!775 Backport CVEs and bugfixes

Merge Pull Request from: @zhangjialin11 
 
Pull new CVEs:
CVE-2023-32269
CVE-2023-2002
CVE-2023-26544
CVE-2023-0459

mm bugfixes from Yu Kuai
fs bugfix from yangerkun
fs perfs from Zhihao Cheng 
 
Link:https://gitee.com/openeuler/kernel/pulls/775 

Reviewed-by: Zheng Zengkai <zhengzengkai@huawei.com> 
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com> 

fs/ntfs3/attrib.c

@@ -101,6 +101,10 @@ int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
 
 	asize = le32_to_cpu(attr->size);
 	run_off = le16_to_cpu(attr->nres.run_off);
+
+	if (run_off > asize)
+		return -EINVAL;
+
 	err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn,
 			    vcn ? *vcn : svcn, Add2Ptr(attr, run_off),
 			    asize - run_off);
@@ -1157,6 +1161,10 @@ int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	}
 
 	ro = le16_to_cpu(attr->nres.run_off);
+
+	if (ro > le32_to_cpu(attr->size))
+		return -EINVAL;
+
 	err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, svcn,
 			    Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro);
 	if (err < 0)
@@ -1832,6 +1840,11 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 			u16 le_sz;
 			u16 roff = le16_to_cpu(attr->nres.run_off);
 
+			if (roff > le32_to_cpu(attr->size)) {
+				err = -EINVAL;
+				goto out;
+			}
+
 			run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn,
 				      evcn1 - 1, svcn, Add2Ptr(attr, roff),
 				      le32_to_cpu(attr->size) - roff);

fs/ntfs3/attrlist.c

@@ -68,6 +68,11 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
 
 		run_init(&ni->attr_list.run);
 
+		if (run_off > le32_to_cpu(attr->size)) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		err = run_unpack_ex(&ni->attr_list.run, ni->mi.sbi, ni->mi.rno,
 				    0, le64_to_cpu(attr->nres.evcn), 0,
 				    Add2Ptr(attr, run_off),

fs/ntfs3/frecord.c

@@ -567,6 +567,12 @@ static int ni_repack(struct ntfs_inode *ni)
 		}
 
 		roff = le16_to_cpu(attr->nres.run_off);
+
+		if (roff > le32_to_cpu(attr->size)) {
+			err = -EINVAL;
+			break;
+		}
+
 		err = run_unpack(&run, sbi, ni->mi.rno, svcn, evcn, svcn,
 				 Add2Ptr(attr, roff),
 				 le32_to_cpu(attr->size) - roff);
@@ -1541,6 +1547,9 @@ int ni_delete_all(struct ntfs_inode *ni)
 		asize = le32_to_cpu(attr->size);
 		roff = le16_to_cpu(attr->nres.run_off);
 
+		if (roff > asize)
+			return -EINVAL;
+
 		/* run==1 means unpack and deallocate. */
 		run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn, svcn,
 			      Add2Ptr(attr, roff), asize - roff);
@@ -2238,6 +2247,11 @@ int ni_decompress_file(struct ntfs_inode *ni)
 		asize = le32_to_cpu(attr->size);
 		roff = le16_to_cpu(attr->nres.run_off);
 
+		if (roff > asize) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		/*run==1  Means unpack and deallocate. */
 		run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn, svcn,
 			      Add2Ptr(attr, roff), asize - roff);

fs/ntfs3/fslog.c

@@ -2727,6 +2727,9 @@ static inline bool check_attr(const struct MFT_REC *rec,
 			return false;
 		}
 
+		if (run_off > asize)
+			return false;
+
 		if (run_unpack(NULL, sbi, 0, svcn, evcn, svcn,
 			       Add2Ptr(attr, run_off), asize - run_off) < 0) {
 			return false;
@@ -4767,6 +4770,12 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 		u16 roff = le16_to_cpu(attr->nres.run_off);
 		CLST svcn = le64_to_cpu(attr->nres.svcn);
 
+		if (roff > t32) {
+			kfree(oa->attr);
+			oa->attr = NULL;
+			goto fake_attr;
+		}
+
 		err = run_unpack(&oa->run0, sbi, inode->i_ino, svcn,
 				 le64_to_cpu(attr->nres.evcn), svcn,
 				 Add2Ptr(attr, roff), t32 - roff);

fs/ntfs3/inode.c

@@ -373,7 +373,13 @@ static struct inode *ntfs_read_mft(struct inode *inode,
 attr_unpack_run:
 	roff = le16_to_cpu(attr->nres.run_off);
 
+	if (roff > asize) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	t64 = le64_to_cpu(attr->nres.svcn);
+
 	err = run_unpack_ex(run, sbi, ino, t64, le64_to_cpu(attr->nres.evcn),
 			    t64, Add2Ptr(attr, roff), asize - roff);
 	if (err < 0)

fs/overlayfs/dir.c

@@ -1303,6 +1303,6 @@ const struct inode_operations ovl_dir_inode_operations = {
 	.permission	= ovl_permission,
 	.getattr	= ovl_getattr,
 	.listxattr	= ovl_listxattr,
-	.get_acl	= ovl_get_acl,
+	.get_acl2	= ovl_get_acl,
 	.update_time	= ovl_update_time,
 };

fs/overlayfs/inode.c

@@ -11,6 +11,7 @@
 #include <linux/posix_acl.h>
 #include <linux/ratelimit.h>
 #include <linux/fiemap.h>
+#include <linux/namei.h>
 #include "overlayfs.h"
 
 
@@ -441,15 +442,26 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 	return res;
 }
 
-struct posix_acl *ovl_get_acl(struct inode *inode, int type)
+struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu)
 {
 	struct inode *realinode = ovl_inode_real(inode);
 	const struct cred *old_cred;
 	struct posix_acl *acl;
 
-	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
+	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL))
 		return NULL;
 
+	if (!realinode) {
+		WARN_ON(!rcu);
+		return ERR_PTR(-ECHILD);
+	}
+
+	if (!IS_POSIXACL(realinode))
+		return NULL;
+
+	if (rcu)
+		return get_cached_acl_rcu(realinode, type);
+
 	old_cred = ovl_override_creds(inode->i_sb);
 	acl = get_acl(realinode, type);
 	revert_creds(old_cred);
@@ -496,7 +508,7 @@ static const struct inode_operations ovl_file_inode_operations = {
 	.permission	= ovl_permission,
 	.getattr	= ovl_getattr,
 	.listxattr	= ovl_listxattr,
-	.get_acl	= ovl_get_acl,
+	.get_acl2	= ovl_get_acl,
 	.update_time	= ovl_update_time,
 	.fiemap		= ovl_fiemap,
 };
@@ -514,7 +526,7 @@ static const struct inode_operations ovl_special_inode_operations = {
 	.permission	= ovl_permission,
 	.getattr	= ovl_getattr,
 	.listxattr	= ovl_listxattr,
-	.get_acl	= ovl_get_acl,
+	.get_acl2	= ovl_get_acl,
 	.update_time	= ovl_update_time,
 };
 

fs/overlayfs/overlayfs.h

@@ -466,7 +466,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
 int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
-struct posix_acl *ovl_get_acl(struct inode *inode, int type);
+struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu);
 int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags);
 bool ovl_is_private_xattr(struct super_block *sb, const char *name);
 

fs/posix_acl.c

@@ -22,6 +22,7 @@
 #include <linux/xattr.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/namei.h>
 
 static struct posix_acl **acl_by_type(struct inode *inode, int type)
 {
@@ -56,7 +57,17 @@ EXPORT_SYMBOL(get_cached_acl);
 
 struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
 {
-	return rcu_dereference(*acl_by_type(inode, type));
+	struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));
+
+	if (acl == ACL_DONT_CACHE && inode->i_op->get_acl2) {
+		struct posix_acl *ret;
+
+		ret = inode->i_op->get_acl2(inode, type, LOOKUP_RCU);
+		if (!IS_ERR(ret))
+			acl = ret;
+	}
+
+	return acl;
 }
 EXPORT_SYMBOL(get_cached_acl_rcu);
 
@@ -134,11 +145,14 @@ struct posix_acl *get_acl(struct inode *inode, int type)
 	 * If the filesystem doesn't have a get_acl() function at all, we'll
 	 * just create the negative cache entry.
 	 */
-	if (!inode->i_op->get_acl) {
+	if (!inode->i_op->get_acl && !inode->i_op->get_acl2) {
 		set_cached_acl(inode, type, NULL);
 		return NULL;
 	}
-	acl = inode->i_op->get_acl(inode, type);
+	if (inode->i_op->get_acl)
+		acl = inode->i_op->get_acl(inode, type);
+	else
+		acl = inode->i_op->get_acl2(inode, type, false);
 
 	if (IS_ERR(acl)) {
 		/*

fs/xfs/xfs_buf_item.c

@@ -370,10 +370,18 @@ xfs_buf_item_format(
  * This is called to pin the buffer associated with the buf log item in memory
  * so it cannot be written out.
  *
- * We also always take a reference to the buffer log item here so that the bli
- * is held while the item is pinned in memory. This means that we can
- * unconditionally drop the reference count a transaction holds when the
- * transaction is completed.
+ * We take a reference to the buffer log item here so that the BLI life cycle
+ * extends at least until the buffer is unpinned via xfs_buf_item_unpin() and
+ * inserted into the AIL.
+ *
+ * We also need to take a reference to the buffer itself as the BLI unpin
+ * processing requires accessing the buffer after the BLI has dropped the final
+ * BLI reference. See xfs_buf_item_unpin() for an explanation.
+ * If unpins race to drop the final BLI reference and only the
+ * BLI owns a reference to the buffer, then the loser of the race can have the
+ * buffer fgreed from under it (e.g. on shutdown). Taking a buffer reference per
+ * pin count ensures the life cycle of the buffer extends for as
+ * long as we hold the buffer pin reference in xfs_buf_item_unpin().
  */
 STATIC void
 xfs_buf_item_pin(
@@ -388,13 +396,30 @@ xfs_buf_item_pin(
 
 	trace_xfs_buf_item_pin(bip);
 
+	xfs_buf_hold(bip->bli_buf);
 	atomic_inc(&bip->bli_refcount);
 	atomic_inc(&bip->bli_buf->b_pin_count);
 }
 
 /*
- * This is called to unpin the buffer associated with the buf log item which
- * was previously pinned with a call to xfs_buf_item_pin().
+ * This is called to unpin the buffer associated with the buf log item which was
+ * previously pinned with a call to xfs_buf_item_pin().  We enter this function
+ * with a buffer pin count, a buffer reference and a BLI reference.
+ *
+ * We must drop the BLI reference before we unpin the buffer because the AIL
+ * doesn't acquire a BLI reference whenever it accesses it. Therefore if the
+ * refcount drops to zero, the bli could still be AIL resident and the buffer
+ * submitted for I/O at any point before we return. This can result in IO
+ * completion freeing the buffer while we are still trying to access it here.
+ * This race condition can also occur in shutdown situations where we abort and
+ * unpin buffers from contexts other that journal IO completion.
+ *
+ * Hence we have to hold a buffer reference per pin count to ensure that the
+ * buffer cannot be freed until we have finished processing the unpin operation.
+ * The reference is taken in xfs_buf_item_pin(), and we must hold it until we
+ * are done processing the buffer state. In the case of an abort (remove =
+ * true) then we re-use the current pin reference as the IO reference we hand
+ * off to IO failure handling.
  */
 STATIC void
 xfs_buf_item_unpin(
@@ -411,24 +436,18 @@ xfs_buf_item_unpin(
 
 	trace_xfs_buf_item_unpin(bip);
 
-	/*
-	 * Drop the bli ref associated with the pin and grab the hold required
-	 * for the I/O simulation failure in the abort case. We have to do this
-	 * before the pin count drops because the AIL doesn't acquire a bli
-	 * reference. Therefore if the refcount drops to zero, the bli could
-	 * still be AIL resident and the buffer submitted for I/O (and freed on
-	 * completion) at any point before we return. This can be removed once
-	 * the AIL properly holds a reference on the bli.
-	 */
 	freed = atomic_dec_and_test(&bip->bli_refcount);
-	if (freed && !stale && remove)
-		xfs_buf_hold(bp);
 	if (atomic_dec_and_test(&bp->b_pin_count))
 		wake_up_all(&bp->b_waiters);
 
-	 /* nothing to do but drop the pin count if the bli is active */
-	if (!freed)
+	 /*
+	  * Nothing to do but drop the buffer pin reference if the BLI is
+	  * still active
+	  */
+	if (!freed) {
+		xfs_buf_rele(bp);
 		return;
+	}
 
 	if (stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
@@ -440,6 +459,15 @@ xfs_buf_item_unpin(
 
 		trace_xfs_buf_item_unpin_stale(bip);
 
+		/*
+		 * The buffer has been locked and referenced since it was marked
+		 * stale so we own both lock and reference exclusively here. We
+		 * do not need the pin reference any more, so drop it now so
+		 * that we only have one reference to drop once item completion
+		 * processing is complete.
+		 */
+		xfs_buf_rele(bp);
+
 		/*
 		 * If we get called here because of an IO error, we may or may
 		 * not have the item on the AIL. xfs_trans_ail_delete() will
@@ -456,16 +484,30 @@ xfs_buf_item_unpin(
 			ASSERT(bp->b_log_item == NULL);
 		}
 		xfs_buf_relse(bp);
-	} else if (remove) {
+		return;
+	}
+
+	if (remove) {
 		/*
-		 * The buffer must be locked and held by the caller to simulate
-		 * an async I/O failure. We acquired the hold for this case
-		 * before the buffer was unpinned.
+		 * We need to simulate an async IO failures here to ensure that
+		 * the correct error completion is run on this buffer. This
+		 * requires a reference to the buffer and for the buffer to be
+		 * locked. We can safely pass ownership of the pin reference to
+		 * the IO to ensure that nothing can free the buffer while we
+		 * wait for the lock and then run the IO failure completion.
 		 */
 		xfs_buf_lock(bp);
 		bp->b_flags |= XBF_ASYNC;
 		xfs_buf_ioend_fail(bp);
+		return;
 	}
+
+	/*
+	 * BLI has no more active references - it will be moved to the AIL to
+	 * manage the remaining BLI/buffer life cycle. There is nothing left for
+	 * us to do here so drop the pin reference to the buffer.
+	 */
+	xfs_buf_rele(bp);
 }
 
 STATIC uint

include/linux/fs.h

@@ -600,6 +600,11 @@ static inline void mapping_allow_writable(struct address_space *mapping)
 
 struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
+/*
+ * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
+ * cache the ACL.  This also means that ->get_acl2() can be called in RCU mode
+ * with the LOOKUP_RCU flag.
+ */
 #define ACL_DONT_CACHE ((void *)(-3))
 
 static inline struct posix_acl *
@@ -1934,7 +1939,7 @@ struct inode_operations {
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 
-	KABI_RESERVE(1)
+	KABI_USE(1, struct posix_acl * (*get_acl2)(struct inode *, int, bool))
 	KABI_RESERVE(2)
 	KABI_RESERVE(3)
 	KABI_RESERVE(4)

include/linux/nospec.h

@@ -11,6 +11,10 @@
 
 struct task_struct;
 
+#ifndef barrier_nospec
+# define barrier_nospec() do { } while (0)
+#endif
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index

include/linux/posix_acl.h

@@ -71,6 +71,8 @@ extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t);
 extern struct posix_acl *get_posix_acl(struct inode *, int);
 extern int set_posix_acl(struct inode *, int, struct posix_acl *);
 
+struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type);
+
 #ifdef CONFIG_FS_POSIX_ACL
 extern int posix_acl_chmod(struct inode *, umode_t);
 extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **,
@@ -81,7 +83,6 @@ extern int simple_set_acl(struct inode *, struct posix_acl *, int);
 extern int simple_acl_create(struct inode *, struct inode *);
 
 struct posix_acl *get_cached_acl(struct inode *inode, int type);
-struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type);
 void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl);
 void forget_cached_acl(struct inode *inode, int type);
 void forget_all_cached_acls(struct inode *inode);

kernel/bpf/core.c

@@ -32,6 +32,7 @@
 #include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/log2.h>
+#include <linux/nospec.h>
 
 #include <asm/barrier.h>
 #include <asm/unaligned.h>
@@ -1642,9 +1643,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 		 * reuse preexisting logic from Spectre v1 mitigation that
 		 * happens to produce the required code on x86 for v4 as well.
 		 */
-#ifdef CONFIG_X86
 		barrier_nospec();
-#endif
 		CONT;
 #define LDST(SIZEOP, SIZE)						\
 	STX_MEM_##SIZEOP:						\

lib/usercopy.c

@@ -3,6 +3,7 @@
 #include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 /* out-of-line parts */
 
@@ -12,6 +13,12 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n
 	unsigned long res = n;
 	might_fault();
 	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+		/*
+		 * Ensure that bad access_ok() speculation will not
+		 * lead to nasty side effects *after* the copy is
+		 * finished:
+		 */
+		barrier_nospec();
 		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}

mm/filemap.c

@@ -2534,7 +2534,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		 * When a read accesses a page several times, only
 		 * mark it as accessed the first time.
 		 */
-		if (pos_same_page(iocb->ki_pos, ra->prev_pos -1, pages[0]))
+		if (!pos_same_page(iocb->ki_pos, ra->prev_pos -1, pages[0]))
 			mark_page_accessed(pages[0]);
 		for (i = 1; i < pg_nr; i++)
 			mark_page_accessed(pages[i]);

net/bluetooth/hci_sock.c

@@ -1000,7 +1000,14 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,
 	if (hci_sock_gen_cookie(sk)) {
 		struct sk_buff *skb;
 
-		if (capable(CAP_NET_ADMIN))
+		/* Perform careful checks before setting the HCI_SOCK_TRUSTED
+		 * flag. Make sure that not only the current task but also
+		 * the socket opener has the required capability, since
+		 * privileged programs can be tricked into making ioctl calls
+		 * on HCI sockets, and the socket should not be marked as
+		 * trusted simply because the ioctl caller is privileged.
+		 */
+		if (sk_capable(sk, CAP_NET_ADMIN))
 			hci_sock_set_flag(sk, HCI_SOCK_TRUSTED);
 
 		/* Send event to monitor */

net/netrom/af_netrom.c

@@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog)
 	struct sock *sk = sock->sk;
 
 	lock_sock(sk);
+	if (sock->state != SS_UNCONNECTED) {
+		release_sock(sk);
+		return -EINVAL;
+	}
+
 	if (sk->sk_state != TCP_LISTEN) {
 		memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN);
 		sk->sk_max_ack_backlog = backlog;