56@huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Xiang Yang <xiangyang3@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/input/input.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/input/input.c b/drivers/input/input.c index 3cfd2c18eebd..cf6f557428c0 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -56,14 +56,17 @@ static inline int is_event_supported(unsigned int code, static int input_defuzz_abs_event(int value, int old_val, int fuzz) { if (fuzz) { - if (value > old_val - fuzz / 2 && value < old_val + fuzz / 2) + if (value > (long)old_val - fuzz / 2 && + value < (long)old_val + fuzz / 2) return old_val; - if (value > old_val - fuzz && value < old_val + fuzz) - return (old_val * 3 + value) / 4; + if (value > (long)old_val - fuzz && + value < (long)old_val + fuzz) + return ((long)old_val * 3 + value) / 4; - if (value > old_val - fuzz * 2 && value < old_val + fuzz * 2) - return (old_val + value) / 2; + if (value > (long)old_val - fuzz * 2 && + value < (long)old_val + fuzz * 2) + return ((long)old_val + value) / 2; } return value; -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc1 commit 81414b4dd48f596bf33e1b32c2e43e2047150ca6 issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Superblock is written out either through ext4_commit_super() or through ext4_handle_dirty_super(). In both cases we recompute the checksum so it is not necessary to recompute it after updating superblock free inodes & blocks counters. Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20201127113405.26867-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 21c4ba2513ce..6e211dc615b3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5007,13 +5007,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); - ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); - ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc1 commit 014c9caa29d3a44e0de695c99ef18bec3e887d52 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- The only difference between __ext4_abort() and __ext4_error() is that the former one ignores errors=continue mount option. Unify the code to reduce duplication. Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20201127113405.26867-5-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/ext4.h | 29 +++++++--------- fs/ext4/ext4_jbd2.c | 4 +-- fs/ext4/inode.c | 2 +- fs/ext4/super.c | 84 ++++++++++++--------------------------------- 4 files changed, 37 insertions(+), 82 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 7cae226b000f..5d7f2995fac6 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2955,9 +2955,9 @@ extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); -extern __printf(6, 7) -void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64, - const char *, ...); +extern __printf(7, 8) +void __ext4_error(struct super_block *, const char *, unsigned int, bool, + int, __u64, const char *, ...); extern __printf(6, 7) void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, int, const char *, ...); @@ -2966,9 +2966,6 @@ void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); -extern __printf(5, 6) -void __ext4_abort(struct super_block *, const char *, unsigned int, int, - const char *, ...); extern __printf(4, 5) void __ext4_warning(struct super_block *, const char *, unsigned int, const char *, ...); @@ -2998,6 +2995,9 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define EXT4_ERROR_FILE(file, block, fmt, a...) \ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) +#define ext4_abort(sb, err, fmt, a...) \ + __ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a) + #ifdef CONFIG_PRINTK #define ext4_error_inode(inode, func, line, block, fmt, ...) \ @@ -3008,11 +3008,11 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define ext4_error_file(file, func, line, block, fmt, ...) \ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__) #define ext4_error(sb, fmt, ...) \ - __ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__) + __ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \ + ##__VA_ARGS__) #define ext4_error_err(sb, err, fmt, ...) \ - __ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__) -#define ext4_abort(sb, err, fmt, ...) \ - __ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__) + __ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \ + ##__VA_ARGS__) #define ext4_warning(sb, fmt, ...) \ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_warning_inode(inode, fmt, ...) \ @@ -3045,17 +3045,12 @@ do { \ #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, 0, 0, " "); \ + __ext4_error(sb, "", 0, false, 0, 0, " "); \ } while (0) #define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, err, 0, " "); \ -} while (0) -#define ext4_abort(sb, err, fmt, ...) \ -do { \ - no_printk(fmt, ##__VA_ARGS__); \ - __ext4_abort(sb, "", 0, err, " "); \ + __ext4_error(sb, "", 0, false, err, 0, " "); \ } while (0) #define ext4_warning(sb, fmt, ...) \ do { \ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 0fd0c42a4f7d..1a0a827a7f34 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -296,8 +296,8 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - __ext4_abort(inode->i_sb, where, line, -err, - "error %d when attempting revoke", err); + __ext4_error(inode->i_sb, where, line, true, -err, 0, + "error %d when attempting revoke", err); } BUFFER_TRACE(bh, "exit"); return err; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3f11c948feb0..e6bed50e1786 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4619,7 +4619,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { if (flags & EXT4_IGET_HANDLE) return ERR_PTR(-ESTALE); - __ext4_error(sb, function, line, EFSCORRUPTED, 0, + __ext4_error(sb, function, line, false, EFSCORRUPTED, 0, "inode #%lu: comm %s: iget: illegal inode #", ino, current->comm); return ERR_PTR(-EFSCORRUPTED); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6e211dc615b3..a39098cf5e7d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -662,16 +662,21 @@ static bool system_going_down(void) * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. + * + * If force_ro is set, we unconditionally force the filesystem into an + * ABORT|READONLY state, unless the error response on the fs has been set to + * panic in which case we take the easy way out and panic immediately. This is + * used to deal with unrecoverable failures such as journal IO errors or ENOMEM + * at a critical moment in log management. */ - -static void ext4_handle_error(struct super_block *sb) +static void ext4_handle_error(struct super_block *sb, bool force_ro) { journal_t *journal = EXT4_SB(sb)->s_journal; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (sb_rdonly(sb) || test_opt(sb, ERRORS_CONT)) + if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT))) return; ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); @@ -682,18 +687,17 @@ static void ext4_handle_error(struct super_block *sb) * could panic during 'reboot -f' as the underlying device got already * disabled. */ - if (test_opt(sb, ERRORS_RO) || system_going_down()) { - ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); - /* - * Make sure updated value of ->s_mount_flags will be visible - * before ->s_flags update - */ - smp_wmb(); - sb->s_flags |= SB_RDONLY; - } else if (test_opt(sb, ERRORS_PANIC)) { + if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); + /* + * Make sure updated value of ->s_mount_flags will be visible before + * ->s_flags update + */ + smp_wmb(); + sb->s_flags |= SB_RDONLY; } #define ext4_error_ratelimit(sb) \ @@ -701,7 +705,7 @@ static void ext4_handle_error(struct super_block *sb) "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, - unsigned int line, int error, __u64 block, + unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; @@ -721,7 +725,7 @@ void __ext4_error(struct super_block *sb, const char *function, va_end(args); } save_error_info(sb, error, 0, block, function, line); - ext4_handle_error(sb); + ext4_handle_error(sb, force_ro); } void __ext4_error_inode(struct inode *inode, const char *function, @@ -753,7 +757,7 @@ void __ext4_error_inode(struct inode *inode, const char *function, } save_error_info(inode->i_sb, error, inode->i_ino, block, function, line); - ext4_handle_error(inode->i_sb); + ext4_handle_error(inode->i_sb, false); } void __ext4_error_file(struct file *file, const char *function, @@ -792,7 +796,7 @@ void __ext4_error_file(struct file *file, const char *function, } save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, function, line); - ext4_handle_error(inode->i_sb); + ext4_handle_error(inode->i_sb, false); } const char *ext4_decode_error(struct super_block *sb, int errno, @@ -860,51 +864,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, } save_error_info(sb, -errno, 0, 0, function, line); - ext4_handle_error(sb); -} - -/* - * ext4_abort is a much stronger failure handler than ext4_error. The - * abort function may be used to deal with unrecoverable failures such - * as journal IO errors or ENOMEM at a critical moment in log management. - * - * We unconditionally force the filesystem into an ABORT|READONLY state, - * unless the error response on the fs has been set to panic in which - * case we take the easy way out and panic immediately. - */ - -void __ext4_abort(struct super_block *sb, const char *function, - unsigned int line, int error, const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) - return; - - save_error_info(sb, error, 0, 0, function, line); - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n", - sb->s_id, function, line, &vaf); - va_end(args); - - if (sb_rdonly(sb) == 0) { - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - if (EXT4_SB(sb)->s_journal) - jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); - - ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); - /* - * Make sure updated value of ->s_mount_flags will be visible - * before ->s_flags update - */ - smp_wmb(); - sb->s_flags |= SB_RDONLY; - } - if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) - panic("EXT4-fs panic from previous error\n"); + ext4_handle_error(sb, false); } void __ext4_msg(struct super_block *sb, @@ -1007,7 +967,7 @@ __acquires(bitlock) ext4_unlock_group(sb, grp); ext4_commit_super(sb, 1); - ext4_handle_error(sb); + ext4_handle_error(sb, false); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc1 commit 02a7780e4d2fcf438ac6773bc469e7ada2af56be category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- We convert errno's to ext4 on-disk format error codes in save_error_info(). Add a function and a bit of macro magic to make this simpler. Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20201127113405.26867-7-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 95 +++++++++++++++++++++---------------------------- 1 file changed, 40 insertions(+), 55 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0594b08da8f6..c62f826a6893 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -551,76 +551,61 @@ static bool system_going_down(void) || system_state == SYSTEM_RESTART; } +struct ext4_err_translation { + int code; + int errno; +}; + +#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } + +static struct ext4_err_translation err_translation[] = { + EXT4_ERR_TRANSLATE(EIO), + EXT4_ERR_TRANSLATE(ENOMEM), + EXT4_ERR_TRANSLATE(EFSBADCRC), + EXT4_ERR_TRANSLATE(EFSCORRUPTED), + EXT4_ERR_TRANSLATE(ENOSPC), + EXT4_ERR_TRANSLATE(ENOKEY), + EXT4_ERR_TRANSLATE(EROFS), + EXT4_ERR_TRANSLATE(EFBIG), + EXT4_ERR_TRANSLATE(EEXIST), + EXT4_ERR_TRANSLATE(ERANGE), + EXT4_ERR_TRANSLATE(EOVERFLOW), + EXT4_ERR_TRANSLATE(EBUSY), + EXT4_ERR_TRANSLATE(ENOTDIR), + EXT4_ERR_TRANSLATE(ENOTEMPTY), + EXT4_ERR_TRANSLATE(ESHUTDOWN), + EXT4_ERR_TRANSLATE(EFAULT), +}; + +static int ext4_errno_to_code(int errno) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(err_translation); i++) + if (err_translation[i].errno == errno) + return err_translation[i].code; + return EXT4_ERR_UNKNOWN; +} + static void __save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - int err; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (bdev_read_only(sb->s_bdev)) return; + /* We default to EFSCORRUPTED error... */ + if (error == 0) + error = EFSCORRUPTED; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); ext4_update_tstamp(es, s_last_error_time); strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); es->s_last_error_ino = cpu_to_le32(ino); es->s_last_error_block = cpu_to_le64(block); - switch (error) { - case EIO: - err = EXT4_ERR_EIO; - break; - case ENOMEM: - err = EXT4_ERR_ENOMEM; - break; - case EFSBADCRC: - err = EXT4_ERR_EFSBADCRC; - break; - case 0: - case EFSCORRUPTED: - err = EXT4_ERR_EFSCORRUPTED; - break; - case ENOSPC: - err = EXT4_ERR_ENOSPC; - break; - case ENOKEY: - err = EXT4_ERR_ENOKEY; - break; - case EROFS: - err = EXT4_ERR_EROFS; - break; - case EFBIG: - err = EXT4_ERR_EFBIG; - break; - case EEXIST: - err = EXT4_ERR_EEXIST; - break; - case ERANGE: - err = EXT4_ERR_ERANGE; - break; - case EOVERFLOW: - err = EXT4_ERR_EOVERFLOW; - break; - case EBUSY: - err = EXT4_ERR_EBUSY; - break; - case ENOTDIR: - err = EXT4_ERR_ENOTDIR; - break; - case ENOTEMPTY: - err = EXT4_ERR_ENOTEMPTY; - break; - case ESHUTDOWN: - err = EXT4_ERR_ESHUTDOWN; - break; - case EFAULT: - err = EXT4_ERR_EFAULT; - break; - default: - err = EXT4_ERR_UNKNOWN; - } - es->s_last_error_errcode = err; + es->s_last_error_errcode = ext4_errno_to_code(error); if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; es->s_first_error_time_hi = es->s_last_error_time_hi; -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc4 commit e789ca0cc1d51296832b8424fa4008ce6e9d1703 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- save_error_info() is always called together with ext4_handle_error(). Combine them into a single call and move unconditional bits out of save_error_info() into ext4_handle_error(). Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20201216101844.22917-2-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9cd4d7453d18..ea4c8f2c03a7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -592,9 +592,6 @@ static void __save_error_info(struct super_block *sb, int error, { struct ext4_sb_info *sbi = EXT4_SB(sb); - EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; - if (bdev_read_only(sb->s_bdev)) - return; /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; @@ -647,13 +644,19 @@ static void save_error_info(struct super_block *sb, int error, * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ -static void ext4_handle_error(struct super_block *sb, bool force_ro) +static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); + if (!bdev_read_only(sb->s_bdev)) + save_error_info(sb, error, ino, block, func, line); + if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT))) return; @@ -710,8 +713,7 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } - save_error_info(sb, error, 0, block, function, line); - ext4_handle_error(sb, force_ro); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, @@ -741,9 +743,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } - save_error_info(inode->i_sb, error, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, + function, line); } void __ext4_error_file(struct file *file, const char *function, @@ -780,9 +781,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } - save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, + function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, @@ -849,8 +849,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } - save_error_info(sb, -errno, 0, 0, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, @@ -944,13 +943,14 @@ __acquires(bitlock) if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; __save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - schedule_work(&EXT4_SB(sb)->s_error_work); + if (!bdev_read_only(sb->s_bdev)) + schedule_work(&EXT4_SB(sb)->s_error_work); return; } ext4_unlock_group(sb, grp); - save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc4 commit 05c2c00f3769abb9e323fcaca70d2de0b48af7ba category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- 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@suse.cz> Link: https://lore.kernel.org/r/20201216101844.22917-4-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> conflicts: fs/ext4/file.c Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/ext4_jbd2.c | 1 - fs/ext4/file.c | 3 +++ fs/ext4/inode.c | 3 +++ fs/ext4/namei.c | 6 ++++++ fs/ext4/resize.c | 12 ++++++++++++ fs/ext4/super.c | 2 +- fs/ext4/xattr.c | 3 +++ 7 files changed, 28 insertions(+), 2 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 1a0a827a7f34..c7e410c4ab7d 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -379,7 +379,6 @@ 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 7b28d44b0ddd..41e2eababdaf 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -826,8 +826,11 @@ static int ext4_sample_last_mounted(struct super_block *sb, err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto out_journal; + lock_buffer(sbi->s_sbh); strncpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); 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 e6bed50e1786..769d06ba95d3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5150,7 +5150,10 @@ static int ext4_do_update_inode(handle_t *handle, err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ab7baf529917..8458079f61cc 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2984,7 +2984,10 @@ 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); @@ -3067,7 +3070,10 @@ 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 928700d57eb6..6155f2b9538c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -899,7 +899,10 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, EXT4_SB(sb)->s_gdb_count++; ext4_kvfree_array_rcu(o_group_desc); + lock_buffer(EXT4_SB(sb)->s_sbh); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); @@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb, reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); + lock_buffer(sbi->s_sbh); ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * @@ -1421,6 +1425,8 @@ 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); + unlock_buffer(sbi->s_sbh); /* Update the free space counts */ percpu_counter_add(&sbi->s_freeclusters_counter, @@ -1717,8 +1723,11 @@ static int ext4_group_extend_no_check(struct super_block *sb, goto errout; } + lock_buffer(EXT4_SB(sb)->s_sbh); 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); + unlock_buffer(EXT4_SB(sb)->s_sbh); 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 */ @@ -1874,10 +1883,13 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) if (err) goto errout; + lock_buffer(sbi->s_sbh); ext4_clear_feature_resize_inode(sb); 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); + unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_super(handle, sb); if (err) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a1f7bf52ed2f..3e7bbf4c5b19 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5447,6 +5447,7 @@ static int ext4_commit_super(struct super_block *sb) if (block_device_ejected(sb)) return -ENODEV; + lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -5518,7 +5519,6 @@ static int ext4_commit_super(struct super_block *sb) BUFFER_TRACE(sbh, "marking dirty"); ext4_superblock_csum_set(sb); - lock_buffer(sbh); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 5462f26907c1..8b9ce0f9502f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -792,7 +792,10 @@ 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) { + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_dirty_super(handle, sb); } } -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.11-rc4 commit e92ad03fa53498f12b3f5ecb8822adc3bf815b28 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- No behavioral change. Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20201216101844.22917-6-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1a871738cf4d..713a2f210966 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5479,8 +5479,8 @@ static int ext4_load_journal(struct super_block *sb, static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *sbh = sbi->s_sbh; lock_buffer(sbh); /* @@ -5497,21 +5497,20 @@ static void ext4_update_super(struct super_block *sb) ext4_update_tstamp(es, s_wtime); if (sb->s_bdev->bd_part) es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); + sbi->s_sectors_written_start) >> 1)); else - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) + es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written); + if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, - EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeclusters_counter))); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter)) + EXT4_C2B(sbi, percpu_counter_sum_positive( + &sbi->s_freeclusters_counter))); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); + &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { -- 2.22.0

From: Jan Kara <jack@suse.cz> mainline inclusion from mainline-v5.12-rc4 commit 2a4ae3bcdf05b8639406eaa09a2939f3c6dd8e75 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- When filesystem mount fails because of corrupted filesystem we first cancel the s_err_report timer reminding fs errors every day and only then we flush s_error_work. However s_error_work may report another fs error and re-arm timer thus resulting in timer use-after-free. Fix the problem by first flushing the work and only after that canceling the s_err_report timer. Reported-by: syzbot+628472a2aac693ab0fcd@syzkaller.appspotmail.com Fixes: 2d01ddc86606 ("ext4: save error info to sb through journal if available") CC: stable@vger.kernel.org Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210315165906.2175-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 713a2f210966..18b724390a74 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5148,8 +5148,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: - del_timer_sync(&sbi->s_err_report); flush_work(&sbi->s_error_work); + del_timer_sync(&sbi->s_err_report); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: -- 2.22.0

From: Mauricio Faria de Oliveira <mfo@canonical.com> mainline inclusion from mainline-5.12-rc1 commit 4ceddce55eb35d15b0f87f5dcf6f0058fd15d3a4 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- There's an I/O error on fsync() in a detached loop device if it has been previously attached. The issue is write cache is enabled in the attach path in loop_configure() but it isn't disabled in the detach path; thus it remains enabled in the block device regardless of whether it is attached or not. Now fsync() can get an I/O request that will just be failed later in loop_queue_rq() as device's state is not 'Lo_bound'. So, disable write cache in the detach path. Do so based on the queue flag, not the loop device flag for read-only (used to enable) as the queue flag can be changed via sysfs even on read-only loop devices (e.g., losetup -r.) Test-case: # DEV=/dev/loop7 # IMG=/tmp/image # truncate --size 1M $IMG # losetup $DEV $IMG # losetup -d $DEV Before: # strace -e fsync parted -s $DEV print 2>&1 | grep fsync fsync(3) = -1 EIO (Input/output error) Warning: Error fsyncing/closing /dev/loop7: Input/output error [ 982.529929] blk_update_request: I/O error, dev loop7, sector 0 op 0x1:(WRITE) flags 0x800 phys_seg 0 prio class 0 After: # strace -e fsync parted -s $DEV print 2>&1 | grep fsync fsync(3) = 0 Co-developed-by: Eric Desrochers <eric.desrochers@canonical.com> Signed-off-by: Eric Desrochers <eric.desrochers@canonical.com> Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com> Tested-by: Gabriel Krisman Bertazi <krisman@collabora.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Yufen Yu <yuyufen@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/block/loop.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a58084c2ed7c..cd13c0eb3f63 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1223,6 +1223,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) goto out_unlock; } + if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) + blk_queue_write_cache(lo->lo_queue, false, false); + /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); -- 2.22.0

From: "Matthew Wilcox (Oracle)" <willy@infradead.org> mainline inclusion from mainline-v5.12-rc3 commit 61cf93700fe6359552848ed5e3becba6cd760efa category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- You can't call idr_remove() from within a idr_for_each() callback, but you can call xa_erase() from an xa_for_each() loop, so switch the entire personality_idr from the IDR to the XArray. This manifests as a use-after-free as idr_for_each() attempts to walk the rest of the node after removing the last entry from it. Fixes: 071698e13ac6 ("io_uring: allow registering credentials") Cc: stable@vger.kernel.org # 5.6+ Reported-by: yangerkun <yangerkun@huawei.com> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> [Pavel: rebased (creds load was moved into io_init_req())] Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/7ccff36e1375f2b0ebf73d957f037b43becc0dde.161521280... Signed-off-by: Jens Axboe <axboe@kernel.dk> Conflicts: fs/io_uring.c Signed-off-by: yangerkun <yangerkun@huawei.com> Reviewed-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/io_uring.c | 59 ++++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 29 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 706ecf330edc..01e1108c0d87 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -346,7 +346,8 @@ struct io_ring_ctx { struct idr io_buffer_idr; - struct idr personality_idr; + struct xarray personalities; + u32 pers_next; struct { unsigned cached_cq_tail; @@ -1212,7 +1213,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_completion(&ctx->ref_comp); init_completion(&ctx->sq_thread_comp); idr_init(&ctx->io_buffer_idr); - idr_init(&ctx->personality_idr); + xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); spin_lock_init(&ctx->completion_lock); @@ -6629,7 +6630,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (id) { struct io_identity *iod; - iod = idr_find(&ctx->personality_idr, id); + iod = xa_load(&ctx->personalities, id); if (unlikely(!iod)) return -EINVAL; refcount_inc(&iod->count); @@ -8445,7 +8446,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_sqe_files_unregister(ctx); io_eventfd_unregister(ctx); io_destroy_buffers(ctx); - idr_destroy(&ctx->personality_idr); #if defined(CONFIG_UNIX) if (ctx->ring_sock) { @@ -8509,7 +8509,7 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { struct io_identity *iod; - iod = idr_remove(&ctx->personality_idr, id); + iod = xa_erase(&ctx->personalities, id); if (iod) { put_cred(iod->creds); if (refcount_dec_and_test(&iod->count)) @@ -8520,14 +8520,6 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) return -EINVAL; } -static int io_remove_personalities(int id, void *p, void *data) -{ - struct io_ring_ctx *ctx = data; - - io_unregister_personality(ctx, id); - return 0; -} - static void io_ring_exit_work(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, @@ -8554,6 +8546,9 @@ static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { + unsigned long index; + struct io_identify *iod; + mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); /* if force is set, the ring is going away. always drop after that */ @@ -8574,7 +8569,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); - idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); + xa_for_each(&ctx->personalities, index, iod) + io_unregister_personality(ctx, index); /* * Do this upfront, so we won't have a grace period where the ring @@ -9137,11 +9133,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } #ifdef CONFIG_PROC_FS -static int io_uring_show_cred(int id, void *p, void *data) +static int io_uring_show_cred(struct seq_file *m, unsigned int id, + const struct io_identity *iod) { - struct io_identity *iod = p; const struct cred *cred = iod->creds; - struct seq_file *m = data; struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; @@ -9209,9 +9204,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, (unsigned int) buf->len); } - if (has_lock && !idr_is_empty(&ctx->personality_idr)) { + if (has_lock && !xa_empty(&ctx->personalities)) { + unsigned long index; + const struct io_identity *iod; + seq_printf(m, "Personalities:\n"); - idr_for_each(&ctx->personality_idr, io_uring_show_cred, m); + xa_for_each(&ctx->personalities, index, iod) + io_uring_show_cred(m, index, iod); } seq_printf(m, "PollList:\n"); spin_lock_irq(&ctx->completion_lock); @@ -9597,21 +9596,23 @@ static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) static int io_register_personality(struct io_ring_ctx *ctx) { - struct io_identity *id; + struct io_identity *iod; + u32 id; int ret; - id = kmalloc(sizeof(*id), GFP_KERNEL); - if (unlikely(!id)) + iod = kmalloc(sizeof(*iod), GFP_KERNEL); + if (unlikely(!iod)) return -ENOMEM; - io_init_identity(id); - id->creds = get_current_cred(); + io_init_identity(iod); + iod->creds = get_current_cred(); - ret = idr_alloc_cyclic(&ctx->personality_idr, id, 1, USHRT_MAX, GFP_KERNEL); - if (ret < 0) { - put_cred(id->creds); - kfree(id); - } + ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)iod, + XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); + if (!ret) + return id; + put_cred(iod->creds); + kfree(iod); return ret; } -- 2.22.0

From: Yang Jihong <yangjihong1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA -------------------------------- Commit 3a95200d3f89a ("arm_pmu: Change API to support 64bit counter values") changes the input "value" type from 32-bit to 64-bit, which introduces the following problem: ARMv7 PMU counters is 32-bit width, in big-endian mode, write counter uses high 32-bit, which writes an incorrect value. Before: Performance counter stats for 'ls': 2.22 msec task-clock # 0.675 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 49 page-faults # 0.022 M/sec 2150476593 cycles # 966.663 GHz 2148588788 instructions # 1.00 insn per cycle 2147745484 branches # 965435.074 M/sec 2147508540 branch-misses # 99.99% of all branches None of the above hw event counters are correct. After: Performance counter stats for 'ls': 2.09 msec task-clock # 0.681 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 46 page-faults # 0.022 M/sec 2807301 cycles # 1.344 GHz 1060159 instructions # 0.38 insn per cycle 250496 branches # 119.914 M/sec 23192 branch-misses # 9.26% of all branches Solution: "value" is forcibly converted to 32-bit type before being written to PMU register. Fixes: 3a95200d3f89a ("arm_pmu: Change API to support 64bit counter values") Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/perf_event_v7.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 2924d7910b10..eb2190477da1 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -773,10 +773,10 @@ static inline void armv7pmu_write_counter(struct perf_event *event, u64 value) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); } else if (idx == ARMV7_IDX_CYCLE_COUNTER) { - asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value)); + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value)); } else { armv7_pmnc_select_counter(idx); - asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value)); + asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value)); } } -- 2.22.0

From: Lorenzo Stoakes <lstoakes@gmail.com> mainline inclusion from mainline-v5.11-rc1 commit 470c61d70299b1826f56ff5fede10786798e3c14 category: bugfix issue: #I3ZXZF CVE: NA Refactor to adapt to commit ("mm/page_alloc: fix counting of managed_pages") Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- setup_per_zone_lowmem_reserve() iterates through each zone setting zone->lowmem_reserve[j] = 0 (where j is the zone's index) then iterates backwards through all preceding zones, setting lower_zone->lowmem_reserve[j] = sum(managed pages of higher zones) / lowmem_reserve_ratio[idx] for each (where idx is the lower zone's index). If the lower zone has no managed pages or its ratio is 0 then all of its lowmem_reserve[] entries are effectively zeroed. As these arrays are only assigned here and all lowmem_reserve[] entries for index < this zone's index are implicitly assumed to be 0 (as these are specifically output in show_free_areas() and zoneinfo_show_print() for example) there is no need to additionally zero index == this zone's index too. This patch avoids zeroing unnecessarily. Rather than iterating through zones and setting lowmem_reserve[j] for each lower zone this patch reverse the process and populates each zone's lowmem_reserve[] values in ascending order. This clarifies what is going on especially in the case of zero managed pages or ratio which is now explicitly shown to clear these values. Link: https://lkml.kernel.org/r/20201129162758.115907-1-lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Baoquan He <bhe@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: yangerkun <yangerkun@huawei.com> Signed-off-by: Liu Shixin <liushixin2@huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/page_alloc.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 423f97a1120c..dc4cc71235aa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7786,31 +7786,24 @@ static void calculate_totalreserve_pages(void) static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - enum zone_type j, idx; + enum zone_type i, j; for_each_online_pgdat(pgdat) { - for (j = 0; j < MAX_NR_ZONES; j++) { - struct zone *zone = pgdat->node_zones + j; - unsigned long managed_pages = zone_managed_pages(zone); - - zone->lowmem_reserve[j] = 0; - - idx = j; - while (idx) { - struct zone *lower_zone; - - idx--; - lower_zone = pgdat->node_zones + idx; - - if (!sysctl_lowmem_reserve_ratio[idx] || - !zone_managed_pages(lower_zone)) { - lower_zone->lowmem_reserve[j] = 0; - continue; + for (i = 0; i < MAX_NR_ZONES - 1; i++) { + struct zone *zone = &pgdat->node_zones[i]; + int ratio = sysctl_lowmem_reserve_ratio[i]; + bool clear = !ratio || !zone_managed_pages(zone); + unsigned long managed_pages = 0; + + for (j = i + 1; j < MAX_NR_ZONES; j++) { + if (clear) { + zone->lowmem_reserve[j] = 0; } else { - lower_zone->lowmem_reserve[j] = - managed_pages / sysctl_lowmem_reserve_ratio[idx]; + struct zone *upper_zone = &pgdat->node_zones[j]; + + managed_pages += zone_managed_pages(upper_zone); + zone->lowmem_reserve[j] = managed_pages / ratio; } - managed_pages += zone_managed_pages(lower_zone); } } } -- 2.22.0

From: Oscar Salvador <osalvador@suse.de> mainline inclusion from mainline-v5.11-rc1 commit 3f4b815a439adfb8f238335612c4b28bc10084d8 category: bugfix issue: #I3ZXZF CVE: NA During LTP test, testcase 'move_pages12' failed. This is because __soft_offline_page() will return -EIO when fail to migrate page. This is not an error for 'move_pages12' but LTP treats 'return -EIO' as an error. Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Currently, we return -EIO when we fail to migrate the page. Migrations' failures are rather transient as they can happen due to several reasons, e.g: high page refcount bump, mapping->migrate_page failing etc. All meaning that at that time the page could not be migrated, but that has nothing to do with an EIO error. Let us return -EBUSY instead, as we do in case we failed to isolate the page. While are it, let us remove the "ret" print as its value does not change. Link: https://lkml.kernel.org/r/20201209092818.30417-1-osalvador@suse.de Signed-off-by: Oscar Salvador <osalvador@suse.de> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Shixin Liu <liushixin2@huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/memory-failure.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 25fb82320e3d..01445ddff58d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1856,11 +1856,11 @@ static int __soft_offline_page(struct page *page) pr_info("soft offline: %#lx: %s migration failed %d, type %lx (%pGp)\n", pfn, msg_page[huge], ret, page->flags, &page->flags); if (ret > 0) - ret = -EIO; + ret = -EBUSY; } } else { - pr_info("soft offline: %#lx: %s isolation failed: %d, page count %d, type %lx (%pGp)\n", - pfn, msg_page[huge], ret, page_count(page), page->flags, &page->flags); + pr_info("soft offline: %#lx: %s isolation failed, page count %d, type %lx (%pGp)\n", + pfn, msg_page[huge], page_count(page), page->flags, &page->flags); ret = -EBUSY; } return ret; -- 2.22.0

From: Linus Walleij <linus.walleij@linaro.org> mainline inclusion from mainline-5.11-rc1 commit d5d44e7e3507b0ad868f68e0c5bca6a57afa1b8b category: feature feature: ARM KASAN support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Disable instrumentation for arch/arm/boot/compressed/* since that code is executed before the kernel has even set up its mappings and definately out of scope for KASan. Disable instrumentation of arch/arm/vdso/* because that code is not linked with the kernel image, so the KASan management code would fail to link. Disable instrumentation of arch/arm/mm/physaddr.c. See commit ec6d06efb0ba ("arm64: Add support for CONFIG_DEBUG_VIRTUAL") for more details. Disable kasan check in the function unwind_pop_register because it does not matter that kasan checks failed when unwind_pop_register() reads the stack memory of a task. Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: kasan-dev@googlegroups.com Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Ard Biesheuvel <ardb@kernel.org> # QEMU/KVM/mach-virt/LPAE/8G Tested-by: Florian Fainelli <f.fainelli@gmail.com> # Brahma SoCs Tested-by: Ahmad Fatoum <a.fatoum@pengutronix.de> # i.MX6Q Reported-by: Florian Fainelli <f.fainelli@gmail.com> Reported-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Abbott Liu <liuwenliang@huawei.com> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> (cherry picked from commit d5d44e7e3507b0ad868f68e0c5bca6a57afa1b8b) Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/Makefile | 1 + arch/arm/kernel/unwind.c | 6 +++++- arch/arm/mm/Makefile | 2 ++ arch/arm/vdso/Makefile | 2 ++ 4 files changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 0d6ee56f5831..54307db7854d 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -24,6 +24,7 @@ OBJS += hyp-stub.o endif GCOV_PROFILE := n +KASAN_SANITIZE := n # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index d2bd0df2318d..f35eb584a18a 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -236,7 +236,11 @@ static int unwind_pop_register(struct unwind_ctrl_block *ctrl, if (*vsp >= (unsigned long *)ctrl->sp_high) return -URC_FAILURE; - ctrl->vrs[reg] = *(*vsp)++; + /* Use READ_ONCE_NOCHECK here to avoid this memory access + * from being tracked by KASAN. + */ + ctrl->vrs[reg] = READ_ONCE_NOCHECK(*(*vsp)); + (*vsp)++; return URC_OK; } diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 7cb1699fbfc4..99699c32d8a5 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -7,6 +7,7 @@ obj-y := extable.o fault.o init.o iomap.o obj-y += dma-mapping$(MMUEXT).o obj-$(CONFIG_MMU) += fault-armv.o flush.o idmap.o ioremap.o \ mmap.o pgd.o mmu.o pageattr.o +KASAN_SANITIZE_mmu.o := n ifneq ($(CONFIG_MMU),y) obj-y += nommu.o @@ -16,6 +17,7 @@ endif obj-$(CONFIG_ARM_PTDUMP_CORE) += dump.o obj-$(CONFIG_ARM_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_MODULES) += proc-syms.o +KASAN_SANITIZE_physaddr.o := n obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 150ce6e6a5d3..b558bee0e1f6 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -42,6 +42,8 @@ GCOV_PROFILE := n # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n +KASAN_SANITIZE := n + # Force dependency $(obj)/vdso.o : $(obj)/vdso.so -- 2.22.0

From: Linus Walleij <linus.walleij@linaro.org> mainline inclusion from mainline-5.11-rc1 commit c12366ba441da2f6f2b915410aca2b5b39c16514 category: feature feature: ARM KASAN support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Define KASAN_SHADOW_OFFSET,KASAN_SHADOW_START and KASAN_SHADOW_END for the Arm kernel address sanitizer. We are "stealing" lowmem (the 4GB addressable by a 32bit architecture) out of the virtual address space to use as shadow memory for KASan as follows: +----+ 0xffffffff | | | | |-> Static kernel image (vmlinux) BSS and page table | |/ +----+ PAGE_OFFSET | | | | |-> Loadable kernel modules virtual address space area | |/ +----+ MODULES_VADDR = KASAN_SHADOW_END | | | | |-> The shadow area of kernel virtual address. | |/ +----+-> TASK_SIZE (start of kernel space) = KASAN_SHADOW_START the | | shadow address of MODULES_VADDR | | | | | | | | |-> The user space area in lowmem. The kernel address | | | sanitizer do not use this space, nor does it map it. | | | | | | | | | | | | | |/ ------ 0 0 .. TASK_SIZE is the memory that can be used by shared userspace/kernelspace. It us used for userspace processes and for passing parameters and memory buffers in system calls etc. We do not need to shadow this area. KASAN_SHADOW_START: This value begins with the MODULE_VADDR's shadow address. It is the start of kernel virtual space. Since we have modules to load, we need to cover also that area with shadow memory so we can find memory bugs in modules. KASAN_SHADOW_END This value is the 0x100000000's shadow address: the mapping that would be after the end of the kernel memory at 0xffffffff. It is the end of kernel address sanitizer shadow area. It is also the start of the module area. KASAN_SHADOW_OFFSET: This value is used to map an address to the corresponding shadow address by the following formula: shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; As you would expect, >> 3 is equal to dividing by 8, meaning each byte in the shadow memory covers 8 bytes of kernel memory, so one bit shadow memory per byte of kernel memory is used. The KASAN_SHADOW_OFFSET is provided in a Kconfig option depending on the VMSPLIT layout of the system: the kernel and userspace can split up lowmem in different ways according to needs, so we calculate the shadow offset depending on this. When kasan is enabled, the definition of TASK_SIZE is not an 8-bit rotated constant, so we need to modify the TASK_SIZE access code in the *.s file. The kernel and modules may use different amounts of memory, according to the VMSPLIT configuration, which in turn determines the PAGE_OFFSET. We use the following KASAN_SHADOW_OFFSETs depending on how the virtual memory is split up: - 0x1f000000 if we have 1G userspace / 3G kernelspace split: - The kernel address space is 3G (0xc0000000) - PAGE_OFFSET is then set to 0x40000000 so the kernel static image (vmlinux) uses addresses 0x40000000 .. 0xffffffff - On top of that we have the MODULES_VADDR which under the worst case (using ARM instructions) is PAGE_OFFSET - 16M (0x01000000) = 0x3f000000 so the modules use addresses 0x3f000000 .. 0x3fffffff - So the addresses 0x3f000000 .. 0xffffffff need to be covered with shadow memory. That is 0xc1000000 bytes of memory. - 1/8 of that is needed for its shadow memory, so 0x18200000 bytes of shadow memory is needed. We "steal" that from the remaining lowmem. - The KASAN_SHADOW_START becomes 0x26e00000, to KASAN_SHADOW_END at 0x3effffff. - Now we can calculate the KASAN_SHADOW_OFFSET for any kernel address as 0x3f000000 needs to map to the first byte of shadow memory and 0xffffffff needs to map to the last byte of shadow memory. Since: SHADOW_ADDR = (address >> 3) + KASAN_SHADOW_OFFSET 0x26e00000 = (0x3f000000 >> 3) + KASAN_SHADOW_OFFSET KASAN_SHADOW_OFFSET = 0x26e00000 - (0x3f000000 >> 3) KASAN_SHADOW_OFFSET = 0x26e00000 - 0x07e00000 KASAN_SHADOW_OFFSET = 0x1f000000 - 0x5f000000 if we have 2G userspace / 2G kernelspace split: - The kernel space is 2G (0x80000000) - PAGE_OFFSET is set to 0x80000000 so the kernel static image uses 0x80000000 .. 0xffffffff. - On top of that we have the MODULES_VADDR which under the worst case (using ARM instructions) is PAGE_OFFSET - 16M (0x01000000) = 0x7f000000 so the modules use addresses 0x7f000000 .. 0x7fffffff - So the addresses 0x7f000000 .. 0xffffffff need to be covered with shadow memory. That is 0x81000000 bytes of memory. - 1/8 of that is needed for its shadow memory, so 0x10200000 bytes of shadow memory is needed. We "steal" that from the remaining lowmem. - The KASAN_SHADOW_START becomes 0x6ee00000, to KASAN_SHADOW_END at 0x7effffff. - Now we can calculate the KASAN_SHADOW_OFFSET for any kernel address as 0x7f000000 needs to map to the first byte of shadow memory and 0xffffffff needs to map to the last byte of shadow memory. Since: SHADOW_ADDR = (address >> 3) + KASAN_SHADOW_OFFSET 0x6ee00000 = (0x7f000000 >> 3) + KASAN_SHADOW_OFFSET KASAN_SHADOW_OFFSET = 0x6ee00000 - (0x7f000000 >> 3) KASAN_SHADOW_OFFSET = 0x6ee00000 - 0x0fe00000 KASAN_SHADOW_OFFSET = 0x5f000000 - 0x9f000000 if we have 3G userspace / 1G kernelspace split, and this is the default split for ARM: - The kernel address space is 1GB (0x40000000) - PAGE_OFFSET is set to 0xc0000000 so the kernel static image uses 0xc0000000 .. 0xffffffff. - On top of that we have the MODULES_VADDR which under the worst case (using ARM instructions) is PAGE_OFFSET - 16M (0x01000000) = 0xbf000000 so the modules use addresses 0xbf000000 .. 0xbfffffff - So the addresses 0xbf000000 .. 0xffffffff need to be covered with shadow memory. That is 0x41000000 bytes of memory. - 1/8 of that is needed for its shadow memory, so 0x08200000 bytes of shadow memory is needed. We "steal" that from the remaining lowmem. - The KASAN_SHADOW_START becomes 0xb6e00000, to KASAN_SHADOW_END at 0xbfffffff. - Now we can calculate the KASAN_SHADOW_OFFSET for any kernel address as 0xbf000000 needs to map to the first byte of shadow memory and 0xffffffff needs to map to the last byte of shadow memory. Since: SHADOW_ADDR = (address >> 3) + KASAN_SHADOW_OFFSET 0xb6e00000 = (0xbf000000 >> 3) + KASAN_SHADOW_OFFSET KASAN_SHADOW_OFFSET = 0xb6e00000 - (0xbf000000 >> 3) KASAN_SHADOW_OFFSET = 0xb6e00000 - 0x17e00000 KASAN_SHADOW_OFFSET = 0x9f000000 - 0x8f000000 if we have 3G userspace / 1G kernelspace with full 1 GB low memory (VMSPLIT_3G_OPT): - The kernel address space is 1GB (0x40000000) - PAGE_OFFSET is set to 0xb0000000 so the kernel static image uses 0xb0000000 .. 0xffffffff. - On top of that we have the MODULES_VADDR which under the worst case (using ARM instructions) is PAGE_OFFSET - 16M (0x01000000) = 0xaf000000 so the modules use addresses 0xaf000000 .. 0xaffffff - So the addresses 0xaf000000 .. 0xffffffff need to be covered with shadow memory. That is 0x51000000 bytes of memory. - 1/8 of that is needed for its shadow memory, so 0x0a200000 bytes of shadow memory is needed. We "steal" that from the remaining lowmem. - The KASAN_SHADOW_START becomes 0xa4e00000, to KASAN_SHADOW_END at 0xaeffffff. - Now we can calculate the KASAN_SHADOW_OFFSET for any kernel address as 0xaf000000 needs to map to the first byte of shadow memory and 0xffffffff needs to map to the last byte of shadow memory. Since: SHADOW_ADDR = (address >> 3) + KASAN_SHADOW_OFFSET 0xa4e00000 = (0xaf000000 >> 3) + KASAN_SHADOW_OFFSET KASAN_SHADOW_OFFSET = 0xa4e00000 - (0xaf000000 >> 3) KASAN_SHADOW_OFFSET = 0xa4e00000 - 0x15e00000 KASAN_SHADOW_OFFSET = 0x8f000000 - The default value of 0xffffffff for KASAN_SHADOW_OFFSET is an error value. We should always match one of the above shadow offsets. When we do this, TASK_SIZE will sometimes get a bit odd values that will not fit into immediate mov assembly instructions. To account for this, we need to rewrite some assembly using TASK_SIZE like this: - mov r1, #TASK_SIZE + ldr r1, =TASK_SIZE or - cmp r4, #TASK_SIZE + ldr r0, =TASK_SIZE + cmp r4, r0 this is done to avoid the immediate #TASK_SIZE that need to fit into a limited number of bits. Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport <rppt@linux.ibm.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Ard Biesheuvel <ardb@kernel.org> # QEMU/KVM/mach-virt/LPAE/8G Tested-by: Florian Fainelli <f.fainelli@gmail.com> # Brahma SoCs Tested-by: Ahmad Fatoum <a.fatoum@pengutronix.de> # i.MX6Q Reported-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Abbott Liu <liuwenliang@huawei.com> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> (cherry picked from commit c12366ba441da2f6f2b915410aca2b5b39c16514) Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- Documentation/arm/memory.rst | 5 ++ arch/arm/Kconfig | 9 ++++ arch/arm/include/asm/kasan_def.h | 81 ++++++++++++++++++++++++++++++ arch/arm/include/asm/memory.h | 5 ++ arch/arm/include/asm/uaccess-asm.h | 2 +- arch/arm/kernel/entry-armv.S | 3 +- arch/arm/kernel/entry-common.S | 9 ++-- arch/arm/mm/mmu.c | 18 +++++++ 8 files changed, 127 insertions(+), 5 deletions(-) create mode 100644 arch/arm/include/asm/kasan_def.h diff --git a/Documentation/arm/memory.rst b/Documentation/arm/memory.rst index 34bb23c44a71..0cb1e2938823 100644 --- a/Documentation/arm/memory.rst +++ b/Documentation/arm/memory.rst @@ -77,6 +77,11 @@ MODULES_VADDR MODULES_END-1 Kernel module space Kernel modules inserted via insmod are placed here using dynamic mappings. +TASK_SIZE MODULES_VADDR-1 KASAn shadow memory when KASan is in use. + The range from MODULES_VADDR to the top + of the memory is shadowed here with 1 bit + per byte of memory. + 00001000 TASK_SIZE-1 User space mappings Per-thread mappings are placed here via the mmap() system call. diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 002e0cf025f5..fc530fad13b2 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1324,6 +1324,15 @@ config PAGE_OFFSET default 0xB0000000 if VMSPLIT_3G_OPT default 0xC0000000 +config KASAN_SHADOW_OFFSET + hex + depends on KASAN + default 0x1f000000 if PAGE_OFFSET=0x40000000 + default 0x5f000000 if PAGE_OFFSET=0x80000000 + default 0x9f000000 if PAGE_OFFSET=0xC0000000 + default 0x8f000000 if PAGE_OFFSET=0xB0000000 + default 0xffffffff + config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 diff --git a/arch/arm/include/asm/kasan_def.h b/arch/arm/include/asm/kasan_def.h new file mode 100644 index 000000000000..5739605aa7cf --- /dev/null +++ b/arch/arm/include/asm/kasan_def.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * arch/arm/include/asm/kasan_def.h + * + * Copyright (c) 2018 Huawei Technologies Co., Ltd. + * + * Author: Abbott Liu <liuwenliang@huawei.com> + */ + +#ifndef __ASM_KASAN_DEF_H +#define __ASM_KASAN_DEF_H + +#ifdef CONFIG_KASAN + +/* + * Define KASAN_SHADOW_OFFSET,KASAN_SHADOW_START and KASAN_SHADOW_END for + * the Arm kernel address sanitizer. We are "stealing" lowmem (the 4GB + * addressable by a 32bit architecture) out of the virtual address + * space to use as shadow memory for KASan as follows: + * + * +----+ 0xffffffff + * | | \ + * | | |-> Static kernel image (vmlinux) BSS and page table + * | |/ + * +----+ PAGE_OFFSET + * | | \ + * | | |-> Loadable kernel modules virtual address space area + * | |/ + * +----+ MODULES_VADDR = KASAN_SHADOW_END + * | | \ + * | | |-> The shadow area of kernel virtual address. + * | |/ + * +----+-> TASK_SIZE (start of kernel space) = KASAN_SHADOW_START the + * | |\ shadow address of MODULES_VADDR + * | | | + * | | | + * | | |-> The user space area in lowmem. The kernel address + * | | | sanitizer do not use this space, nor does it map it. + * | | | + * | | | + * | | | + * | | | + * | |/ + * ------ 0 + * + * 1) KASAN_SHADOW_START + * This value begins with the MODULE_VADDR's shadow address. It is the + * start of kernel virtual space. Since we have modules to load, we need + * to cover also that area with shadow memory so we can find memory + * bugs in modules. + * + * 2) KASAN_SHADOW_END + * This value is the 0x100000000's shadow address: the mapping that would + * be after the end of the kernel memory at 0xffffffff. It is the end of + * kernel address sanitizer shadow area. It is also the start of the + * module area. + * + * 3) KASAN_SHADOW_OFFSET: + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * + * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; + * + * As you would expect, >> 3 is equal to dividing by 8, meaning each + * byte in the shadow memory covers 8 bytes of kernel memory, so one + * bit shadow memory per byte of kernel memory is used. + * + * The KASAN_SHADOW_OFFSET is provided in a Kconfig option depending + * on the VMSPLIT layout of the system: the kernel and userspace can + * split up lowmem in different ways according to needs, so we calculate + * the shadow offset depending on this. + */ + +#define KASAN_SHADOW_SCALE_SHIFT 3 +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_END ((UL(1) << (32 - KASAN_SHADOW_SCALE_SHIFT)) \ + + KASAN_SHADOW_OFFSET) +#define KASAN_SHADOW_START ((KASAN_SHADOW_END >> 3) + KASAN_SHADOW_OFFSET) + +#endif +#endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index f717d7122d9d..38a163f50130 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -18,6 +18,7 @@ #ifdef CONFIG_NEED_MACH_MEMORY_H #include <mach/memory.h> #endif +#include <asm/kasan_def.h> /* PAGE_OFFSET - the virtual address of the start of the kernel image */ #define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) @@ -28,7 +29,11 @@ * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area */ +#ifndef CONFIG_KASAN #define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M)) +#else +#define TASK_SIZE (KASAN_SHADOW_START) +#endif #define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M) /* diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h index 907571fd05c6..e6eb7a2aaf1e 100644 --- a/arch/arm/include/asm/uaccess-asm.h +++ b/arch/arm/include/asm/uaccess-asm.h @@ -85,7 +85,7 @@ */ .macro uaccess_entry, tsk, tmp0, tmp1, tmp2, disable ldr \tmp1, [\tsk, #TI_ADDR_LIMIT] - mov \tmp2, #TASK_SIZE + ldr \tmp2, =TASK_SIZE str \tmp2, [\tsk, #TI_ADDR_LIMIT] DACR( mrc p15, 0, \tmp0, c3, c0, 0) DACR( str \tmp0, [sp, #SVC_DACR]) diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 1c9e6d1452c5..0ea8529a4872 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -406,7 +406,8 @@ ENDPROC(__fiq_abt) @ if it was interrupted in a critical region. Here we @ perform a quick test inline since it should be false @ 99.9999% of the time. The rest is done out of line. - cmp r4, #TASK_SIZE + ldr r0, =TASK_SIZE + cmp r4, r0 blhs kuser_cmpxchg64_fixup #endif #endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 271cb8a1eba1..fee279e28a72 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -50,7 +50,8 @@ __ret_fast_syscall: UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK @@ -87,7 +88,8 @@ __ret_fast_syscall: #endif disable_irq_notrace @ disable interrupts ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK @@ -128,7 +130,8 @@ ret_slow_syscall: disable_irq_notrace @ disable interrupts ENTRY(ret_to_user_from_irq) ldr r2, [tsk, #TI_ADDR_LIMIT] - cmp r2, #TASK_SIZE + ldr r1, =TASK_SIZE + cmp r2, r1 blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index fa259825310c..c06ebfbc48c4 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -29,6 +29,7 @@ #include <asm/procinfo.h> #include <asm/memory.h> #include <asm/pgalloc.h> +#include <asm/kasan_def.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -1255,8 +1256,25 @@ static inline void prepare_page_table(void) /* * Clear out all the mappings below the kernel image. */ +#ifdef CONFIG_KASAN + /* + * KASan's shadow memory inserts itself between the TASK_SIZE + * and MODULES_VADDR. Do not clear the KASan shadow memory mappings. + */ + for (addr = 0; addr < KASAN_SHADOW_START; addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); + /* + * Skip over the KASan shadow area. KASAN_SHADOW_END is sometimes + * equal to MODULES_VADDR and then we exit the pmd clearing. If we + * are using a thumb-compiled kernel, there there will be 8MB more + * to clear as KASan always offset to 16 MB below MODULES_VADDR. + */ + for (addr = KASAN_SHADOW_END; addr < MODULES_VADDR; addr += PMD_SIZE) + pmd_clear(pmd_off_k(addr)); +#else for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); +#endif #ifdef CONFIG_XIP_KERNEL /* The XIP kernel is mapped in the module area -- skip over it */ -- 2.22.0

From: Linus Walleij <linus.walleij@linaro.org> mainline inclusion from mainline-5.11-rc1 commit 421015713b306e47af95d4d61cdfbd96d462e4cb category: feature feature: ARM KASAN support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- This patch enables the kernel address sanitizer for ARM. XIP_KERNEL has not been tested and is therefore not allowed for now. Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: kasan-dev@googlegroups.com Acked-by: Dmitry Vyukov <dvyukov@google.com> Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Tested-by: Ard Biesheuvel <ardb@kernel.org> # QEMU/KVM/mach-virt/LPAE/8G Tested-by: Florian Fainelli <f.fainelli@gmail.com> # Brahma SoCs Tested-by: Ahmad Fatoum <a.fatoum@pengutronix.de> # i.MX6Q Signed-off-by: Abbott Liu <liuwenliang@huawei.com> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> (cherry picked from commit 421015713b306e47af95d4d61cdfbd96d462e4cb) Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- Documentation/dev-tools/kasan.rst | 4 ++-- Documentation/features/debug/KASAN/arch-support.txt | 2 +- arch/arm/Kconfig | 1 + 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 2b68addaadcd..b3e489064a18 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -18,8 +18,8 @@ out-of-bounds accesses for global variables is only supported since Clang 11. Tag-based KASAN is only supported in Clang. -Currently generic KASAN is supported for the x86_64, arm64, xtensa, s390 and -riscv architectures, and tag-based KASAN is supported only for arm64. +Currently generic KASAN is supported for the x86_64, arm, arm64, xtensa, s390 +and riscv architectures, and tag-based KASAN is supported only for arm64. Usage ----- diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt index c3fe9b266e7b..b2288dc14b72 100644 --- a/Documentation/features/debug/KASAN/arch-support.txt +++ b/Documentation/features/debug/KASAN/arch-support.txt @@ -8,7 +8,7 @@ ----------------------- | alpha: | TODO | | arc: | TODO | - | arm: | TODO | + | arm: | ok | | arm64: | ok | | c6x: | TODO | | csky: | TODO | diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fc530fad13b2..5516dd83409e 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -68,6 +68,7 @@ config ARM select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 4d576cab16f57e1f87978f6997a725179398341e category: feature feature: ARM KASAN support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- KASAN uses the routines in stacktrace.c to capture the call stack each time memory gets allocated or freed. Some of these routines are also used to log CPU and memory context when exceptions are taken, and so in some cases, memory accesses may be made that are not strictly in line with the KASAN constraints, and may therefore trigger false KASAN positives. So follow the example set by other architectures, and simply disable KASAN instrumentation for these routines. Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> (cherry picked from commit 4d576cab16f57e1f87978f6997a725179398341e) Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/Makefile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 89e5d864e923..f6431b46866e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -21,6 +21,9 @@ obj-y := elf.o entry-common.o irq.o opcodes.o \ setup.o signal.o sigreturn_codes.o \ stacktrace.o sys_arm.o time.o traps.o +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_traps.o := n + ifneq ($(CONFIG_ARM_UNWIND),y) obj-$(CONFIG_FRAME_POINTER) += return_address.o endif -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit eae78e1a97201a81a851342ad9659b60f61a3951 category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Move the phys2virt patching code into a separate .S file before doing some work on it. Suggested-by: Nicolas Pitre <nico@fluxnic.net> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit eae78e1a97201a81a851342ad9659b60f61a3951) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/Makefile | 1 + arch/arm/kernel/head.S | 138 -------------------------------- arch/arm/kernel/phys2virt.S | 151 ++++++++++++++++++++++++++++++++++++ 3 files changed, 152 insertions(+), 138 deletions(-) create mode 100644 arch/arm/kernel/phys2virt.S diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index f6431b46866e..c38c8b019d24 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -95,6 +95,7 @@ obj-$(CONFIG_PARAVIRT) += paravirt.o head-y := head$(MMUEXT).o obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_ARM_PATCH_PHYS_VIRT) += phys2virt.o # This is executed very early using a temporary stack when no memory allocator # nor global data is available. Everything has to be allocated on the stack. diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 4af5c7679624..dbc409a66555 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -585,142 +585,4 @@ ENTRY(fixup_smp) ldmfd sp!, {r4 - r6, pc} ENDPROC(fixup_smp) -#ifdef __ARMEB__ -#define LOW_OFFSET 0x4 -#define HIGH_OFFSET 0x0 -#else -#define LOW_OFFSET 0x0 -#define HIGH_OFFSET 0x4 -#endif - -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT - -/* __fixup_pv_table - patch the stub instructions with the delta between - * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and - * can be expressed by an immediate shifter operand. The stub instruction - * has a form of '(add|sub) rd, rn, #imm'. - */ - __HEAD -__fixup_pv_table: - adr r0, 1f - ldmia r0, {r3-r7} - mvn ip, #0 - subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET - add r4, r4, r3 @ adjust table start address - add r5, r5, r3 @ adjust table end address - add r6, r6, r3 @ adjust __pv_phys_pfn_offset address - add r7, r7, r3 @ adjust __pv_offset address - mov r0, r8, lsr #PAGE_SHIFT @ convert to PFN - str r0, [r6] @ save computed PHYS_OFFSET to __pv_phys_pfn_offset - strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits - mov r6, r3, lsr #24 @ constant for add/sub instructions - teq r3, r6, lsl #24 @ must be 16MiB aligned -THUMB( it ne @ cross section branch ) - bne __error - str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits - b __fixup_a_pv_table -ENDPROC(__fixup_pv_table) - - .align -1: .long . - .long __pv_table_begin - .long __pv_table_end -2: .long __pv_phys_pfn_offset - .long __pv_offset - - .text -__fixup_a_pv_table: - adr r0, 3f - ldr r6, [r0] - add r6, r6, r3 - ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word - ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word - mov r6, r6, lsr #24 - cmn r0, #1 -#ifdef CONFIG_THUMB2_KERNEL - moveq r0, #0x200000 @ set bit 21, mov to mvn instruction - lsls r6, #24 - beq 2f - clz r7, r6 - lsr r6, #24 - lsl r6, r7 - bic r6, #0x0080 - lsrs r7, #1 - orrcs r6, #0x0080 - orr r6, r6, r7, lsl #12 - orr r6, #0x4000 - b 2f -1: add r7, r3 - ldrh ip, [r7, #2] -ARM_BE8(rev16 ip, ip) - tst ip, #0x4000 - and ip, #0x8f00 - orrne ip, r6 @ mask in offset bits 31-24 - orreq ip, r0 @ mask in offset bits 7-0 -ARM_BE8(rev16 ip, ip) - strh ip, [r7, #2] - bne 2f - ldrh ip, [r7] -ARM_BE8(rev16 ip, ip) - bic ip, #0x20 - orr ip, ip, r0, lsr #16 -ARM_BE8(rev16 ip, ip) - strh ip, [r7] -2: cmp r4, r5 - ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 1b - bx lr -#else - moveq r0, #0x400000 @ set bit 22, mov to mvn instruction - b 2f -1: ldr ip, [r7, r3] -#ifdef CONFIG_CPU_ENDIAN_BE8 - @ in BE8, we load data in BE, but instructions still in LE - bic ip, ip, #0xff000000 - tst ip, #0x000f0000 @ check the rotation field - orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 - biceq ip, ip, #0x00004000 @ clear bit 22 - orreq ip, ip, r0, ror #8 @ mask in offset bits 7-0 -#else - bic ip, ip, #0x000000ff - tst ip, #0xf00 @ check the rotation field - orrne ip, ip, r6 @ mask in offset bits 31-24 - biceq ip, ip, #0x400000 @ clear bit 22 - orreq ip, ip, r0 @ mask in offset bits 7-0 -#endif - str ip, [r7, r3] -2: cmp r4, r5 - ldrcc r7, [r4], #4 @ use branch for delay slot - bcc 1b - ret lr -#endif -ENDPROC(__fixup_a_pv_table) - - .align -3: .long __pv_offset - -ENTRY(fixup_pv_table) - stmfd sp!, {r4 - r7, lr} - mov r3, #0 @ no offset - mov r4, r0 @ r0 = table start - add r5, r0, r1 @ r1 = table size - bl __fixup_a_pv_table - ldmfd sp!, {r4 - r7, pc} -ENDPROC(fixup_pv_table) - - .data - .align 2 - .globl __pv_phys_pfn_offset - .type __pv_phys_pfn_offset, %object -__pv_phys_pfn_offset: - .word 0 - .size __pv_phys_pfn_offset, . -__pv_phys_pfn_offset - - .globl __pv_offset - .type __pv_offset, %object -__pv_offset: - .quad 0 - .size __pv_offset, . -__pv_offset -#endif - #include "head-common.S" diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S new file mode 100644 index 000000000000..7c17fbfeeedd --- /dev/null +++ b/arch/arm/kernel/phys2virt.S @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 1994-2002 Russell King + * Copyright (c) 2003 ARM Limited + * All Rights Reserved + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/page.h> + +#ifdef __ARMEB__ +#define LOW_OFFSET 0x4 +#define HIGH_OFFSET 0x0 +#else +#define LOW_OFFSET 0x0 +#define HIGH_OFFSET 0x4 +#endif + +/* + * __fixup_pv_table - patch the stub instructions with the delta between + * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be + * 16MiB aligned. + * + * Called from head.S, which expects the following registers to be preserved: + * r1 = machine no, r2 = atags or dtb, + * r8 = phys_offset, r9 = cpuid, r10 = procinfo + */ + __HEAD +ENTRY(__fixup_pv_table) + adr r0, 1f + ldmia r0, {r3-r7} + mvn ip, #0 + subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET + add r4, r4, r3 @ adjust table start address + add r5, r5, r3 @ adjust table end address + add r6, r6, r3 @ adjust __pv_phys_pfn_offset address + add r7, r7, r3 @ adjust __pv_offset address + mov r0, r8, lsr #PAGE_SHIFT @ convert to PFN + str r0, [r6] @ save computed PHYS_OFFSET to __pv_phys_pfn_offset + strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits + mov r6, r3, lsr #24 @ constant for add/sub instructions + teq r3, r6, lsl #24 @ must be 16MiB aligned + bne 0f + str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits + b __fixup_a_pv_table +0: mov r0, r0 @ deadloop on error + b 0b +ENDPROC(__fixup_pv_table) + + .align +1: .long . + .long __pv_table_begin + .long __pv_table_end +2: .long __pv_phys_pfn_offset + .long __pv_offset + + .text +__fixup_a_pv_table: + adr r0, 3f + ldr r6, [r0] + add r6, r6, r3 + ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word + ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word + mov r6, r6, lsr #24 + cmn r0, #1 +#ifdef CONFIG_THUMB2_KERNEL + moveq r0, #0x200000 @ set bit 21, mov to mvn instruction + lsls r6, #24 + beq 2f + clz r7, r6 + lsr r6, #24 + lsl r6, r7 + bic r6, #0x0080 + lsrs r7, #1 + orrcs r6, #0x0080 + orr r6, r6, r7, lsl #12 + orr r6, #0x4000 + b 2f +1: add r7, r3 + ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) + tst ip, #0x4000 + and ip, #0x8f00 + orrne ip, r6 @ mask in offset bits 31-24 + orreq ip, r0 @ mask in offset bits 7-0 +ARM_BE8(rev16 ip, ip) + strh ip, [r7, #2] + bne 2f + ldrh ip, [r7] +ARM_BE8(rev16 ip, ip) + bic ip, #0x20 + orr ip, ip, r0, lsr #16 +ARM_BE8(rev16 ip, ip) + strh ip, [r7] +2: cmp r4, r5 + ldrcc r7, [r4], #4 @ use branch for delay slot + bcc 1b + bx lr +#else + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction + b 2f +1: ldr ip, [r7, r3] +#ifdef CONFIG_CPU_ENDIAN_BE8 + @ in BE8, we load data in BE, but instructions still in LE + bic ip, ip, #0xff000000 + tst ip, #0x000f0000 @ check the rotation field + orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 + biceq ip, ip, #0x00004000 @ clear bit 22 + orreq ip, ip, r0, ror #8 @ mask in offset bits 7-0 +#else + bic ip, ip, #0x000000ff + tst ip, #0xf00 @ check the rotation field + orrne ip, ip, r6 @ mask in offset bits 31-24 + biceq ip, ip, #0x400000 @ clear bit 22 + orreq ip, ip, r0 @ mask in offset bits 7-0 +#endif + str ip, [r7, r3] +2: cmp r4, r5 + ldrcc r7, [r4], #4 @ use branch for delay slot + bcc 1b + ret lr +#endif +ENDPROC(__fixup_a_pv_table) + + .align +3: .long __pv_offset + +ENTRY(fixup_pv_table) + stmfd sp!, {r4 - r7, lr} + mov r3, #0 @ no offset + mov r4, r0 @ r0 = table start + add r5, r0, r1 @ r1 = table size + bl __fixup_a_pv_table + ldmfd sp!, {r4 - r7, pc} +ENDPROC(fixup_pv_table) + + .data + .align 2 + .globl __pv_phys_pfn_offset + .type __pv_phys_pfn_offset, %object +__pv_phys_pfn_offset: + .word 0 + .size __pv_phys_pfn_offset, . -__pv_phys_pfn_offset + + .globl __pv_offset + .type __pv_offset, %object +__pv_offset: + .quad 0 + .size __pv_offset, . -__pv_offset -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 7a94849e81b5c10e71f0a555300313c2789d9b0d category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- The big and little endian versions of the ARM p2v patching routine only differ in the values of the constants, so factor those out into macros so that we only have one version of the logic sequence to maintain. Acked-by: Nicolas Pitre <nico@fluxnic.net> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 7a94849e81b5c10e71f0a555300313c2789d9b0d) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/phys2virt.S | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S index 8fb1f7bcc720..5031e5a2e78b 100644 --- a/arch/arm/kernel/phys2virt.S +++ b/arch/arm/kernel/phys2virt.S @@ -95,23 +95,25 @@ ARM_BE8(rev16 ip, ip) ARM_BE8(rev16 ip, ip) strh ip, [r7] #else - moveq r0, #0x400000 @ set bit 22, mov to mvn instruction - b .Lnext -.Lloop: ldr ip, [r7, r3] #ifdef CONFIG_CPU_ENDIAN_BE8 - @ in BE8, we load data in BE, but instructions still in LE - bic ip, ip, #0xff000000 - tst ip, #0x000f0000 @ check the rotation field - orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 - biceq ip, ip, #0x00004000 @ clear bit 22 - orreq ip, ip, r0, ror #8 @ mask in offset bits 7-0 +@ in BE8, we load data in BE, but instructions still in LE +#define PV_BIT22 0x00004000 +#define PV_IMM8_MASK 0xff000000 +#define PV_ROT_MASK 0x000f0000 #else - bic ip, ip, #0x000000ff - tst ip, #0xf00 @ check the rotation field - orrne ip, ip, r6 @ mask in offset bits 31-24 - biceq ip, ip, #0x400000 @ clear bit 22 - orreq ip, ip, r0 @ mask in offset bits 7-0 +#define PV_BIT22 0x00400000 +#define PV_IMM8_MASK 0x000000ff +#define PV_ROT_MASK 0xf00 #endif + + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction + b .Lnext +.Lloop: ldr ip, [r7, r3] + bic ip, ip, #PV_IMM8_MASK + tst ip, #PV_ROT_MASK @ check the rotation field + orrne ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 + biceq ip, ip, #PV_BIT22 @ clear bit 22 + orreq ip, ip, r0 ARM_BE8(, ror #8) @ mask in offset bits 7-0 (or bit 22) str ip, [r7, r3] #endif -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 2730e8eaa4f2baccc03296e0c5ee109c0673fe5f category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Free up a register in the p2v patching code by switching to relative references, which don't require keeping the phys-to-virt displacement live in a register. Acked-by: Nicolas Pitre <nico@fluxnic.net> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 2730e8eaa4f2baccc03296e0c5ee109c0673fe5f) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/include/asm/memory.h | 6 +++--- arch/arm/kernel/phys2virt.S | 18 +++++++----------- 2 files changed, 10 insertions(+), 14 deletions(-) diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 4201c10325d0..96814304a797 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -197,7 +197,7 @@ extern const void *__pv_table_begin, *__pv_table_end; __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 1b - .\n" \ " .popsection\n" \ : "=r" (to) \ : "r" (from), "I" (__PV_BITS_31_24)) @@ -206,7 +206,7 @@ extern const void *__pv_table_begin, *__pv_table_end; __asm__ volatile("@ __pv_stub_mov\n" \ "1: mov %R0, %1\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 1b - .\n" \ " .popsection\n" \ : "=r" (t) \ : "I" (__PV_BITS_7_0)) @@ -216,7 +216,7 @@ extern const void *__pv_table_begin, *__pv_table_end; "1: adds %Q0, %1, %2\n" \ " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b\n" \ + " .long 1b - .\n" \ " .popsection\n" \ : "+r" (y) \ : "r" (x), "I" (__PV_BITS_31_24) \ diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S index 5031e5a2e78b..8e4be15e1559 100644 --- a/arch/arm/kernel/phys2virt.S +++ b/arch/arm/kernel/phys2virt.S @@ -58,9 +58,7 @@ ENDPROC(__fixup_pv_table) .text __fixup_a_pv_table: - adr r0, 3f - ldr r6, [r0] - add r6, r6, r3 + adr_l r6, __pv_offset ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word mov r6, r6, lsr #24 @@ -78,7 +76,8 @@ __fixup_a_pv_table: orr r6, r6, r7, lsl #12 orr r6, #0x4000 b .Lnext -.Lloop: add r7, r3 +.Lloop: add r7, r4 + adds r4, #4 ldrh ip, [r7, #2] ARM_BE8(rev16 ip, ip) tst ip, #0x4000 @@ -108,28 +107,25 @@ ARM_BE8(rev16 ip, ip) moveq r0, #0x400000 @ set bit 22, mov to mvn instruction b .Lnext -.Lloop: ldr ip, [r7, r3] +.Lloop: ldr ip, [r7, r4] bic ip, ip, #PV_IMM8_MASK tst ip, #PV_ROT_MASK @ check the rotation field orrne ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 biceq ip, ip, #PV_BIT22 @ clear bit 22 orreq ip, ip, r0 ARM_BE8(, ror #8) @ mask in offset bits 7-0 (or bit 22) - str ip, [r7, r3] + str ip, [r7, r4] + add r4, r4, #4 #endif .Lnext: cmp r4, r5 - ldrcc r7, [r4], #4 @ use branch for delay slot + ldrcc r7, [r4] @ use branch for delay slot bcc .Lloop ret lr ENDPROC(__fixup_a_pv_table) - .align -3: .long __pv_offset - ENTRY(fixup_pv_table) stmfd sp!, {r4 - r7, lr} - mov r3, #0 @ no offset mov r4, r0 @ r0 = table start add r5, r0, r1 @ r1 = table size bl __fixup_a_pv_table -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit e8e00f5afb087912fb3edb225ee373aa6499bb79 category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- In preparation for reducing the phys-to-virt minimum relative alignment from 16 MiB to 2 MiB, switch to patchable sequences involving MOVW instructions that can more easily be manipulated to carry a 12-bit immediate. Note that the non-LPAE ARM sequence is not updated: MOVW may not be supported on non-LPAE platforms, and the sequence itself can be updated more easily to apply the 12 bits of displacement. For Thumb2, which has many more versions of opcodes, switch to a sequence that can be patched by the same patching code for both versions. Note that the Thumb2 opcodes for MOVW and MVN are unambiguous, and have no rotation bits in their immediate fields, so there is no need to use placeholder constants in the asm blocks. While at it, drop the 'volatile' qualifiers from the asm blocks: the code does not have any side effects that are invisible to the compiler, so it is free to omit these sequences if the outputs are not used. Suggested-by: Russell King <linux@armlinux.org.uk> Acked-by: Nicolas Pitre <nico@fluxnic.net> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit e8e00f5afb087912fb3edb225ee373aa6499bb79) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/include/asm/memory.h | 44 +++++++--- arch/arm/kernel/phys2virt.S | 147 +++++++++++++++++++++++++++------- 2 files changed, 148 insertions(+), 43 deletions(-) diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 96814304a797..47fb189d6234 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -193,6 +193,7 @@ extern const void *__pv_table_begin, *__pv_table_end; #define PHYS_OFFSET ((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT) #define PHYS_PFN_OFFSET (__pv_phys_pfn_offset) +#ifndef CONFIG_THUMB2_KERNEL #define __pv_stub(from,to,instr) \ __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ @@ -202,25 +203,45 @@ extern const void *__pv_table_begin, *__pv_table_end; : "=r" (to) \ : "r" (from), "I" (__PV_BITS_31_24)) -#define __pv_stub_mov_hi(t) \ - __asm__ volatile("@ __pv_stub_mov\n" \ - "1: mov %R0, %1\n" \ +#define __pv_add_carry_stub(x, y) \ + __asm__("@ __pv_add_carry_stub\n" \ + "0: movw %R0, #0\n" \ + " adds %Q0, %1, %R0, lsl #24\n" \ + "1: mov %R0, %2\n" \ + " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b - .\n" \ + " .long 0b - ., 1b - .\n" \ " .popsection\n" \ - : "=r" (t) \ - : "I" (__PV_BITS_7_0)) + : "=&r" (y) \ + : "r" (x), "I" (__PV_BITS_7_0) \ + : "cc") + +#else +#define __pv_stub(from,to,instr) \ + __asm__("@ __pv_stub\n" \ + "0: movw %0, #0\n" \ + " lsl %0, #24\n" \ + " " instr " %0, %1, %0\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 0b - .\n" \ + " .popsection\n" \ + : "=&r" (to) \ + : "r" (from)) #define __pv_add_carry_stub(x, y) \ - __asm__ volatile("@ __pv_add_carry_stub\n" \ - "1: adds %Q0, %1, %2\n" \ + __asm__("@ __pv_add_carry_stub\n" \ + "0: movw %R0, #0\n" \ + " lsls %R0, #24\n" \ + " adds %Q0, %1, %R0\n" \ + "1: mvn %R0, #0\n" \ " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b - .\n" \ + " .long 0b - ., 1b - .\n" \ " .popsection\n" \ - : "+r" (y) \ - : "r" (x), "I" (__PV_BITS_31_24) \ + : "=&r" (y) \ + : "r" (x) \ : "cc") +#endif static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x) { @@ -229,7 +250,6 @@ static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x) if (sizeof(phys_addr_t) == 4) { __pv_stub(x, t, "add"); } else { - __pv_stub_mov_hi(t); __pv_add_carry_stub(x, t); } return t; diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S index be8fb0d89877..a4e364689663 100644 --- a/arch/arm/kernel/phys2virt.S +++ b/arch/arm/kernel/phys2virt.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 1994-2002 Russell King - * Copyright (c) 2003 ARM Limited + * Copyright (c) 2003, 2020 ARM Limited * All Rights Reserved */ @@ -58,55 +58,140 @@ __fixup_a_pv_table: mov r6, r6, lsr #24 cmn r0, #1 #ifdef CONFIG_THUMB2_KERNEL + @ + @ The Thumb-2 versions of the patchable sequences are + @ + @ phys-to-virt: movw <reg>, #offset<31:24> + @ lsl <reg>, #24 + @ sub <VA>, <PA>, <reg> + @ + @ virt-to-phys (non-LPAE): movw <reg>, #offset<31:24> + @ lsl <reg>, #24 + @ add <PA>, <VA>, <reg> + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:24> + @ lsl <reg>, #24 + @ adds <PAlo>, <VA>, <reg> + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are MOVW + @ instructions, where we need to patch in the offset into the + @ second halfword of the opcode (the 16-bit immediate is encoded + @ as imm4:i:imm3:imm8) + @ + @ 15 11 10 9 4 3 0 15 14 12 11 8 7 0 + @ +-----------+---+-------------+------++---+------+----+------+ + @ MOVW | 1 1 1 1 0 | i | 1 0 0 1 0 0 | imm4 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+-------------+------++---+------+----+------+ + @ + @ In the LPAE case, we also need to patch in the high word of the + @ offset into the immediate field of the MOV instruction, or patch it + @ to a MVN instruction if the offset is negative. In this case, we + @ need to inspect the first halfword of the opcode, to check whether + @ it is MOVW or MOV/MVN, and to perform the MOV to MVN patching if + @ needed. The encoding of the immediate is rather complex for values + @ of i:imm3 != 0b0000, but fortunately, we never need more than 8 lower + @ order bits, which can be patched into imm8 directly (and i:imm3 + @ cleared) + @ + @ 15 11 10 9 5 0 15 14 12 11 8 7 0 + @ +-----------+---+---------------------++---+------+----+------+ + @ MOV | 1 1 1 1 0 | i | 0 0 0 1 0 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ MVN | 1 1 1 1 0 | i | 0 0 0 1 1 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+---------------------++---+------+----+------+ + @ moveq r0, #0x200000 @ set bit 21, mov to mvn instruction - lsls r6, #24 - beq .Lnext - clz r7, r6 - lsr r6, #24 - lsl r6, r7 - bic r6, #0x0080 - lsrs r7, #1 - orrcs r6, #0x0080 - orr r6, r6, r7, lsl #12 - orr r6, #0x4000 b .Lnext .Lloop: add r7, r4 - adds r4, #4 - ldrh ip, [r7, #2] -ARM_BE8(rev16 ip, ip) - tst ip, #0x4000 - and ip, #0x8f00 - orrne ip, r6 @ mask in offset bits 31-24 - orreq ip, r0 @ mask in offset bits 7-0 -ARM_BE8(rev16 ip, ip) - strh ip, [r7, #2] - bne .Lnext + adds r4, #4 @ clears Z flag +#ifdef CONFIG_ARM_LPAE ldrh ip, [r7] ARM_BE8(rev16 ip, ip) - bic ip, #0x20 - orr ip, ip, r0, lsr #16 + tst ip, #0x200 @ MOVW has bit 9 set, MVN has it clear + bne 0f @ skip to MOVW handling (Z flag is clear) + bic ip, #0x20 @ clear bit 5 (MVN -> MOV) + orr ip, ip, r0, lsr #16 @ MOV -> MVN if offset < 0 ARM_BE8(rev16 ip, ip) strh ip, [r7] + @ Z flag is set +0: +#endif + ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) + and ip, #0xf00 @ clear everything except Rd field + orreq ip, r0 @ Z flag set -> MOV/MVN -> patch in high bits + orrne ip, r6 @ Z flag clear -> MOVW -> patch in low bits +ARM_BE8(rev16 ip, ip) + strh ip, [r7, #2] #else #ifdef CONFIG_CPU_ENDIAN_BE8 @ in BE8, we load data in BE, but instructions still in LE -#define PV_BIT22 0x00004000 +#define PV_BIT24 0x00000001 #define PV_IMM8_MASK 0xff000000 -#define PV_ROT_MASK 0x000f0000 #else -#define PV_BIT22 0x00400000 +#define PV_BIT24 0x01000000 #define PV_IMM8_MASK 0x000000ff -#define PV_ROT_MASK 0xf00 #endif + @ + @ The ARM versions of the patchable sequences are + @ + @ phys-to-virt: sub <VA>, <PA>, #offset<31:24>, lsl #24 + @ + @ virt-to-phys (non-LPAE): add <PA>, <VA>, #offset<31:24>, lsl #24 + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:24> + @ adds <PAlo>, <VA>, <reg>, lsl #24 + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are ADD or SUB + @ instructions, where we need to patch in the offset into the + @ immediate field of the opcode, which is emitted with the correct + @ rotation value. (The effective value of the immediate is imm12<7:0> + @ rotated right by [2 * imm12<11:8>] bits) + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ ADD | cond | 0 0 1 0 1 0 0 0 | Rn | Rd | imm12 | + @ SUB | cond | 0 0 1 0 0 1 0 0 | Rn | Rd | imm12 | + @ MOV | cond | 0 0 1 1 1 0 1 0 | Rn | Rd | imm12 | + @ MVN | cond | 0 0 1 1 1 1 1 0 | Rn | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ + @ In the LPAE case, we use a MOVW instruction to carry the low offset + @ word, and patch in the high word of the offset into the immediate + @ field of the subsequent MOV instruction, or patch it to a MVN + @ instruction if the offset is negative. We can distinguish MOVW + @ instructions based on bits 23:22 of the opcode, and ADD/SUB can be + @ distinguished from MOV/MVN (all using the encodings above) using + @ bit 24. + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ MOVW | cond | 0 0 1 1 0 0 0 0 | imm4 | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ moveq r0, #0x400000 @ set bit 22, mov to mvn instruction b .Lnext .Lloop: ldr ip, [r7, r4] +#ifdef CONFIG_ARM_LPAE + tst ip, #PV_BIT24 @ ADD/SUB have bit 24 clear + beq 1f +ARM_BE8(rev ip, ip) + tst ip, #0xc00000 @ MOVW has bits 23:22 clear + bic ip, ip, #0x400000 @ clear bit 22 + bfc ip, #0, #12 @ clear imm12 field of MOV[W] instruction + orreq ip, ip, r6 @ MOVW -> mask in offset bits 31-24 + orrne ip, ip, r0 @ MOV -> mask in offset bits 7-0 (or bit 22) +ARM_BE8(rev ip, ip) + b 2f +1: +#endif bic ip, ip, #PV_IMM8_MASK - tst ip, #PV_ROT_MASK @ check the rotation field - orrne ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 - biceq ip, ip, #PV_BIT22 @ clear bit 22 - orreq ip, ip, r0 ARM_BE8(, ror #8) @ mask in offset bits 7-0 (or bit 22) + orr ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 +2: str ip, [r7, r4] add r4, r4, #4 #endif -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 62c4a2e202b18e1d7176875b7e7af240f340596b category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Replace the open coded PC relative offset calculations with a pair of adr_l invocations. This removes some open coded arithmetic involving virtual addresses, avoids literal pools on v7+, and slightly reduces the footprint of the code. Reviewed-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 62c4a2e202b18e1d7176875b7e7af240f340596b) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/head-common.S | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 89c80154b9ef..29b2eda136bb 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -173,11 +173,12 @@ ENDPROC(lookup_processor_type) * r9 = cpuid (preserved) */ __lookup_processor_type: - adr r3, __lookup_processor_type_data - ldmia r3, {r4 - r6} - sub r3, r3, r4 @ get offset between virt&phys - add r5, r5, r3 @ convert virt addresses to - add r6, r6, r3 @ physical address space + /* + * Look in <asm/procinfo.h> for information about the __proc_info + * structure. + */ + adr_l r5, __proc_info_begin + adr_l r6, __proc_info_end 1: ldmia r5, {r3, r4} @ value, mask and r4, r4, r9 @ mask wanted bits teq r3, r4 @@ -189,17 +190,6 @@ __lookup_processor_type: 2: ret lr ENDPROC(__lookup_processor_type) -/* - * Look in <asm/procinfo.h> for information about the __proc_info structure. - */ - .align 2 - .type __lookup_processor_type_data, %object -__lookup_processor_type_data: - .long . - .long __proc_info_begin - .long __proc_info_end - .size __lookup_processor_type_data, . - __lookup_processor_type_data - __error_lpae: #ifdef CONFIG_DEBUG_LL adr r0, str_lpae -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 91580f0dbf24c6d616091526a900213bc7aa48fe category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Replace the open coded PC relative offset calculations with adr_l and ldr_l invocations. This removes some open coded arithmetic involving virtual addresses, avoids literal pools on v7+, and slightly reduces the footprint of the code. Note that it also removes a stale comment about the contents of r6. Reviewed-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 91580f0dbf24c6d616091526a900213bc7aa48fe) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/head.S | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 205881bb0919..fcd998ba9c9a 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -382,10 +382,8 @@ ENTRY(secondary_startup) /* * Use the page tables supplied from __cpu_up. */ - adr r4, __secondary_data - ldmia r4, {r5, r7, r12} @ address to jump to after - sub lr, r4, r5 @ mmu has been enabled - add r3, r7, lr + adr_l r3, secondary_data + mov_l r12, __secondary_switched ldrd r4, r5, [r3, #0] @ get secondary_data.pgdir ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps @@ -400,22 +398,13 @@ ARM_BE8(eor r4, r4, r5) @ without using a temp reg. ENDPROC(secondary_startup) ENDPROC(secondary_startup_arm) - /* - * r6 = &secondary_data - */ ENTRY(__secondary_switched) - ldr sp, [r7, #12] @ get secondary_data.stack + ldr_l r7, secondary_data + 12 @ get secondary_data.stack + mov sp, r7 mov fp, #0 b secondary_start_kernel ENDPROC(__secondary_switched) - .align - - .type __secondary_data, %object -__secondary_data: - .long . - .long secondary_data - .long __secondary_switched #endif /* defined(CONFIG_SMP) */ -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 59d2f2827dfdccf8911d5e51465136b52ba623c4 category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Now that calling __do_fixup_smp_on_up() can be done without passing the physical-to-virtual offset in r3, we can replace the open coded PC relative offset calculations with a pair of adr_l invocations. This removes some open coded arithmetic involving virtual addresses, avoids literal pools on v7+, and slightly reduces the footprint of the code. Reviewed-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 59d2f2827dfdccf8911d5e51465136b52ba623c4) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/head.S | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index e87e0878b8f2..7adab03a31bc 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -519,19 +519,11 @@ ARM_BE8(rev r0, r0) @ byteswap if big endian retne lr __fixup_smp_on_up: - adr r0, 1f - ldmia r0, {r3 - r5} - sub r3, r0, r3 - add r4, r4, r3 - add r5, r5, r3 + adr_l r4, __smpalt_begin + adr_l r5, __smpalt_end b __do_fixup_smp_on_up ENDPROC(__fixup_smp) - .align -1: .word . - .word __smpalt_begin - .word __smpalt_end - .pushsection .data .align 2 .globl smp_on_up -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 3bcf906b194cebb6817cbb2f07b69e12aa5d7f51 category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Replace the open coded arithmetic with a simple adr_l/sub pair. This removes some open coded arithmetic involving virtual addresses, avoids literal pools on v7+, and slightly reduces the footprint of the code. Reviewed-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> (cherry picked from commit 3bcf906b194cebb6817cbb2f07b69e12aa5d7f51) Signed-off-by: Zhao Hongjiang <zhaohongjiang@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/head.S | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 7adab03a31bc..7f62c5eccdf3 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -103,10 +103,8 @@ ENTRY(stext) #endif #ifndef CONFIG_XIP_KERNEL - adr r3, 2f - ldmia r3, {r4, r8} - sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET) - add r8, r8, r4 @ PHYS_OFFSET + adr_l r8, _text @ __pa(_text) + sub r8, r8, #TEXT_OFFSET @ PHYS_OFFSET #else ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case #endif @@ -158,10 +156,6 @@ ENTRY(stext) 1: b __enable_mmu ENDPROC(stext) .ltorg -#ifndef CONFIG_XIP_KERNEL -2: .long . - .long PAGE_OFFSET -#endif /* * Setup the initial page tables. We only setup the barest -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-5.11-rc1 commit 6c7a6d22fcef9181239ea7248c6b0c4117b9325e category: feature issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Commit aaac3733171fca94 ("ARM: kvm: replace open coded VA->PA calculations with adr_l call") removed all uses of .L__boot_cpu_mode_offset, so there is no longer a need to define it. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Signed-off-by: Chen Jun <chenjun102@huawei.com> Acked-by: Xie XiuQi <xiexiuqi@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/hyp-stub.S | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index 103d0bdb2b7e..b699b22a4db1 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -225,12 +225,6 @@ ENTRY(__hyp_soft_restart) ret lr ENDPROC(__hyp_soft_restart) -#ifndef ZIMAGE -.align 2 -.L__boot_cpu_mode_offset: - .long __boot_cpu_mode - . -#endif - .align 5 ENTRY(__hyp_stub_vectors) __hyp_stub_reset: W(b) . -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit 6b12f315331362a8ec9e8fe3f97d9ae09e43fd28 category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=6b12f315331362a8ec9e8fe3f97d9ae09e43fd28 ------------------------------------------------- This replaces a couple of open coded calculations to obtain the physical address of a far symbol with calls to the new adr_l etc macros. Acked-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/mach-exynos/headsmp.S | 9 +-------- arch/arm/mach-exynos/sleep.S | 26 +++++--------------------- 2 files changed, 6 insertions(+), 29 deletions(-) diff --git a/arch/arm/mach-exynos/headsmp.S b/arch/arm/mach-exynos/headsmp.S index 0ac2cb9a7355..be7cd0eebe1d 100644 --- a/arch/arm/mach-exynos/headsmp.S +++ b/arch/arm/mach-exynos/headsmp.S @@ -19,10 +19,7 @@ ENTRY(exynos4_secondary_startup) ARM_BE8(setend be) mrc p15, 0, r0, c0, c0, 5 and r0, r0, #15 - adr r4, 1f - ldmia r4, {r5, r6} - sub r4, r4, r5 - add r6, r6, r4 + adr_l r6, exynos_pen_release pen: ldr r7, [r6] cmp r7, r0 bne pen @@ -33,7 +30,3 @@ pen: ldr r7, [r6] */ b secondary_startup ENDPROC(exynos4_secondary_startup) - - .align 2 -1: .long . - .long exynos_pen_release diff --git a/arch/arm/mach-exynos/sleep.S b/arch/arm/mach-exynos/sleep.S index ed93f91853b8..ed27515a4458 100644 --- a/arch/arm/mach-exynos/sleep.S +++ b/arch/arm/mach-exynos/sleep.S @@ -8,6 +8,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/assembler.h> #include <asm/hardware/cache-l2x0.h> #include "smc.h" @@ -54,19 +55,13 @@ ENTRY(exynos_cpu_resume_ns) cmp r0, r1 bne skip_cp15 - adr r0, _cp15_save_power - ldr r1, [r0] - ldr r1, [r0, r1] - adr r0, _cp15_save_diag - ldr r2, [r0] - ldr r2, [r0, r2] + ldr_l r1, cp15_save_power + ldr_l r2, cp15_save_diag mov r0, #SMC_CMD_C15RESUME dsb smc #0 #ifdef CONFIG_CACHE_L2X0 - adr r0, 1f - ldr r2, [r0] - add r0, r2, r0 + adr_l r0, l2x0_saved_regs /* Check that the address has been initialised. */ ldr r1, [r0, #L2X0_R_PHY_BASE] @@ -85,9 +80,7 @@ ENTRY(exynos_cpu_resume_ns) smc #0 /* Reload saved regs pointer because smc corrupts registers. */ - adr r0, 1f - ldr r2, [r0] - add r0, r2, r0 + adr_l r0, l2x0_saved_regs ldr r1, [r0, #L2X0_R_PWR_CTRL] ldr r2, [r0, #L2X0_R_AUX_CTRL] @@ -106,15 +99,6 @@ skip_cp15: b cpu_resume ENDPROC(exynos_cpu_resume_ns) - .align -_cp15_save_power: - .long cp15_save_power - . -_cp15_save_diag: - .long cp15_save_diag - . -#ifdef CONFIG_CACHE_L2X0 -1: .long l2x0_saved_regs - . -#endif /* CONFIG_CACHE_L2X0 */ - .data .align 2 .globl cp15_save_diag -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit e2aa765c4eb9bbcdd3046744e6f73050d1175138 category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=e2aa765c4eb9bbcdd3046744e6f73050d1175138 ------------------------------------------------- This replaces a few copies of the open coded calculations of the physical address of 'pen_release' in the secondary startup code of a couple of platforms. This ensures these quantities are invariant under runtime relocation. Cc: Russell King <linux@armlinux.org.uk> Acked-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/mach-prima2/headsmp.S | 11 +++-------- arch/arm/mach-spear/headsmp.S | 11 +++-------- arch/arm/plat-versatile/headsmp.S | 9 +-------- 3 files changed, 7 insertions(+), 24 deletions(-) diff --git a/arch/arm/mach-prima2/headsmp.S b/arch/arm/mach-prima2/headsmp.S index 88ea1243942a..e09dcaca320e 100644 --- a/arch/arm/mach-prima2/headsmp.S +++ b/arch/arm/mach-prima2/headsmp.S @@ -8,6 +8,8 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> + /* * SIRFSOC specific entry point for secondary CPUs. This provides * a "holding pen" into which all secondary cores are held until we're @@ -16,10 +18,7 @@ ENTRY(sirfsoc_secondary_startup) mrc p15, 0, r0, c0, c0, 5 and r0, r0, #15 - adr r4, 1f - ldmia r4, {r5, r6} - sub r4, r4, r5 - add r6, r6, r4 + adr_l r6, prima2_pen_release pen: ldr r7, [r6] cmp r7, r0 bne pen @@ -30,7 +29,3 @@ pen: ldr r7, [r6] */ b secondary_startup ENDPROC(sirfsoc_secondary_startup) - - .align -1: .long . - .long prima2_pen_release diff --git a/arch/arm/mach-spear/headsmp.S b/arch/arm/mach-spear/headsmp.S index 96f89436ccf6..32ffc75ff332 100644 --- a/arch/arm/mach-spear/headsmp.S +++ b/arch/arm/mach-spear/headsmp.S @@ -10,6 +10,8 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> + __INIT /* @@ -20,10 +22,7 @@ ENTRY(spear13xx_secondary_startup) mrc p15, 0, r0, c0, c0, 5 and r0, r0, #15 - adr r4, 1f - ldmia r4, {r5, r6} - sub r4, r4, r5 - add r6, r6, r4 + adr_l r6, spear_pen_release pen: ldr r7, [r6] cmp r7, r0 bne pen @@ -37,8 +36,4 @@ pen: ldr r7, [r6] * should now contain the SVC stack for this core */ b secondary_startup - - .align -1: .long . - .long spear_pen_release ENDPROC(spear13xx_secondary_startup) diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S index 09d9fc30c8ca..cec71853b0b3 100644 --- a/arch/arm/plat-versatile/headsmp.S +++ b/arch/arm/plat-versatile/headsmp.S @@ -18,10 +18,7 @@ ENTRY(versatile_secondary_startup) ARM_BE8(setend be) mrc p15, 0, r0, c0, c0, 5 bic r0, #0xff000000 - adr r4, 1f - ldmia r4, {r5, r6} - sub r4, r4, r5 - add r6, r6, r4 + adr_l r6, versatile_cpu_release pen: ldr r7, [r6] cmp r7, r0 bne pen @@ -31,8 +28,4 @@ pen: ldr r7, [r6] * should now contain the SVC stack for this core */ b secondary_startup - - .align -1: .long . - .long versatile_cpu_release ENDPROC(versatile_secondary_startup) -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit 04be01192973461cdd00ab47908a78f0e2f55ef8 category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=04be01192973461cdd00ab47908a78f0e2f55ef8 Update the Kconfig RELOCATABLE depends on !JUMP_LABEL to resolve compilation conflicts between fpic and JUMP_LABEL ------------------------------------------------- Update the build flags and linker script to allow vmlinux to be built as a PIE binary, which retains relocation information about absolute symbol references so that they can be fixed up at runtime. This will be used for implementing KASLR, Cc: Russell King <linux@armlinux.org.uk> Acked-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/Kconfig | 5 +++++ arch/arm/Makefile | 5 +++++ arch/arm/include/asm/assembler.h | 2 +- arch/arm/include/asm/vmlinux.lds.h | 6 +++++- arch/arm/kernel/vmlinux.lds.S | 6 ++++++ scripts/module.lds.S | 1 + 6 files changed, 23 insertions(+), 2 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 97f9d004e6d0..c856542174a7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1678,6 +1678,11 @@ config STACKPROTECTOR_PER_TASK Enable this option to switch to a different method that uses a different canary value for each task. +config RELOCATABLE + bool + depends on !XIP_KERNEL && !JUMP_LABEL + select HAVE_ARCH_PREL32_RELOCATIONS + endmenu menu "Boot options" diff --git a/arch/arm/Makefile b/arch/arm/Makefile index e15f76ca2887..4f550fc0e811 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -48,6 +48,11 @@ CHECKFLAGS += -D__ARMEL__ KBUILD_LDFLAGS += -EL endif +ifeq ($(CONFIG_RELOCATABLE),y) +KBUILD_CFLAGS += -fpic -include $(srctree)/include/linux/hidden.h +LDFLAGS_vmlinux += -pie -shared -Bsymbolic +endif + # # The Scalar Replacement of Aggregates (SRA) optimization pass in GCC 4.9 and # later may result in code being generated that handles signed short and signed diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index b6d5c0d83674..20993615087a 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -528,7 +528,7 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) * mov_l - move a constant value or [relocated] address into a register */ .macro mov_l, dst:req, imm:req - .if __LINUX_ARM_ARCH__ < 7 + .if CONFIG_RELOCATABLE == 1 || __LINUX_ARM_ARCH__ < 7 ldr \dst, =\imm .else movw \dst, #:lower16:\imm diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h index 4a91428c324d..c1ced85cd8e5 100644 --- a/arch/arm/include/asm/vmlinux.lds.h +++ b/arch/arm/include/asm/vmlinux.lds.h @@ -50,7 +50,11 @@ EXIT_CALL \ ARM_MMU_DISCARD(*(.text.fixup)) \ ARM_MMU_DISCARD(*(__ex_table)) \ - COMMON_DISCARDS + COMMON_DISCARDS \ + *(.ARM.exidx.discard.text) \ + *(.interp .dynamic) \ + *(.dynsym .dynstr .hash) + /* * Sections that should stay zero sized, which is safer to explicitly diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index f7f4620d59c3..262ba776d32d 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -115,6 +115,12 @@ SECTIONS __smpalt_end = .; } #endif + .rel.dyn : ALIGN(8) { + __rel_begin = .; + *(.rel .rel.* .rel.dyn) + } + __rel_end = ADDR(.rel.dyn) + SIZEOF(.rel.dyn); + .init.pv_table : { __pv_table_begin = .; *(.pv_table) diff --git a/scripts/module.lds.S b/scripts/module.lds.S index 69b9b71a6a47..088a5a2c446d 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -7,6 +7,7 @@ SECTIONS { /DISCARD/ : { *(.discard) *(.discard.*) + *(*.discard.*) } __ksymtab 0 : { *(SORT(___ksymtab+*)) } -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit 2c7e6b4d7cbff417ff96a24c243508e16168f90c category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=2c7e6b4d7cbff417ff96a24c243508e16168f90c ------------------------------------------------- Replace some unnecessary absolute references with relative ones. Cc: Russell King <linux@armlinux.org.uk> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/sleep.S | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index 43077e11dafd..7e64648654ae 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -61,15 +61,14 @@ ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} #ifdef MULTI_CPU - ldr r10, =processor - ldr r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state + ldr_l r4, processor + CPU_SLEEP_SIZE @ size of CPU sleep state #else - ldr r4, =cpu_suspend_size + adr_l r4, cpu_suspend_size #endif mov r5, sp @ current virtual SP add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn sub sp, sp, r4 @ allocate CPU state on stack - ldr r3, =sleep_save_sp + adr_l r3, sleep_save_sp stmfd sp!, {r0, r1} @ save suspend func arg and pointer ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] ALT_SMP(W(nop)) @ don't use adr_l inside ALT_SMP() -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit fe64d7efe89877bc52454f9f2bc9ab0ce01ae8fc category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=fe64d7efe89877bc52454f9f2bc9ab0ce01ae8fc ------------------------------------------------- The location of swapper_pg_dir is relative to the kernel, not to PAGE_OFFSET or PHYS_OFFSET. So define the symbol relative to the start of the kernel image, and refer to it via its name. Cc: Russell King <linux@armlinux.org.uk> Acked-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/head.S | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 7f62c5eccdf3..cd850e6c6b1a 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -45,14 +45,6 @@ #define PMD_ORDER 2 #endif - .globl swapper_pg_dir - .equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE - - .macro pgtbl, rd, phys - add \rd, \phys, #TEXT_OFFSET - sub \rd, \rd, #PG_DIR_SIZE - .endm - /* * Kernel startup entry point. * --------------------------- @@ -74,6 +66,9 @@ .arm __HEAD + .globl swapper_pg_dir + .equ swapper_pg_dir, . - PG_DIR_SIZE + ENTRY(stext) ARM_BE8(setend be ) @ ensure we are in BE8 mode @@ -169,7 +164,7 @@ ENDPROC(stext) * r4 = physical page table address */ __create_page_tables: - pgtbl r4, r8 @ page table address + adr_l r4, swapper_pg_dir @ page table address /* * Clear the swapper page table -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit c11744cd7b351b0fbc5233c04c32822544c96fc1 category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=c11744cd7b351b0fbc5233c04c32822544c96fc1 Update the Kconfig RANDOMIZE_BASE depends on !JUMP_LABEL to resolve compilation conflicts between fpic and JUMP_LABEL. ------------------------------------------------- This implements randomization of the placement of the kernel image inside the lowmem region. It is intended to work together with the decompressor to place the kernel at an offset in physical memory that is a multiple of 2 MB, and to take the same offset into account when creating the virtual mapping. This uses runtime relocation of the kernel built as a PIE binary, to fix up all absolute symbol references to refer to their runtime virtual address. The physical-to-virtual mapping remains unchanged. In order to allow the decompressor to hand over to the core kernel without making assumptions that are not guaranteed to hold when invoking the core kernel directly using bootloaders that are not KASLR aware, the KASLR offset is expected to be placed in r3 when entering the kernel 4 bytes past the entry point, skipping the first instruction. Cc: Russell King <linux@armlinux.org.uk> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/Kconfig | 12 +++++ arch/arm/kernel/head.S | 102 +++++++++++++++++++++++++++++++++++++---- 2 files changed, 105 insertions(+), 9 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c856542174a7..2f7a32b77282 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1683,6 +1683,18 @@ config RELOCATABLE depends on !XIP_KERNEL && !JUMP_LABEL select HAVE_ARCH_PREL32_RELOCATIONS +config RANDOMIZE_BASE + bool "Randomize the address of the kernel image" + depends on MMU && AUTO_ZRELADDR + depends on !XIP_KERNEL && !ZBOOT_ROM && !JUMP_LABEL + select RELOCATABLE + select ARM_MODULE_PLTS if MODULES + select MODULE_REL_CRCS if MODVERSIONS + help + Randomizes the virtual and physical address at which the kernel + image is loaded, as a security feature that deters exploit attempts + relying on knowledge of the location of kernel internals. + endmenu menu "Boot options" diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index cd850e6c6b1a..26f3e9a0ffe9 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -45,6 +45,28 @@ #define PMD_ORDER 2 #endif + .macro get_kaslr_offset, reg +#ifdef CONFIG_RANDOMIZE_BASE + ldr_l \reg, __kaslr_offset +#else + mov \reg, #0 +#endif + .endm + + .macro add_kaslr_offset, reg, tmp +#ifdef CONFIG_RANDOMIZE_BASE + get_kaslr_offset \tmp + add \reg, \reg, \tmp +#endif + .endm + + .macro sub_kaslr_offset, reg, tmp +#ifdef CONFIG_RANDOMIZE_BASE + get_kaslr_offset \tmp + sub \reg, \reg, \tmp +#endif + .endm + /* * Kernel startup entry point. * --------------------------- @@ -70,6 +92,7 @@ .equ swapper_pg_dir, . - PG_DIR_SIZE ENTRY(stext) + mov r3, #0 @ normal entry point - clear r3 ARM_BE8(setend be ) @ ensure we are in BE8 mode THUMB( badr r9, 1f ) @ Kernel is always entered in ARM. @@ -77,6 +100,16 @@ ENTRY(stext) THUMB( .thumb ) @ switch to Thumb now. THUMB(1: ) +#ifdef CONFIG_RANDOMIZE_BASE + str_l r3, __kaslr_offset, r9 @ offset in r3 if entered via kaslr ep + + .section ".bss", "aw", %nobits + .align 2 +__kaslr_offset: + .long 0 @ will be wiped before entering C code + .previous +#endif + #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install #endif @@ -100,6 +133,7 @@ ENTRY(stext) #ifndef CONFIG_XIP_KERNEL adr_l r8, _text @ __pa(_text) sub r8, r8, #TEXT_OFFSET @ PHYS_OFFSET + sub_kaslr_offset r8, r12 #else ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case #endif @@ -136,8 +170,8 @@ ENTRY(stext) * r0 will hold the CPU control register value, r1, r2, r4, and * r9 will be preserved. r5 will also be preserved if LPAE. */ - ldr r13, =__mmap_switched @ address to jump to after - @ mmu has been enabled + adr_l lr, __primary_switch @ address to jump to after + mov r13, lr @ mmu has been enabled badr lr, 1f @ return (PIC) address #ifdef CONFIG_ARM_LPAE mov r5, #0 @ high TTBR0 @@ -148,7 +182,8 @@ ENTRY(stext) ldr r12, [r10, #PROCINFO_INITFUNC] add r12, r12, r10 ret r12 -1: b __enable_mmu +1: get_kaslr_offset r12 @ get before turning MMU on + b __enable_mmu ENDPROC(stext) .ltorg @@ -227,9 +262,14 @@ __create_page_tables: /* * Map our RAM from the start to the end of the kernel .bss section. */ - add r0, r4, #PAGE_OFFSET >> (SECTION_SHIFT - PMD_ORDER) - ldr r6, =(_end - 1) - orr r3, r8, r7 + get_kaslr_offset r3 + add r0, r3, #PAGE_OFFSET + add r0, r4, r0, lsr #(SECTION_SHIFT - PMD_ORDER) + adr_l r6, _end - 1 + sub r6, r6, r8 + add r6, r6, #PAGE_OFFSET + add r3, r3, r8 + orr r3, r3, r7 add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: str r3, [r0], #1 << PMD_ORDER add r3, r3, #1 << SECTION_SHIFT @@ -372,7 +412,7 @@ ENTRY(secondary_startup) * Use the page tables supplied from __cpu_up. */ adr_l r3, secondary_data - mov_l r12, __secondary_switched + mov_l r12, __secondary_switch ldrd r4, r5, [r3, #0] @ get secondary_data.pgdir ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps @@ -410,6 +450,7 @@ ENDPROC(__secondary_switched) * r4 = TTBR pointer (low word) * r5 = TTBR pointer (high word if LPAE) * r9 = processor ID + * r12 = KASLR offset * r13 = *virtual* address to jump to upon completion */ __enable_mmu: @@ -447,6 +488,7 @@ ENDPROC(__enable_mmu) * r1 = machine ID * r2 = atags or dtb pointer * r9 = processor ID + * r12 = KASLR offset * r13 = *virtual* address to jump to upon completion * * other registers depend on the function called upon completion @@ -462,10 +504,52 @@ ENTRY(__turn_mmu_on) mov r3, r3 mov r3, r13 ret r3 -__turn_mmu_on_end: ENDPROC(__turn_mmu_on) - .popsection +__primary_switch: +#ifdef CONFIG_RELOCATABLE + adr_l r7, _text @ r7 := __pa(_text) + sub r7, r7, #TEXT_OFFSET @ r7 := PHYS_OFFSET + + adr_l r5, __rel_begin + adr_l r6, __rel_end + sub r5, r5, r7 + sub r6, r6, r7 + + add r5, r5, #PAGE_OFFSET + add r6, r6, #PAGE_OFFSET + add r5, r5, r12 + add r6, r6, r12 + + adr_l r3, __stubs_start @ __pa(__stubs_start) + sub r3, r3, r7 @ offset of __stubs_start + add r3, r3, #PAGE_OFFSET @ __va(__stubs_start) + sub r3, r3, #0xffff1000 @ subtract VA of stubs section + +0: cmp r5, r6 + bge 1f + ldm r5!, {r7, r8} @ load next relocation entry + cmp r8, #23 @ R_ARM_RELATIVE + bne 0b + cmp r7, #0xff000000 @ vector page? + addgt r7, r7, r3 @ fix up VA offset + ldr r8, [r7, r12] + add r8, r8, r12 + str r8, [r7, r12] + b 0b +1: +#endif + ldr pc, =__mmap_switched +ENDPROC(__primary_switch) + +#ifdef CONFIG_SMP +__secondary_switch: + ldr pc, =__secondary_switched +ENDPROC(__secondary_switch) +#endif + .ltorg +__turn_mmu_on_end: + .popsection #ifdef CONFIG_SMP_ON_UP __HEAD -- 2.22.0

From: Ard Biesheuvel <ard.biesheuvel@linaro.org> maillist inclusion commit b152e5c5054c3937211a541be50d8a7c98a59974 category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/commit/?h=arm-kaslr-latest&id=b152e5c5054c3937211a541be50d8a7c98a59974 ------------------------------------------------- Add support to the decompressor to load the kernel at a randomized offset, and invoke the kernel proper while passing on the information about the offset at which the kernel was loaded. This implementation will extract some pseudo-randomness from the low bits of the generic timer (if available), and use CRC-16 to combine it with the build ID string and the device tree binary (which ideally has a /chosen/kaslr-seed property, but may also have other properties that differ between boots). This seed is used to select one of the candidate offsets in the lowmem region that don't overlap the zImage itself, the DTB, the initrd and /memreserve/s and/or /reserved-memory nodes that should be left alone. When booting via the UEFI stub, it is left up to the firmware to supply a suitable seed and select an offset. Cc: Russell King <linux@armlinux.org.uk> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> [ycc: remove __efi_kaslr_offset for UEFI is not supported for now] Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/Makefile | 9 +- arch/arm/boot/compressed/head.S | 88 ++++++ arch/arm/boot/compressed/kaslr.c | 434 ++++++++++++++++++++++++++++++ 3 files changed, 530 insertions(+), 1 deletion(-) create mode 100644 arch/arm/boot/compressed/kaslr.c diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 54307db7854d..7d6d00416411 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -84,8 +84,15 @@ compress-$(CONFIG_KERNEL_LZ4) = lz4 libfdt_objs := fdt_rw.o fdt_ro.o fdt_wip.o fdt.o +ifneq ($(CONFIG_ARM_ATAG_DTB_COMPAT)$(CONFIG_RANDOMIZE_BASE),) +OBJS += $(libfdt_objs) ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y) -OBJS += $(libfdt_objs) atags_to_fdt.o +OBJS += atags_to_fdt.o +endif +ifeq ($(CONFIG_RANDOMIZE_BASE),y) +OBJS += kaslr.o +CFLAGS_kaslr.o := -I $(srctree)/scripts/dtc/libfdt +endif endif # -fstack-protector-strong triggers protection checks in this code, diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 1b92d8a66036..adc17fce4b00 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -165,6 +165,25 @@ orr \res, \res, \tmp1, lsl #24 .endm + .macro record_seed +#ifdef CONFIG_RANDOMIZE_BASE + sub ip, r1, ip, ror #1 @ poor man's kaslr seed, will + sub ip, r2, ip, ror #2 @ be superseded by kaslr-seed + sub ip, r3, ip, ror #3 @ from /chosen if present + sub ip, r4, ip, ror #5 + sub ip, r5, ip, ror #8 + sub ip, r6, ip, ror #13 + sub ip, r7, ip, ror #21 + sub ip, r8, ip, ror #3 + sub ip, r9, ip, ror #24 + sub ip, r10, ip, ror #27 + sub ip, r11, ip, ror #19 + sub ip, r13, ip, ror #14 + sub ip, r14, ip, ror #2 + str_l ip, __kaslr_seed, r9 +#endif + .endm + .section ".start", "ax" /* * sort out different calling conventions @@ -212,6 +231,7 @@ start: __EFI_HEADER 1: ARM_BE8( setend be ) @ go BE8 if compiled for BE8 + record_seed AR_CLASS( mrs r9, cpsr ) #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install @ get into SVC mode, reversibly @@ -422,6 +442,38 @@ restart: adr r0, LC1 dtb_check_done: #endif +#ifdef CONFIG_RANDOMIZE_BASE + ldr r1, __kaslr_offset @ check if the kaslr_offset is + cmp r1, #0 @ already set + bne 1f + + stmfd sp!, {r0-r3, ip, lr} + adr_l r2, _text @ start of zImage + stmfd sp!, {r2, r8, r10} @ pass stack arguments + + ldr_l r3, __kaslr_seed +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7) + /* + * Get some pseudo-entropy from the low bits of the generic + * timer if it is implemented. + */ + mrc p15, 0, r1, c0, c1, 1 @ read ID_PFR1 register + tst r1, #0x10000 @ have generic timer? + mrrcne p15, 1, r3, r1, c14 @ read CNTVCT +#endif + adr_l r0, __kaslr_offset @ pass &__kaslr_offset in r0 + mov r1, r4 @ pass base address + mov r2, r9 @ pass decompressed image size + eor r3, r3, r3, ror #16 @ pass pseudorandom seed + bl kaslr_early_init + add sp, sp, #12 + cmp r0, #0 + addne r4, r4, r0 @ add offset to base address + ldmfd sp!, {r0-r3, ip, lr} + bne restart +1: +#endif + /* * Check to see if we will overwrite ourselves. * r4 = final kernel address (possibly with LSB set) @@ -1415,10 +1467,46 @@ __enter_kernel: mov r0, #0 @ must be 0 mov r1, r7 @ restore architecture number mov r2, r8 @ restore atags pointer +#ifdef CONFIG_RANDOMIZE_BASE + ldr r3, __kaslr_offset + add r4, r4, #4 @ skip first instruction +#endif ARM( mov pc, r4 ) @ call kernel M_CLASS( add r4, r4, #1 ) @ enter in Thumb mode for M class THUMB( bx r4 ) @ entry point is always ARM for A/R classes +#ifdef CONFIG_RANDOMIZE_BASE + /* + * Minimal implementation of CRC-16 that does not use a + * lookup table and uses 32-bit wide loads, so it still + * performs reasonably well with the D-cache off. Equivalent + * to lib/crc16.c for input sizes that are 4 byte multiples. + */ +ENTRY(__crc16) + push {r4, lr} + ldr r3, =0xa001 @ CRC-16 polynomial +0: subs r2, r2, #4 + popmi {r4, pc} + ldr r4, [r1], #4 +#ifdef __ARMEB__ + eor ip, r4, r4, ror #16 @ endian swap + bic ip, ip, #0x00ff0000 + mov r4, r4, ror #8 + eor r4, r4, ip, lsr #8 +#endif + eor r0, r0, r4 + .rept 32 + lsrs r0, r0, #1 + eorcs r0, r0, r3 + .endr + b 0b +ENDPROC(__crc16) + + .align 2 +__kaslr_seed: .long 0 +__kaslr_offset: .long 0 +#endif + reloc_code_end: #ifdef CONFIG_EFI_STUB diff --git a/arch/arm/boot/compressed/kaslr.c b/arch/arm/boot/compressed/kaslr.c new file mode 100644 index 000000000000..6ac666f3d8be --- /dev/null +++ b/arch/arm/boot/compressed/kaslr.c @@ -0,0 +1,434 @@ +/* + * Copyright (C) 2017 Linaro Ltd; <ard.biesheuvel@linaro.org> + * + * 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. + * + */ + +#include <linux/libfdt_env.h> +#include <libfdt.h> +#include <linux/types.h> +#include <generated/compile.h> +#include <generated/utsrelease.h> +#include <asm/pgtable.h> + +#include CONFIG_UNCOMPRESS_INCLUDE + +struct regions { + u32 pa_start; + u32 pa_end; + u32 image_size; + u32 zimage_start; + u32 zimage_size; + u32 dtb_start; + u32 dtb_size; + u32 initrd_start; + u32 initrd_size; + int reserved_mem; + int reserved_mem_addr_cells; + int reserved_mem_size_cells; +}; + +extern u32 __crc16(u32 crc, u32 const input[], int byte_count); + +static u32 __memparse(const char *val, const char **retptr) +{ + int base = 10; + u32 ret = 0; + + if (*val == '0') { + val++; + if (*val == 'x' || *val == 'X') { + val++; + base = 16; + } else { + base = 8; + } + } + + while (*val != ',' && *val != ' ' && *val != '\0') { + char c = *val++; + + switch (c) { + case '0' ... '9': + ret = ret * base + (c - '0'); + continue; + case 'a' ... 'f': + ret = ret * base + (c - 'a' + 10); + continue; + case 'A' ... 'F': + ret = ret * base + (c - 'A' + 10); + continue; + case 'g': + case 'G': + ret <<= 10; + case 'm': + case 'M': + ret <<= 10; + case 'k': + case 'K': + ret <<= 10; + break; + default: + if (retptr) + *retptr = NULL; + return 0; + } + } + if (retptr) + *retptr = val; + return ret; +} + +static bool regions_intersect(u32 s1, u32 e1, u32 s2, u32 e2) +{ + return e1 >= s2 && e2 >= s1; +} + +static bool intersects_reserved_region(const void *fdt, u32 start, + u32 end, struct regions *regions) +{ + int subnode, len, i; + u64 base, size; + + /* check for overlap with /memreserve/ entries */ + for (i = 0; i < fdt_num_mem_rsv(fdt); i++) { + if (fdt_get_mem_rsv(fdt, i, &base, &size) < 0) + continue; + if (regions_intersect(start, end, base, base + size)) + return true; + } + + if (regions->reserved_mem < 0) + return false; + + /* check for overlap with static reservations in /reserved-memory */ + for (subnode = fdt_first_subnode(fdt, regions->reserved_mem); + subnode >= 0; + subnode = fdt_next_subnode(fdt, subnode)) { + const fdt32_t *reg; + + len = 0; + reg = fdt_getprop(fdt, subnode, "reg", &len); + while (len >= (regions->reserved_mem_addr_cells + + regions->reserved_mem_size_cells)) { + + base = fdt32_to_cpu(reg[0]); + if (regions->reserved_mem_addr_cells == 2) + base = (base << 32) | fdt32_to_cpu(reg[1]); + + reg += regions->reserved_mem_addr_cells; + len -= 4 * regions->reserved_mem_addr_cells; + + size = fdt32_to_cpu(reg[0]); + if (regions->reserved_mem_size_cells == 2) + size = (size << 32) | fdt32_to_cpu(reg[1]); + + reg += regions->reserved_mem_size_cells; + len -= 4 * regions->reserved_mem_size_cells; + + if (base >= regions->pa_end) + continue; + + if (regions_intersect(start, end, base, + min(base + size, (u64)U32_MAX))) + return true; + } + } + return false; +} + +static bool intersects_occupied_region(const void *fdt, u32 start, + u32 end, struct regions *regions) +{ + if (regions_intersect(start, end, regions->zimage_start, + regions->zimage_start + regions->zimage_size)) + return true; + + if (regions_intersect(start, end, regions->initrd_start, + regions->initrd_start + regions->initrd_size)) + return true; + + if (regions_intersect(start, end, regions->dtb_start, + regions->dtb_start + regions->dtb_size)) + return true; + + return intersects_reserved_region(fdt, start, end, regions); +} + +static u32 count_suitable_regions(const void *fdt, struct regions *regions, + u32 *bitmap) +{ + u32 pa, i = 0, ret = 0; + + for (pa = regions->pa_start; pa < regions->pa_end; pa += SZ_2M, i++) { + if (!intersects_occupied_region(fdt, pa, + pa + regions->image_size, + regions)) { + ret++; + } else { + /* set 'occupied' bit */ + bitmap[i >> 5] |= BIT(i & 0x1f); + } + } + return ret; +} + +static u32 get_region_number(u32 num, u32 *bitmap) +{ + u32 i; + + for (i = 0; num > 0; i++) + if (!(bitmap[i >> 5] & BIT(i & 0x1f))) + num--; + return i; +} + +static void get_cell_sizes(const void *fdt, int node, int *addr_cells, + int *size_cells) +{ + const int *prop; + int len; + + /* + * Retrieve the #address-cells and #size-cells properties + * from the 'node', or use the default if not provided. + */ + *addr_cells = *size_cells = 1; + + prop = fdt_getprop(fdt, node, "#address-cells", &len); + if (len == 4) + *addr_cells = fdt32_to_cpu(*prop); + prop = fdt_getprop(fdt, node, "#size-cells", &len); + if (len == 4) + *size_cells = fdt32_to_cpu(*prop); +} + +static u32 get_memory_end(const void *fdt) +{ + int mem_node, address_cells, size_cells, len; + const fdt32_t *reg; + u64 memory_end = 0; + + /* Look for a node called "memory" at the lowest level of the tree */ + mem_node = fdt_path_offset(fdt, "/memory"); + if (mem_node <= 0) + return 0; + + get_cell_sizes(fdt, 0, &address_cells, &size_cells); + + /* + * Now find the 'reg' property of the /memory node, and iterate over + * the base/size pairs. + */ + len = 0; + reg = fdt_getprop(fdt, mem_node, "reg", &len); + while (len >= 4 * (address_cells + size_cells)) { + u64 base, size; + + base = fdt32_to_cpu(reg[0]); + if (address_cells == 2) + base = (base << 32) | fdt32_to_cpu(reg[1]); + + reg += address_cells; + len -= 4 * address_cells; + + size = fdt32_to_cpu(reg[0]); + if (size_cells == 2) + size = (size << 32) | fdt32_to_cpu(reg[1]); + + reg += size_cells; + len -= 4 * size_cells; + + memory_end = max(memory_end, base + size); + } + return min(memory_end, (u64)U32_MAX); +} + +static char *__strstr(const char *s1, const char *s2, int l2) +{ + int l1; + + l1 = strlen(s1); + while (l1 >= l2) { + l1--; + if (!memcmp(s1, s2, l2)) + return (char *)s1; + s1++; + } + return NULL; +} + +static const char *get_cmdline_param(const char *cmdline, const char *param, + int param_size) +{ + static const char default_cmdline[] = CONFIG_CMDLINE; + const char *p; + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline != NULL) { + p = __strstr(cmdline, param, param_size); + if (p == cmdline || + (p > cmdline && *(p - 1) == ' ')) + return p; + } + + if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || + IS_ENABLED(CONFIG_CMDLINE_EXTEND)) { + p = __strstr(default_cmdline, param, param_size); + if (p == default_cmdline || + (p > default_cmdline && *(p - 1) == ' ')) + return p; + } + return NULL; +} + +static void __puthex32(const char *name, u32 val) +{ + int i; + + while (*name) + putc(*name++); + putc(':'); + for (i = 28; i >= 0; i -= 4) { + char c = (val >> i) & 0xf; + + if (c < 10) + putc(c + '0'); + else + putc(c + 'a' - 10); + } + putc('\r'); + putc('\n'); +} +#define puthex32(val) __puthex32(#val, (val)) + +u32 kaslr_early_init(u32 *kaslr_offset, u32 image_base, u32 image_size, + u32 seed, u32 zimage_start, const void *fdt, + u32 zimage_end) +{ + static const char __aligned(4) build_id[] = UTS_VERSION UTS_RELEASE; + u32 bitmap[(VMALLOC_END - PAGE_OFFSET) / SZ_2M / 32] = {}; + struct regions regions; + const char *command_line; + const char *p; + int chosen, len; + u32 lowmem_top, count, num; + + if (fdt_check_header(fdt)) + return 0; + + chosen = fdt_path_offset(fdt, "/chosen"); + if (chosen < 0) + return 0; + + command_line = fdt_getprop(fdt, chosen, "bootargs", &len); + + /* check the command line for the presence of 'nokaslr' */ + p = get_cmdline_param(command_line, "nokaslr", sizeof("nokaslr") - 1); + if (p != NULL) + return 0; + + /* check the command line for the presence of 'vmalloc=' */ + p = get_cmdline_param(command_line, "vmalloc=", sizeof("vmalloc=") - 1); + if (p != NULL) + lowmem_top = VMALLOC_END - __memparse(p + 8, NULL) - + VMALLOC_OFFSET; + else + lowmem_top = VMALLOC_DEFAULT_BASE; + + regions.image_size = image_base % SZ_128M + round_up(image_size, SZ_2M); + regions.pa_start = round_down(image_base, SZ_128M); + regions.pa_end = lowmem_top - PAGE_OFFSET + regions.pa_start; + regions.zimage_start = zimage_start; + regions.zimage_size = zimage_end - zimage_start; + regions.dtb_start = (u32)fdt; + regions.dtb_size = fdt_totalsize(fdt); + + /* + * Stir up the seed a bit by taking the CRC of the DTB: + * hopefully there's a /chosen/kaslr-seed in there. + */ + seed = __crc16(seed, fdt, regions.dtb_size); + + /* stir a bit more using data that changes between builds */ + seed = __crc16(seed, (u32 *)build_id, sizeof(build_id)); + + /* check for initrd on the command line */ + regions.initrd_start = regions.initrd_size = 0; + p = get_cmdline_param(command_line, "initrd=", sizeof("initrd=") - 1); + if (p != NULL) { + regions.initrd_start = __memparse(p + 7, &p); + if (*p++ == ',') + regions.initrd_size = __memparse(p, NULL); + if (regions.initrd_size == 0) + regions.initrd_start = 0; + } + + /* ... or in /chosen */ + if (regions.initrd_size == 0) { + const fdt32_t *prop; + u64 start = 0, end = 0; + + prop = fdt_getprop(fdt, chosen, "linux,initrd-start", &len); + if (prop) { + start = fdt32_to_cpu(prop[0]); + if (len == 8) + start = (start << 32) | fdt32_to_cpu(prop[1]); + } + + prop = fdt_getprop(fdt, chosen, "linux,initrd-end", &len); + if (prop) { + end = fdt32_to_cpu(prop[0]); + if (len == 8) + end = (end << 32) | fdt32_to_cpu(prop[1]); + } + if (start != 0 && end != 0 && start < U32_MAX) { + regions.initrd_start = start; + regions.initrd_size = max_t(u64, end, U32_MAX) - start; + } + } + + /* check the memory nodes for the size of the lowmem region */ + regions.pa_end = min(regions.pa_end, get_memory_end(fdt)) - + regions.image_size; + + puthex32(regions.image_size); + puthex32(regions.pa_start); + puthex32(regions.pa_end); + puthex32(regions.zimage_start); + puthex32(regions.zimage_size); + puthex32(regions.dtb_start); + puthex32(regions.dtb_size); + puthex32(regions.initrd_start); + puthex32(regions.initrd_size); + + /* check for a reserved-memory node and record its cell sizes */ + regions.reserved_mem = fdt_path_offset(fdt, "/reserved-memory"); + if (regions.reserved_mem >= 0) + get_cell_sizes(fdt, regions.reserved_mem, + ®ions.reserved_mem_addr_cells, + ®ions.reserved_mem_size_cells); + + /* + * Iterate over the physical memory range covered by the lowmem region + * in 2 MB increments, and count each offset at which we don't overlap + * with any of the reserved regions for the zImage itself, the DTB, + * the initrd and any regions described as reserved in the device tree. + * If the region does overlap, set the respective bit in the bitmap[]. + * Using this random value, we go over the bitmap and count zero bits + * until we counted enough iterations, and return the offset we ended + * up at. + */ + count = count_suitable_regions(fdt, ®ions, bitmap); + puthex32(count); + + num = ((u16)seed * count) >> 16; + puthex32(num); + + *kaslr_offset = get_region_number(num, bitmap) * SZ_2M; + puthex32(*kaslr_offset); + + return *kaslr_offset; +} -- 2.22.0

From: Ye Bin <yebin10@huawei.com> ohos inclusion category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA ------------------------------------------------- Fix memtop calculate, when there is no memory top info, we can't use zero instead it. Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/kaslr.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/compressed/kaslr.c b/arch/arm/boot/compressed/kaslr.c index 6a4c60b22908..a4446202332f 100644 --- a/arch/arm/boot/compressed/kaslr.c +++ b/arch/arm/boot/compressed/kaslr.c @@ -316,7 +316,7 @@ u32 kaslr_early_init(u32 *kaslr_offset, u32 image_base, u32 image_size, const char *command_line; const char *p; int chosen, len; - u32 lowmem_top, count, num; + u32 lowmem_top, count, num, mem_fdt; if (fdt_check_header(fdt)) return 0; @@ -393,8 +393,11 @@ u32 kaslr_early_init(u32 *kaslr_offset, u32 image_base, u32 image_size, } /* check the memory nodes for the size of the lowmem region */ - regions.pa_end = min(regions.pa_end, get_memory_end(fdt)) - - regions.image_size; + mem_fdt = get_memory_end(fdt); + if (mem_fdt) + regions.pa_end = min(regions.pa_end, mem_fdt) - regions.image_size; + else + regions.pa_end = regions.pa_end - regions.image_size; puthex32(regions.image_size); puthex32(regions.pa_start); -- 2.22.0

From: Ye Bin <yebin10@huawei.com> ohos inclusion category: feature feature: ARM kaslr support issue: #I3ZXZF CVE: NA ------------------------------------------------- If we not hide the GOT, when insert module which reference global variable we got error "Unknown symbol_GLOBAL_OFFSET_TABLE_ (err 0)". Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com> Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/decompress.c | 4 ++++ arch/arm/boot/compressed/misc.c | 3 +++ 2 files changed, 7 insertions(+) diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index aa075d8372ea..38a5dd847e03 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #define _LINUX_STRING_H_ +#ifdef CONFIG_RANDOMIZE_BASE +#pragma GCC visibility pop +#endif + #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index e1e9a5dde853..974a08df7c7a 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -16,6 +16,9 @@ * which should point to addresses in RAM and cleared to 0 on start. * This allows for a much quicker boot time. */ +#ifdef CONFIG_RANDOMIZE_BASE +#pragma GCC visibility pop +#endif unsigned int __machine_arch_type; -- 2.22.0

From: Cui GaoSheng <cuigaosheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------------------------------ Fix follow warnings: armeb-linux-gnueabi-ld: warning: orphan section `.gnu.hash' from `arch/arm/kernel/head.o' being placed in section `.gnu.hash' Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/kernel/vmlinux.lds.S | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 1a9849968ce6..8af654bd16bf 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -70,6 +70,10 @@ SECTIONS #endif _etext = .; /* End of text section */ + .gnu.hash : { + *(.gnu.hash) + } + RO_DATA(PAGE_SIZE) . = ALIGN(4); -- 2.22.0

From: Cui GaoSheng <cuigaosheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------------------------------ Fix the bug of hidden symbols when decompressing code is compiled, we can't enable hidden cflags because decompressed code needs to support symbol relocation. Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/Makefile | 5 +++++ arch/arm/boot/compressed/decompress.c | 4 ---- arch/arm/boot/compressed/misc.c | 4 ---- 3 files changed, 5 insertions(+), 8 deletions(-) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 7d6d00416411..4b554eaf4c38 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -113,6 +113,11 @@ targets := vmlinux vmlinux.lds piggy_data piggy.o \ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S +ifeq ($(CONFIG_RELOCATABLE),y) +HIDDEN_STR := -include $(srctree)/include/linux/hidden.h +KBUILD_CFLAGS := $(subst $(HIDDEN_STR), , $(KBUILD_CFLAGS)) +endif + KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \ diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index 38a5dd847e03..aa075d8372ea 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -1,10 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _LINUX_STRING_H_ -#ifdef CONFIG_RANDOMIZE_BASE -#pragma GCC visibility pop -#endif - #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index 974a08df7c7a..abc083b0db96 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -16,10 +16,6 @@ * which should point to addresses in RAM and cleared to 0 on start. * This allows for a much quicker boot time. */ -#ifdef CONFIG_RANDOMIZE_BASE -#pragma GCC visibility pop -#endif - unsigned int __machine_arch_type; #include <linux/compiler.h> /* for inline */ -- 2.22.0

From: Cui GaoSheng <cuigaosheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------------------------------ Use adr_l instead of adr macro for symbol relocation, because linux symbol relocation has scope restrictions. Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/head.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 4b95a9268aba..1ba21b868ea3 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -152,7 +152,7 @@ * in little-endian form. */ .macro get_inflated_image_size, res:req, tmp1:req, tmp2:req - adr \res, .Linflated_image_size_offset + adr_l \res, .Linflated_image_size_offset ldr \tmp1, [\res] add \tmp1, \tmp1, \res @ address of inflated image size @@ -308,7 +308,7 @@ not_angel: orrcc r4, r4, #1 @ remember we skipped cache_on blcs cache_on -restart: adr r0, LC1 +restart: adr_l r0, LC1 ldr sp, [r0] ldr r6, [r0, #4] add sp, sp, r0 -- 2.22.0

From: Ye Bin <yebin10@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ----------------------------------------------- When we configure CONFIG_RANDOMIZE_BASE we find that: [XX]$arm-linux-gnueabihf-readelf -s ./arch/arm/vdso/vdso.so Symbol table '.dynsym' contains 5 entries: Num: Value Size Type Bind Vis Ndx Name 0: 00000000 0 NOTYPE LOCAL DEFAULT UND 1: 00000278 0 SECTION LOCAL DEFAULT 8 2: 00000000 0 OBJECT GLOBAL DEFAULT ABS LINUX_2.6 We can't find __vdso_gettimeofday and __vdso_clock_gettime symbol. So call clock_gettime and gettimeofday will call system call. This results in performance degradation. Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: yangerkun <yangerkun@huawei.com> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/vdso/vgettimeofday.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c index 1976c6f325a4..425e4f2458ec 100644 --- a/arch/arm/vdso/vgettimeofday.c +++ b/arch/arm/vdso/vgettimeofday.c @@ -4,6 +4,11 @@ * * Copyright 2015 Mentor Graphics Corporation. */ + +#ifdef CONFIG_RANDOMIZE_BASE +#pragma GCC visibility pop +#endif + #include <linux/time.h> #include <linux/types.h> -- 2.22.0

From: Gaosheng Cui <cuigaosheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------------------------------ Gcc flag '-fvisibility=hidden' specifies the visibility attribute for external linkage entities in object files. You can also selectively set visibility attributes for entities by using pairs of the #pragma GCC visibility push and #pragma GCC visibility pop compiler directives throughout your source program.when we include the hidden.h, __bss_start and __bss_end went from global symbol to local symbol,so we need to modify the regular expression to accommodate this change. Fixes: 27fdadbf34d2 ("[Backport] ARM: 9056/1: decompressor: fix BSS size calculation for LLVM ld.lld") Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 4b554eaf4c38..7a972136af38 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -127,8 +127,8 @@ asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. KBSS_SZ = $(shell echo $$(($$($(NM) $(obj)/../../../../vmlinux | \ - sed -n -e 's/^\([^ ]*\) [ABD] __bss_start$$/-0x\1/p' \ - -e 's/^\([^ ]*\) [ABD] __bss_stop$$/+0x\1/p') )) ) + sed -n -e 's/^\([^ ]*\) [ABbD] __bss_start$$/-0x\1/p' \ + -e 's/^\([^ ]*\) [ABbD] __bss_stop$$/+0x\1/p') )) ) LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ) # Supply ZRELADDR to the decompressor via a linker symbol. ifneq ($(CONFIG_AUTO_ZRELADDR),y) -- 2.22.0