From 38c9c22a85aeed28d0831f230136e9cf6fa2ed44 Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Thu, 7 Jul 2022 18:53:29 +0800 Subject: ntfs: fix use-after-free in ntfs_ucsncmp() Syzkaller reported use-after-free bug as follows: ================================================================== BUG: KASAN: use-after-free in ntfs_ucsncmp+0x123/0x130 Read of size 2 at addr ffff8880751acee8 by task a.out/879 CPU: 7 PID: 879 Comm: a.out Not tainted 5.19.0-rc4-next-20220630-00001-gcc5218c8bd2c-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x1c0/0x2b0 print_address_description.constprop.0.cold+0xd4/0x484 print_report.cold+0x55/0x232 kasan_report+0xbf/0xf0 ntfs_ucsncmp+0x123/0x130 ntfs_are_names_equal.cold+0x2b/0x41 ntfs_attr_find+0x43b/0xb90 ntfs_attr_lookup+0x16d/0x1e0 ntfs_read_locked_attr_inode+0x4aa/0x2360 ntfs_attr_iget+0x1af/0x220 ntfs_read_locked_inode+0x246c/0x5120 ntfs_iget+0x132/0x180 load_system_files+0x1cc6/0x3480 ntfs_fill_super+0xa66/0x1cf0 mount_bdev+0x38d/0x460 legacy_get_tree+0x10d/0x220 vfs_get_tree+0x93/0x300 do_new_mount+0x2da/0x6d0 path_mount+0x496/0x19d0 __x64_sys_mount+0x284/0x300 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f3f2118d9ea Code: 48 8b 0d a9 f4 0b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 76 f4 0b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc269deac8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f3f2118d9ea RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffc269dec00 RBP: 00007ffc269dec80 R08: 00007ffc269deb00 R09: 00007ffc269dec44 R10: 0000000000000000 R11: 0000000000000202 R12: 000055f81ab1d220 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 The buggy address belongs to the physical page: page:0000000085430378 refcount:1 mapcount:1 mapping:0000000000000000 index:0x555c6a81d pfn:0x751ac memcg:ffff888101f7e180 anon flags: 0xfffffc00a0014(uptodate|lru|mappedtodisk|swapbacked|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc00a0014 ffffea0001bf2988 ffffea0001de2448 ffff88801712e201 raw: 0000000555c6a81d 0000000000000000 0000000100000000 ffff888101f7e180 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880751acd80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8880751ace00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff8880751ace80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffff8880751acf00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8880751acf80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== The reason is that struct ATTR_RECORD->name_offset is 6485, end address of name string is out of bounds. Fix this by adding sanity check on end address of attribute name string. [akpm@linux-foundation.org: coding-style cleanups] [chenxiaosong2@huawei.com: cleanup suggested by Hawkins Jiawei] Link: https://lkml.kernel.org/r/20220709064511.3304299-1-chenxiaosong2@huawei.com Link: https://lkml.kernel.org/r/20220707105329.4020708-1-chenxiaosong2@huawei.com Signed-off-by: ChenXiaoSong Signed-off-by: Hawkins Jiawei Cc: Anton Altaparmakov Cc: ChenXiaoSong Cc: Yongqiang Liu Cc: Zhang Yi Cc: Zhang Xiaoxu Signed-off-by: Andrew Morton --- fs/ntfs/attrib.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 4de597a83b88..52615e6090e1 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, a = (ATTR_RECORD*)((u8*)ctx->attr + le32_to_cpu(ctx->attr->length)); for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) { - if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec + - le32_to_cpu(ctx->mrec->bytes_allocated)) + u8 *mrec_end = (u8 *)ctx->mrec + + le32_to_cpu(ctx->mrec->bytes_allocated); + u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) + + a->name_length * sizeof(ntfschar); + if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end || + name_end > mrec_end) break; ctx->attr = a; if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) || -- cgit v1.2.3 From bdeb77bc2c405fa9f954c20269db175a0bd2793f Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Sat, 16 Jul 2022 21:37:10 -0700 Subject: fs: sendfile handles O_NONBLOCK of out_fd sendfile has to return EAGAIN if out_fd is nonblocking and the write into it would block. Here is a small reproducer for the problem: #define _GNU_SOURCE /* See feature_test_macros(7) */ #include #include #include #include #include #include #include #define FILE_SIZE (1UL << 30) int main(int argc, char **argv) { int p[2], fd; if (pipe2(p, O_NONBLOCK)) return 1; fd = open(argv[1], O_RDWR | O_TMPFILE, 0666); if (fd < 0) return 1; ftruncate(fd, FILE_SIZE); if (sendfile(p[1], fd, 0, FILE_SIZE) == -1) { fprintf(stderr, "FAIL\n"); } if (sendfile(p[1], fd, 0, FILE_SIZE) != -1 || errno != EAGAIN) { fprintf(stderr, "FAIL\n"); } return 0; } It worked before b964bf53e540, it is stuck after b964bf53e540, and it works again with this fix. This regression occurred because do_splice_direct() calls pipe_write that handles O_NONBLOCK. Here is a trace log from the reproducer: 1) | __x64_sys_sendfile64() { 1) | do_sendfile() { 1) | __fdget() 1) | rw_verify_area() 1) | __fdget() 1) | rw_verify_area() 1) | do_splice_direct() { 1) | rw_verify_area() 1) | splice_direct_to_actor() { 1) | do_splice_to() { 1) | rw_verify_area() 1) | generic_file_splice_read() 1) + 74.153 us | } 1) | direct_splice_actor() { 1) | iter_file_splice_write() { 1) | __kmalloc() 1) 0.148 us | pipe_lock(); 1) 0.153 us | splice_from_pipe_next.part.0(); 1) 0.162 us | page_cache_pipe_buf_confirm(); ... 16 times 1) 0.159 us | page_cache_pipe_buf_confirm(); 1) | vfs_iter_write() { 1) | do_iter_write() { 1) | rw_verify_area() 1) | do_iter_readv_writev() { 1) | pipe_write() { 1) | mutex_lock() 1) 0.153 us | mutex_unlock(); 1) 1.368 us | } 1) 1.686 us | } 1) 5.798 us | } 1) 6.084 us | } 1) 0.174 us | kfree(); 1) 0.152 us | pipe_unlock(); 1) + 14.461 us | } 1) + 14.783 us | } 1) 0.164 us | page_cache_pipe_buf_release(); ... 16 times 1) 0.161 us | page_cache_pipe_buf_release(); 1) | touch_atime() 1) + 95.854 us | } 1) + 99.784 us | } 1) ! 107.393 us | } 1) ! 107.699 us | } Link: https://lkml.kernel.org/r/20220415005015.525191-1-avagin@gmail.com Fixes: b964bf53e540 ("teach sendfile(2) to handle send-to-pipe directly") Signed-off-by: Andrei Vagin Cc: Al Viro Cc: Signed-off-by: Andrew Morton --- fs/read_write.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/read_write.c b/fs/read_write.c index b1b1cdfee9d3..9737d42bb348 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1263,6 +1263,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, count, fl); file_end_write(out.file); } else { + if (out.file->f_flags & O_NONBLOCK) + fl |= SPLICE_F_NONBLOCK; + retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); } -- cgit v1.2.3 From c80af0c250c8f8a3c978aa5aafbe9c39b336b813 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Fri, 3 Jun 2022 15:28:01 -0700 Subject: Revert "ocfs2: mount shared volume without ha stack" This reverts commit 912f655d78c5d4ad05eac287f23a435924df7144. This commit introduced a regression that can cause mount hung. The changes in __ocfs2_find_empty_slot causes that any node with none-zero node number can grab the slot that was already taken by node 0, so node 1 will access the same journal with node 0, when it try to grab journal cluster lock, it will hung because it was already acquired by node 0. It's very easy to reproduce this, in one cluster, mount node 0 first, then node 1, you will see the following call trace from node 1. [13148.735424] INFO: task mount.ocfs2:53045 blocked for more than 122 seconds. [13148.739691] Not tainted 5.15.0-2148.0.4.el8uek.mountracev2.x86_64 #2 [13148.742560] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [13148.745846] task:mount.ocfs2 state:D stack: 0 pid:53045 ppid: 53044 flags:0x00004000 [13148.749354] Call Trace: [13148.750718] [13148.752019] ? usleep_range+0x90/0x89 [13148.753882] __schedule+0x210/0x567 [13148.755684] schedule+0x44/0xa8 [13148.757270] schedule_timeout+0x106/0x13c [13148.759273] ? __prepare_to_swait+0x53/0x78 [13148.761218] __wait_for_common+0xae/0x163 [13148.763144] __ocfs2_cluster_lock.constprop.0+0x1d6/0x870 [ocfs2] [13148.765780] ? ocfs2_inode_lock_full_nested+0x18d/0x398 [ocfs2] [13148.768312] ocfs2_inode_lock_full_nested+0x18d/0x398 [ocfs2] [13148.770968] ocfs2_journal_init+0x91/0x340 [ocfs2] [13148.773202] ocfs2_check_volume+0x39/0x461 [ocfs2] [13148.775401] ? iput+0x69/0xba [13148.777047] ocfs2_mount_volume.isra.0.cold+0x40/0x1f5 [ocfs2] [13148.779646] ocfs2_fill_super+0x54b/0x853 [ocfs2] [13148.781756] mount_bdev+0x190/0x1b7 [13148.783443] ? ocfs2_remount+0x440/0x440 [ocfs2] [13148.785634] legacy_get_tree+0x27/0x48 [13148.787466] vfs_get_tree+0x25/0xd0 [13148.789270] do_new_mount+0x18c/0x2d9 [13148.791046] __x64_sys_mount+0x10e/0x142 [13148.792911] do_syscall_64+0x3b/0x89 [13148.794667] entry_SYSCALL_64_after_hwframe+0x170/0x0 [13148.797051] RIP: 0033:0x7f2309f6e26e [13148.798784] RSP: 002b:00007ffdcee7d408 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [13148.801974] RAX: ffffffffffffffda RBX: 00007ffdcee7d4a0 RCX: 00007f2309f6e26e [13148.804815] RDX: 0000559aa762a8ae RSI: 0000559aa939d340 RDI: 0000559aa93a22b0 [13148.807719] RBP: 00007ffdcee7d5b0 R08: 0000559aa93a2290 R09: 00007f230a0b4820 [13148.810659] R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffdcee7d420 [13148.813609] R13: 0000000000000000 R14: 0000559aa939f000 R15: 0000000000000000 [13148.816564] To fix it, we can just fix __ocfs2_find_empty_slot. But original commit introduced the feature to mount ocfs2 locally even it is cluster based, that is a very dangerous, it can easily cause serious data corruption, there is no way to stop other nodes mounting the fs and corrupting it. Setup ha or other cluster-aware stack is just the cost that we have to take for avoiding corruption, otherwise we have to do it in kernel. Link: https://lkml.kernel.org/r/20220603222801.42488-1-junxiao.bi@oracle.com Fixes: 912f655d78c5("ocfs2: mount shared volume without ha stack") Signed-off-by: Junxiao Bi Acked-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Cc: Signed-off-by: Andrew Morton --- fs/ocfs2/ocfs2.h | 4 +--- fs/ocfs2/slot_map.c | 46 +++++++++++++++++++--------------------------- fs/ocfs2/super.c | 21 --------------------- 3 files changed, 20 insertions(+), 51 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 337527571461..740b64238312 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -277,7 +277,6 @@ enum ocfs2_mount_options OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */ OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */ OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */ - OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */ }; #define OCFS2_OSB_SOFT_RO 0x0001 @@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb) static inline int ocfs2_mount_local(struct ocfs2_super *osb) { - return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT) - || (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER)); + return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT); } static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb) diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index 0b0ae3ebb0cf..da7718cef735 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -252,16 +252,14 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si, int i, ret = -ENOSPC; if ((preferred >= 0) && (preferred < si->si_num_slots)) { - if (!si->si_slots[preferred].sl_valid || - !si->si_slots[preferred].sl_node_num) { + if (!si->si_slots[preferred].sl_valid) { ret = preferred; goto out; } } for(i = 0; i < si->si_num_slots; i++) { - if (!si->si_slots[i].sl_valid || - !si->si_slots[i].sl_node_num) { + if (!si->si_slots[i].sl_valid) { ret = i; break; } @@ -456,30 +454,24 @@ int ocfs2_find_slot(struct ocfs2_super *osb) spin_lock(&osb->osb_lock); ocfs2_update_slot_info(si); - if (ocfs2_mount_local(osb)) - /* use slot 0 directly in local mode */ - slot = 0; - else { - /* search for ourselves first and take the slot if it already - * exists. Perhaps we need to mark this in a variable for our - * own journal recovery? Possibly not, though we certainly - * need to warn to the user */ - slot = __ocfs2_node_num_to_slot(si, osb->node_num); + /* search for ourselves first and take the slot if it already + * exists. Perhaps we need to mark this in a variable for our + * own journal recovery? Possibly not, though we certainly + * need to warn to the user */ + slot = __ocfs2_node_num_to_slot(si, osb->node_num); + if (slot < 0) { + /* if no slot yet, then just take 1st available + * one. */ + slot = __ocfs2_find_empty_slot(si, osb->preferred_slot); if (slot < 0) { - /* if no slot yet, then just take 1st available - * one. */ - slot = __ocfs2_find_empty_slot(si, osb->preferred_slot); - if (slot < 0) { - spin_unlock(&osb->osb_lock); - mlog(ML_ERROR, "no free slots available!\n"); - status = -EINVAL; - goto bail; - } - } else - printk(KERN_INFO "ocfs2: Slot %d on device (%s) was " - "already allocated to this node!\n", - slot, osb->dev_str); - } + spin_unlock(&osb->osb_lock); + mlog(ML_ERROR, "no free slots available!\n"); + status = -EINVAL; + goto bail; + } + } else + printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already " + "allocated to this node!\n", slot, osb->dev_str); ocfs2_set_slot(si, slot, osb->node_num); osb->slot_num = slot; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index f7298816d8d9..438be028935d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -172,7 +172,6 @@ enum { Opt_dir_resv_level, Opt_journal_async_commit, Opt_err_cont, - Opt_nocluster, Opt_err, }; @@ -206,7 +205,6 @@ static const match_table_t tokens = { {Opt_dir_resv_level, "dir_resv_level=%u"}, {Opt_journal_async_commit, "journal_async_commit"}, {Opt_err_cont, "errors=continue"}, - {Opt_nocluster, "nocluster"}, {Opt_err, NULL} }; @@ -618,13 +616,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) goto out; } - tmp = OCFS2_MOUNT_NOCLUSTER; - if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) { - ret = -EINVAL; - mlog(ML_ERROR, "Cannot change nocluster option on remount\n"); - goto out; - } - tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL | OCFS2_MOUNT_HB_NONE; if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) { @@ -865,7 +856,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb, } if (ocfs2_userspace_stack(osb) && - !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) && strncmp(osb->osb_cluster_stack, mopt->cluster_stack, OCFS2_STACK_LABEL_LEN)) { mlog(ML_ERROR, @@ -1137,11 +1127,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" : "ordered"); - if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) && - !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)) - printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted " - "without cluster aware mode.\n", osb->dev_str); - atomic_set(&osb->vol_state, VOLUME_MOUNTED); wake_up(&osb->osb_mount_event); @@ -1452,9 +1437,6 @@ static int ocfs2_parse_options(struct super_block *sb, case Opt_journal_async_commit: mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; break; - case Opt_nocluster: - mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER; - break; default: mlog(ML_ERROR, "Unrecognized mount option \"%s\" " @@ -1566,9 +1548,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root) if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) seq_printf(s, ",journal_async_commit"); - if (opts & OCFS2_MOUNT_NOCLUSTER) - seq_printf(s, ",nocluster"); - return 0; } -- cgit v1.2.3 From d172b1a3bd065dd89234eac547fc62cf80681631 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 11 Jul 2022 09:59:06 -0700 Subject: userfaultfd: provide properly masked address for huge-pages Commit 824ddc601adc ("userfaultfd: provide unmasked address on page-fault") was introduced to fix an old bug, in which the offset in the address of a page-fault was masked. Concerns were raised - although were never backed by actual code - that some userspace code might break because the bug has been around for quite a while. To address these concerns a new flag was introduced, and only when this flag is set by the user, userfaultfd provides the exact address of the page-fault. The commit however had a bug, and if the flag is unset, the offset was always masked based on a base-page granularity. Yet, for huge-pages, the behavior prior to the commit was that the address is masked to the huge-page granulrity. While there are no reports on real breakage, fix this issue. If the flag is unset, use the address with the masking that was done before. Link: https://lkml.kernel.org/r/20220711165906.2682-1-namit@vmware.com Fixes: 824ddc601adc ("userfaultfd: provide unmasked address on page-fault") Signed-off-by: Nadav Amit Reported-by: James Houghton Reviewed-by: Mike Rapoport Reviewed-by: Peter Xu Reviewed-by: James Houghton Cc: David Hildenbrand Cc: Jan Kara Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e943370107d0..de86f5b2859f 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -192,17 +192,19 @@ static inline void msg_init(struct uffd_msg *msg) } static inline struct uffd_msg userfault_msg(unsigned long address, + unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; + msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; - if (!(features & UFFD_FEATURE_EXACT_ADDRESS)) - address &= PAGE_MASK; - msg.arg.pagefault.address = address; + msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? + real_address : address; + /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. @@ -488,8 +490,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason, - ctx->features); + uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, + reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; -- cgit v1.2.3