May 2024 - Linux-stable-mirror

[PATCH 5.4] smb: client: fix potential OOBs in smb2_parse_contexts()

by Shaoying Xu

From: Paulo Alcantara <pc(a)manguebit.com> [ Upstream commit af1689a9b7701d9907dfc84d2a4b57c4bc907144 ] Validate offsets and lengths before dereferencing create contexts in smb2_parse_contexts(). This fixes following oops when accessing invalid create contexts from server: BUG: unable to handle page fault for address: ffff8881178d8cc3 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 4a01067 P4D 4a01067 PUD 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 1736 Comm: mount.cifs Not tainted 6.7.0-rc4 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 RIP: 0010:smb2_parse_contexts+0xa0/0x3a0 [cifs] Code: f8 10 75 13 48 b8 93 ad 25 50 9c b4 11 e7 49 39 06 0f 84 d2 00 00 00 8b 45 00 85 c0 74 61 41 29 c5 48 01 c5 41 83 fd 0f 76 55 <0f> b7 7d 04 0f b7 45 06 4c 8d 74 3d 00 66 83 f8 04 75 bc ba 04 00 RSP: 0018:ffffc900007939e0 EFLAGS: 00010216 RAX: ffffc90000793c78 RBX: ffff8880180cc000 RCX: ffffc90000793c90 RDX: ffffc90000793cc0 RSI: ffff8880178d8cc0 RDI: ffff8880180cc000 RBP: ffff8881178d8cbf R08: ffffc90000793c22 R09: 0000000000000000 R10: ffff8880180cc000 R11: 0000000000000024 R12: 0000000000000000 R13: 0000000000000020 R14: 0000000000000000 R15: ffffc90000793c22 FS: 00007f873753cbc0(0000) GS:ffff88806bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8881178d8cc3 CR3: 00000000181ca000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x181/0x480 ? search_module_extables+0x19/0x60 ? srso_alias_return_thunk+0x5/0xfbef5 ? exc_page_fault+0x1b6/0x1c0 ? asm_exc_page_fault+0x26/0x30 ? smb2_parse_contexts+0xa0/0x3a0 [cifs] SMB2_open+0x38d/0x5f0 [cifs] ? smb2_is_path_accessible+0x138/0x260 [cifs] smb2_is_path_accessible+0x138/0x260 [cifs] cifs_is_path_remote+0x8d/0x230 [cifs] cifs_mount+0x7e/0x350 [cifs] cifs_smb3_do_mount+0x128/0x780 [cifs] smb3_get_tree+0xd9/0x290 [cifs] vfs_get_tree+0x2c/0x100 ? capable+0x37/0x70 path_mount+0x2d7/0xb80 ? srso_alias_return_thunk+0x5/0xfbef5 ? _raw_spin_unlock_irqrestore+0x44/0x60 __x64_sys_mount+0x11a/0x150 do_syscall_64+0x47/0xf0 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7f8737657b1e Reported-by: Robert Morris <rtm(a)csail.mit.edu> Cc: stable(a)vger.kernel.org Signed-off-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> [Guru: Removed changes to cached_dir.c and checking return value of smb2_parse_contexts in smb2ops.c] Signed-off-by: Guruswamy Basavaiah <guruswamy.basavaiah(a)broadcom.com> [v5.4: Fixed merge-conflicts in smb2_parse_contexts for missing parameter POSIX response] Signed-off-by: Shaoying Xu <shaoyi(a)amazon.com> --- fs/cifs/smb2ops.c | 4 ++- fs/cifs/smb2pdu.c | 81 +++++++++++++++++++++++++++++---------------- fs/cifs/smb2proto.h | 10 +++--- 3 files changed, 62 insertions(+), 33 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index d9cdbae93608..17599294eecd 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -787,9 +787,11 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, /* BB TBD check to see if oplock level check can be removed below */ if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { kref_get(&tcon->crfid.refcount); - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, oparms.fid->lease_key, &oplock, NULL); + if (rc) + goto oshr_exit; } else goto oshr_exit; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5545d5991bc2..af1d24caf906 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1929,48 +1929,73 @@ parse_query_id_ctxt(struct create_context *cc, struct smb2_file_all_info *buf) buf->IndexNumber = pdisk_id->DiskFileId; } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - - next = le32_to_cpu(cc->Next); - if (!next) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen >= doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; + } + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -2680,8 +2705,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 7fb4fdd814f5..0c3480be7b8f 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -238,10 +238,12 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); -- 2.40.1

12 months

2
1
0 0

[PATCH 5.15 0/2] netlink, fix issues caught by syzbot

by Yenchia Chen

From: "yenchia.chen" <yenchia.chen(a)mediatek.com> Hi, We think 5.15.y could pick these commits. Below is the mainline commit: netlink: annotate lockless accesses to nlk->max_recvmsg_len [ Upstream commit a1865f2e7d10dde00d35a2122b38d2e469ae67ed ] netlink: annotate data-races around sk->sk_err [ Upstream commit d0f95894fda7d4f895b29c1097f92d7fee278cb2 ] Eric Dumazet (2): netlink: annotate lockless accesses to nlk->max_recvmsg_len netlink: annotate data-races around sk->sk_err net/netlink/af_netlink.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) -- 2.18.0

12 months

4
6
0 0

[PATCH] ima: fix deadlock when traversing "ima_default_rules".

by GUO Zihua

From: liqiong <liqiong(a)nfschina.com> [ Upstream commit eb0782bbdfd0d7c4786216659277c3fd585afc0e ] The current IMA ruleset is identified by the variable "ima_rules" that default to "&ima_default_rules". When loading a custom policy for the first time, the variable is updated to "&ima_policy_rules" instead. That update isn't RCU-safe, and deadlocks are possible. Indeed, some functions like ima_match_policy() may loop indefinitely when traversing "ima_default_rules" with list_for_each_entry_rcu(). When iterating over the default ruleset back to head, if the list head is "ima_default_rules", and "ima_rules" have been updated to "&ima_policy_rules", the loop condition (&entry->list != ima_rules) stays always true, traversing won't terminate, causing a soft lockup and RCU stalls. Introduce a temporary value for "ima_rules" when iterating over the ruleset to avoid the deadlocks. Addition: A rcu_read_lock pair is added within ima_update_policy_flag to avoid suspicious RCU usage warning. This pair of RCU lock was added with commit 4f2946aa0c45 ("IMA: introduce a new policy option func=SETXATTR_CHECK") on mainstream. Signed-off-by: liqiong <liqiong(a)nfschina.com> Reviewed-by: THOBY Simon <Simon.THOBY(a)viveris.fr> Fixes: 38d859f991f3 ("IMA: policy can now be updated multiple times") Reported-by: kernel test robot <lkp(a)intel.com> (Fix sparse: incompatible types in comparison expression.) Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: GUO Zihua <guozihua(a)huawei.com> --- security/integrity/ima/ima_policy.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 1c403e8a8044..4f5d44037081 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -210,7 +210,7 @@ static struct ima_rule_entry *arch_policy_entry __ro_after_init; static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); -static struct list_head *ima_rules = &ima_default_rules; +static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules); static int ima_policy __initdata; @@ -648,12 +648,14 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, { struct ima_rule_entry *entry; int action = 0, actmask = flags | (flags << 1); + struct list_head *ima_rules_tmp; if (template_desc) *template_desc = ima_template_desc_current(); rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!(entry->action & actmask)) continue; @@ -701,11 +703,15 @@ int ima_match_policy(struct inode *inode, const struct cred *cred, u32 secid, void ima_update_policy_flag(void) { struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; - list_for_each_entry(entry, ima_rules, list) { + rcu_read_lock(); + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action & IMA_DO_MASK) ima_policy_flag |= entry->action; } + rcu_read_unlock(); ima_appraise |= (build_ima_appraise | temp_ima_appraise); if (!ima_appraise) @@ -898,10 +904,10 @@ void ima_update_policy(void) list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu); - if (ima_rules != policy) { + if (ima_rules != (struct list_head __rcu *)policy) { ima_policy_flag = 0; - ima_rules = policy; + rcu_assign_pointer(ima_rules, policy); /* * IMA architecture specific policy rules are specified * as strings and converted to an array of ima_entry_rules @@ -989,7 +995,7 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); - if (ima_rules == &ima_default_rules) { + if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) { kfree(entry->lsm[lsm_rule].args_p); entry->lsm[lsm_rule].args_p = NULL; result = -EINVAL; @@ -1598,9 +1604,11 @@ void *ima_policy_start(struct seq_file *m, loff_t *pos) { loff_t l = *pos; struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!l--) { rcu_read_unlock(); return entry; @@ -1619,7 +1627,8 @@ void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos) rcu_read_unlock(); (*pos)++; - return (&entry->list == ima_rules) ? NULL : entry; + return (&entry->list == &ima_default_rules || + &entry->list == &ima_policy_rules) ? NULL : entry; } void ima_policy_stop(struct seq_file *m, void *v) @@ -1823,6 +1832,7 @@ bool ima_appraise_signature(enum kernel_read_file_id id) struct ima_rule_entry *entry; bool found = false; enum ima_hooks func; + struct list_head *ima_rules_tmp; if (id >= READING_MAX_ID) return false; @@ -1834,7 +1844,8 @@ bool ima_appraise_signature(enum kernel_read_file_id id) func = read_idmap[id] ?: FILE_CHECK; rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action != APPRAISE) continue; -- 2.34.1

12 months

4
4
0 0

[PATCH 5.15 0/5] Backport CVE-2024-26583 and CVE-2024-26584 fixes

by Shaoying Xu

Backport fix commit ("tls: fix race between async notify and socket close") for CVE-2024-26583 [1]. It's dependent on three tls commits being used to simplify and factor out async waiting. They also benefit backporting fix commit ("net: tls: handle backlogging of crypto requests") for CVE-2024-26584 [2]. Therefore, add them for clean backport: Jakub Kicinski (4): tls: rx: simplify async wait net: tls: factor out tls_*crypt_async_wait() tls: fix race between async notify and socket close net: tls: handle backlogging of crypto requests Sabrina Dubroca (1): tls: extract context alloc/initialization out of tls_set_sw_offload Please review and consider applying these patches. [1] https://lore.kernel.org/all/2024022146-traction-unjustly-f451@gregkh/ [2] https://lore.kernel.org/all/2024022148-showpiece-yanking-107c@gregkh/ include/net/tls.h | 6 -- net/tls/tls_sw.c | 199 ++++++++++++++++++++++++---------------------- 2 files changed, 106 insertions(+), 99 deletions(-) -- 2.40.1

12 months

2
6
0 0

[PATCH v4.19] dm: limit the number of targets and parameter size area

by Srish Srinivasan

From: Mikulas Patocka <mpatocka(a)redhat.com> commit bd504bcfec41a503b32054da5472904b404341a4 upstream. The kvmalloc function fails with a warning if the size is larger than INT_MAX. The warning was triggered by a syscall testing robot. In order to avoid the warning, this commit limits the number of targets to 1048576 and the size of the parameter area to 1073741824. Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> Signed-off-by: He Gao <hegao(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [srish: Apply to stable branch linux-4.19.y] Signed-off-by: Srish Srinivasan <srish.srinivasan(a)broadcom.com> --- drivers/md/dm-core.h | 2 ++ drivers/md/dm-ioctl.c | 3 ++- drivers/md/dm-table.c | 9 +++++++-- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 8cda3f7dd..2542f0881 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -18,6 +18,8 @@ #include "dm.h" #define DM_RESERVED_MAX_IOS 1024 +#define DM_MAX_TARGETS 1048576 +#define DM_MAX_TARGET_PARAMS 1024 struct dm_kobject_holder { struct kobject kobj; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 88e89796c..70929ff79 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1734,7 +1734,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) + if (unlikely(param_kernel->data_size < minimum_data_size) || + unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) return -EINVAL; secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 3faaf21be..4822f66b0 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -187,7 +187,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num) int dm_table_create(struct dm_table **result, fmode_t mode, unsigned num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; @@ -202,7 +207,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, if (!num_targets) { kfree(t); - return -ENOMEM; + return -EOVERFLOW; } if (alloc_targets(t, num_targets)) { -- 2.35.6

12 months

2
1
0 0

[PATCH] 9p: add missing locking around taking dentry fid list

by Dominique Martinet

Fix a use-after-free on dentry's d_fsdata fid list when a thread lookups a fid through dentry while another thread unlinks it: UAF thread: refcount_t: addition on 0; use-after-free. p9_fid_get linux/./include/net/9p/client.h:262 v9fs_fid_find+0x236/0x280 linux/fs/9p/fid.c:129 v9fs_fid_lookup_with_uid linux/fs/9p/fid.c:181 v9fs_fid_lookup+0xbf/0xc20 linux/fs/9p/fid.c:314 v9fs_vfs_getattr_dotl+0xf9/0x360 linux/fs/9p/vfs_inode_dotl.c:400 vfs_statx+0xdd/0x4d0 linux/fs/stat.c:248 Freed by: p9_client_clunk+0xb0/0xe0 linux/net/9p/client.c:1456 p9_fid_put linux/./include/net/9p/client.h:278 v9fs_dentry_release+0xb5/0x140 linux/fs/9p/vfs_dentry.c:55 v9fs_remove+0x38f/0x620 linux/fs/9p/vfs_inode.c:518 vfs_unlink+0x29a/0x810 linux/fs/namei.c:4335 The problem is that d_fsdata was not accessed under d_lock, because d_release() normally is only called once the dentry is otherwise no longer accessible but since we also call it explicitly in v9fs_remove that lock is required: move the hlist out of the dentry under lock then unref its fids once they are no longer accessible. Fixes: 154372e67d40 ("fs/9p: fix create-unlink-getattr idiom") Cc: stable(a)vger.kernel.org Reported-by: Meysam Firouzi Reported-by: Amirmohammad Eftekhar Signed-off-by: Dominique Martinet <asmadeus(a)codewreck.org> --- fs/9p/vfs_dentry.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f16f73581634..01338d4c2d9e 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry) static void v9fs_dentry_release(struct dentry *dentry) { struct hlist_node *p, *n; + struct hlist_head head; p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); - hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata) + + spin_lock(&dentry->d_lock); + hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head); + spin_unlock(&dentry->d_lock); + + hlist_for_each_safe(p, n, &head) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); - dentry->d_fsdata = NULL; } static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) -- 2.44.0

12 months

2
6
0 0

[PATCH stable 5.4 0/3] net: bcmgenet: protect contended accesses

by Doug Berger

Some registers may be modified by parallel execution contexts and require protections to prevent corruption. A review of the driver revealed the need for these additional protections. Doug Berger (3): net: bcmgenet: synchronize EXT_RGMII_OOB_CTRL access net: bcmgenet: synchronize use of bcmgenet_set_rx_mode() net: bcmgenet: synchronize UMAC_CMD access drivers/net/ethernet/broadcom/genet/bcmgenet.c | 14 +++++++++++++- drivers/net/ethernet/broadcom/genet/bcmgenet.h | 2 ++ drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 6 ++++++ drivers/net/ethernet/broadcom/genet/bcmmii.c | 4 ++++ 4 files changed, 25 insertions(+), 1 deletion(-) -- These commits are dependent on the previously submitted: [PATCH stable 5.4 0/2] net: bcmgenet: revisit MAC reset 2.34.1

12 months

2
4
0 0

[PATCH stable 5.4 0/2] net: bcmgenet: revisit MAC reset

by Doug Berger

Commit 3a55402c9387 ("net: bcmgenet: use RGMII loopback for MAC reset") was intended to resolve issues with reseting the UniMAC core within the GENET block by providing better control over the clocks used by the UniMAC core. Unfortunately, it is not compatible with all of the supported system configurations so an alternative method must be applied. This commit set provides such an alternative. The first commit reverts the previous change and the second commit provides the alternative reset sequence that addresses the concerns observed with the previous implementation. This replacement implementation should be applied to the stable branches wherever commit 3a55402c9387 ("net: bcmgenet: use RGMII loopback for MAC reset") has been applied. Unfortunately, reverting that commit may conflict with some restructuring changes introduced by commit 4f8d81b77e66 ("net: bcmgenet: Refactor register access in bcmgenet_mii_config"). The first commit in this set has been manually edited to resolve the conflict on stable/linux-5.4.y. Doug Berger (2): Revert "net: bcmgenet: use RGMII loopback for MAC reset" net: bcmgenet: keep MAC in reset until PHY is up .../net/ethernet/broadcom/genet/bcmgenet.c | 10 ++--- .../ethernet/broadcom/genet/bcmgenet_wol.c | 6 ++- drivers/net/ethernet/broadcom/genet/bcmmii.c | 39 +++---------------- 3 files changed, 16 insertions(+), 39 deletions(-) -- 2.34.1

12 months

2
3
0 0

[PATCH RESEND 6.6.y] kselftest: Add a ksft_perror() helper

by Edward Liaw

From: Mark Brown <broonie(a)kernel.org> [ Upstream commit 907f33028871fa7c9a3db1efd467b78ef82cce20 ] The standard library perror() function provides a convenient way to print an error message based on the current errno but this doesn't play nicely with KTAP output. Provide a helper which does an equivalent thing in a KTAP compatible format. nolibc doesn't have a strerror() and adding the table of strings required doesn't seem like a good fit for what it's trying to do so when we're using that only print the errno. Signed-off-by: Mark Brown <broonie(a)kernel.org> Reviewed-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Stable-dep-of: 071af0c9e582 ("selftests: timers: Convert posix_timers test to generate KTAP output") Signed-off-by: Edward Liaw <edliaw(a)google.com> --- tools/testing/selftests/kselftest.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index e8eecbc83a60..ad7b97e16f37 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -48,6 +48,7 @@ #include <stdlib.h> #include <unistd.h> #include <stdarg.h> +#include <string.h> #include <stdio.h> #include <sys/utsname.h> #endif @@ -156,6 +157,19 @@ static inline void ksft_print_msg(const char *msg, ...) va_end(args); } +static inline void ksft_perror(const char *msg) +{ +#ifndef NOLIBC + ksft_print_msg("%s: %s (%d)\n", msg, strerror(errno), errno); +#else + /* + * nolibc doesn't provide strerror() and it seems + * inappropriate to add one, just print the errno. + */ + ksft_print_msg("%s: %d)\n", msg, errno); +#endif +} + static inline void ksft_test_result_pass(const char *msg, ...) { int saved_errno = errno; -- 2.45.0.215.g3402c0e53f-goog

12 months

2
1
0 0

[PATCH 6.1 01/24] xfs: write page faults in iomap are not buffered writes

by Leah Rumancik

From: Dave Chinner <dchinner(a)redhat.com> [ Upstream commit 118e021b4b66f758f8e8f21dc0e5e0a4c721e69e ] When we reserve a delalloc region in xfs_buffered_write_iomap_begin, we mark the iomap as IOMAP_F_NEW so that the the write context understands that it allocated the delalloc region. If we then fail that buffered write, xfs_buffered_write_iomap_end() checks for the IOMAP_F_NEW flag and if it is set, it punches out the unused delalloc region that was allocated for the write. The assumption this code makes is that all buffered write operations that can allocate space are run under an exclusive lock (i_rwsem). This is an invalid assumption: page faults in mmap()d regions call through this same function pair to map the file range being faulted and this runs only holding the inode->i_mapping->invalidate_lock in shared mode. IOWs, we can have races between page faults and write() calls that fail the nested page cache write operation that result in data loss. That is, the failing iomap_end call will punch out the data that the other racing iomap iteration brought into the page cache. This can be reproduced with generic/34[46] if we arbitrarily fail page cache copy-in operations from write() syscalls. Code analysis tells us that the iomap_page_mkwrite() function holds the already instantiated and uptodate folio locked across the iomap mapping iterations. Hence the folio cannot be removed from memory whilst we are mapping the range it covers, and as such we do not care if the mapping changes state underneath the iomap iteration loop: 1. if the folio is not already dirty, there is no writeback races possible. 2. if we allocated the mapping (delalloc or unwritten), the folio cannot already be dirty. See #1. 3. If the folio is already dirty, it must be up to date. As we hold it locked, it cannot be reclaimed from memory. Hence we always have valid data in the page cache while iterating the mapping. 4. Valid data in the page cache can exist when the underlying mapping is DELALLOC, UNWRITTEN or WRITTEN. Having the mapping change from DELALLOC->UNWRITTEN or UNWRITTEN->WRITTEN does not change the data in the page - it only affects actions if we are initialising a new page. Hence #3 applies and we don't care about these extent map transitions racing with iomap_page_mkwrite(). 5. iomap_page_mkwrite() checks for page invalidation races (truncate, hole punch, etc) after it locks the folio. We also hold the mapping->invalidation_lock here, and hence the mapping cannot change due to extent removal operations while we are iterating the folio. As such, filesystems that don't use bufferheads will never fail the iomap_folio_mkwrite_iter() operation on the current mapping, regardless of whether the iomap should be considered stale. Further, the range we are asked to iterate is limited to the range inside EOF that the folio spans. Hence, for XFS, we will only map the exact range we are asked for, and we will only do speculative preallocation with delalloc if we are mapping a hole at the EOF page. The iterator will consume the entire range of the folio that is within EOF, and anything beyond the EOF block cannot be accessed. We never need to truncate this post-EOF speculative prealloc away in the context of the iomap_page_mkwrite() iterator because if it remains unused we'll remove it when the last reference to the inode goes away. Hence we don't actually need an .iomap_end() cleanup/error handling path at all for iomap_page_mkwrite() for XFS. This means we can separate the page fault processing from the complexity of the .iomap_end() processing in the buffered write path. This also means that the buffered write path will also be able to take the mapping->invalidate_lock as necessary. Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Leah Rumancik <leah.rumancik(a)gmail.com> Acked-by: Darrick J. Wong <djwong(a)kernel.org> --- fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_iomap.c | 9 +++++++++ fs/xfs/xfs_iomap.h | 1 + 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index e462d39c840e..595a5bcf46b9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1325,7 +1325,7 @@ __xfs_filemap_fault( if (write_fault) { xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); ret = iomap_page_mkwrite(vmf, - &xfs_buffered_write_iomap_ops); + &xfs_page_mkwrite_iomap_ops); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); } else { ret = filemap_fault(vmf); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 07da03976ec1..5cea069a38b4 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1187,6 +1187,15 @@ const struct iomap_ops xfs_buffered_write_iomap_ops = { .iomap_end = xfs_buffered_write_iomap_end, }; +/* + * iomap_page_mkwrite() will never fail in a way that requires delalloc extents + * that it allocated to be revoked. Hence we do not need an .iomap_end method + * for this operation. + */ +const struct iomap_ops xfs_page_mkwrite_iomap_ops = { + .iomap_begin = xfs_buffered_write_iomap_begin, +}; + static int xfs_read_iomap_begin( struct inode *inode, diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index c782e8c0479c..0f62ab633040 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -47,6 +47,7 @@ xfs_aligned_fsb_count( } extern const struct iomap_ops xfs_buffered_write_iomap_ops; +extern const struct iomap_ops xfs_page_mkwrite_iomap_ops; extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; -- 2.45.0.rc1.225.g2a3ae87e7f-goog

12 months

3
30
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2024