!591 Backport CVEs and bugfixes

Merge Pull Request from: @zhangjialin11 
 
Pull new CVEs:
CVE-2023-1829
CVE-2022-36280
CVE-2022-1015
CVE-2023-1989
CVE-2023-30456
CVE-2023-1990

xfs bugfixes from Long Li and yangerkun 
 
Link:https://gitee.com/openeuler/kernel/pulls/591 

Reviewed-by: Xie XiuQi <xiexiuqi@huawei.com> 
Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com> 

Documentation/admin-guide/xfs.rst

@@ -296,7 +296,7 @@ The following sysctls are available for the XFS filesystem:
 		XFS_ERRLEVEL_LOW:       1
 		XFS_ERRLEVEL_HIGH:      5
 
-  fs.xfs.panic_mask		(Min: 0  Default: 0  Max: 256)
+  fs.xfs.panic_mask		(Min: 0  Default: 0  Max: 511)
 	Causes certain error conditions to call BUG(). Value is a bitmask;
 	OR together the tags which represent errors which should cause panics:
 

arch/x86/kvm/vmx/nested.c

@@ -2986,7 +2986,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					struct vmcs12 *vmcs12,
 					enum vm_entry_failure_code *entry_failure_code)
 {
-	bool ia32e;
+	bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
 
 	*entry_failure_code = ENTRY_FAIL_DEFAULT;
 
@@ -3012,6 +3012,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					   vmcs12->guest_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
+	if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
+		return -EINVAL;
+
+	if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+	    CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -3023,7 +3030,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	 */
 	if (to_vmx(vcpu)->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
-		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
 		if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
 		    CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
 		    CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&

drivers/bluetooth/btsdio.c

@@ -355,6 +355,7 @@ static void btsdio_remove(struct sdio_func *func)
 	if (!data)
 		return;
 
+	cancel_work_sync(&data->work);
 	hdev = data->hdev;
 
 	sdio_set_drvdata(func, NULL);

drivers/gpu/drm/vmwgfx/vmwgfx_kms.c

@@ -182,7 +182,8 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 	if (cmd->dma.guest.ptr.offset % PAGE_SIZE ||
 	    box->x != 0    || box->y != 0    || box->z != 0    ||
 	    box->srcx != 0 || box->srcy != 0 || box->srcz != 0 ||
-	    box->d != 1    || box_count != 1) {
+	    box->d != 1    || box_count != 1 ||
+	    box->w > 64 || box->h > 64) {
 		/* TODO handle none page aligned offsets */
 		/* TODO handle more dst & src != 0 */
 		/* TODO handle more then one copy */

drivers/nfc/st-nci/ndlc.c

@@ -286,13 +286,15 @@ EXPORT_SYMBOL(ndlc_probe);
 
 void ndlc_remove(struct llt_ndlc *ndlc)
 {
-	st_nci_remove(ndlc->ndev);
-
 	/* cancel timers */
 	del_timer_sync(&ndlc->t1_timer);
 	del_timer_sync(&ndlc->t2_timer);
 	ndlc->t2_active = false;
 	ndlc->t1_active = false;
+	/* cancel work */
+	cancel_work_sync(&ndlc->sm_work);
+
+	st_nci_remove(ndlc->ndev);
 
 	skb_queue_purge(&ndlc->rcv_q);
 	skb_queue_purge(&ndlc->send_q);

fs/xfs/libxfs/xfs_bmap.c

@@ -926,13 +926,15 @@ xfs_bmap_add_attrfork_btree(
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
+	struct xfs_btree_block	*block = ip->i_df.if_broot;
 	xfs_btree_cur_t		*cur;		/* btree cursor */
 	int			error;		/* error return value */
 	xfs_mount_t		*mp;		/* file system mount struct */
 	int			stat;		/* newroot status */
 
 	mp = ip->i_mount;
-	if (ip->i_df.if_broot_bytes <= xfs_inode_data_fork_size(ip))
+
+	if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(ip))
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
@@ -4053,7 +4055,7 @@ xfs_bmap_alloc_userdata(
 	 * the busy list.
 	 */
 	bma->datatype = XFS_ALLOC_NOBUSY;
-	if (whichfork == XFS_DATA_FORK) {
+	if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) {
 		bma->datatype |= XFS_ALLOC_USERDATA;
 		if (bma->offset == 0)
 			bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;

fs/xfs/libxfs/xfs_btree.c

@@ -2840,9 +2840,22 @@ xfs_btree_split_worker(
 }
 
 /*
- * BMBT split requests often come in with little stack to work on. Push
+ * BMBT split requests often come in with little stack to work on so we push
  * them off to a worker thread so there is lots of stack to use. For the other
  * btree types, just call directly to avoid the context switch overhead here.
+ *
+ * Care must be taken here - the work queue rescuer thread introduces potential
+ * AGF <> worker queue deadlocks if the BMBT block allocation has to lock new
+ * AGFs to allocate blocks. A task being run by the rescuer could attempt to
+ * lock an AGF that is already locked by a task queued to run by the rescuer,
+ * resulting in an ABBA deadlock as the rescuer cannot run the lock holder to
+ * release it until the current thread it is running gains the lock.
+ *
+ * To avoid this issue, we only ever queue BMBT splits that don't have an AGF
+ * already locked to allocate from. The only place that doesn't hold an AGF
+ * locked is unwritten extent conversion at IO completion, but that has already
+ * been offloaded to a worker thread and hence has no stack consumption issues
+ * we have to worry about.
  */
 STATIC int					/* error */
 xfs_btree_split(
@@ -2856,7 +2869,8 @@ xfs_btree_split(
 	struct xfs_btree_split_args	args;
 	DECLARE_COMPLETION_ONSTACK(done);
 
-	if (cur->bc_btnum != XFS_BTNUM_BMAP)
+	if (cur->bc_btnum != XFS_BTNUM_BMAP ||
+	    cur->bc_tp->t_firstblock == NULLFSBLOCK)
 		return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
 
 	args.cur = cur;

fs/xfs/libxfs/xfs_log_format.h

@@ -580,7 +580,7 @@ typedef struct xfs_efi_log_format {
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_t		efi_extents[];	/* array of extents to free */
 } xfs_efi_log_format_t;
 
 typedef struct xfs_efi_log_format_32 {
@@ -588,7 +588,7 @@ typedef struct xfs_efi_log_format_32 {
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_32_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_32_t		efi_extents[];	/* array of extents to free */
 } __attribute__((packed)) xfs_efi_log_format_32_t;
 
 typedef struct xfs_efi_log_format_64 {
@@ -596,7 +596,7 @@ typedef struct xfs_efi_log_format_64 {
 	uint16_t		efi_size;	/* size of this item */
 	uint32_t		efi_nextents;	/* # extents to free */
 	uint64_t		efi_id;		/* efi identifier */
-	xfs_extent_64_t		efi_extents[1];	/* array of extents to free */
+	xfs_extent_64_t		efi_extents[];	/* array of extents to free */
 } xfs_efi_log_format_64_t;
 
 /*
@@ -609,7 +609,7 @@ typedef struct xfs_efd_log_format {
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_t		efd_extents[];	/* array of extents freed */
 } xfs_efd_log_format_t;
 
 typedef struct xfs_efd_log_format_32 {
@@ -617,7 +617,7 @@ typedef struct xfs_efd_log_format_32 {
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_32_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_32_t		efd_extents[];	/* array of extents freed */
 } __attribute__((packed)) xfs_efd_log_format_32_t;
 
 typedef struct xfs_efd_log_format_64 {
@@ -625,7 +625,7 @@ typedef struct xfs_efd_log_format_64 {
 	uint16_t		efd_size;	/* size of this item */
 	uint32_t		efd_nextents;	/* # of extents freed */
 	uint64_t		efd_efi_id;	/* id of corresponding efi */
-	xfs_extent_64_t		efd_extents[1];	/* array of extents freed */
+	xfs_extent_64_t		efd_extents[];	/* array of extents freed */
 } xfs_efd_log_format_64_t;
 
 /*

fs/xfs/libxfs/xfs_log_recover.h

@@ -108,12 +108,6 @@ struct xlog_recover {
 
 #define ITEM_TYPE(i)	(*(unsigned short *)(i)->ri_buf[0].i_addr)
 
-/*
- * This is the number of entries in the l_buf_cancel_table used during
- * recovery.
- */
-#define	XLOG_BC_TABLE_SIZE	64
-
 #define	XLOG_RECOVER_CRCPASS	0
 #define	XLOG_RECOVER_PASS1	1
 #define	XLOG_RECOVER_PASS2	2
@@ -124,5 +118,13 @@ bool xlog_is_buffer_cancelled(struct xlog *log, xfs_daddr_t blkno, uint len);
 
 void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type,
 		uint64_t intent_id);
+int xlog_alloc_buf_cancel_table(struct xlog *log);
+void xlog_free_buf_cancel_table(struct xlog *log);
+
+#ifdef DEBUG
+void xlog_check_buf_cancel_table(struct xlog *log);
+#else
+#define xlog_check_buf_cancel_table(log) do { } while (0)
+#endif
 
 #endif	/* __XFS_LOG_RECOVER_H__ */

fs/xfs/xfs_bmap_item.c

@@ -590,28 +590,18 @@ static const struct xfs_item_ops xfs_bui_item_ops = {
 	.iop_relog	= xfs_bui_item_relog,
 };
 
-/*
- * Copy an BUI format buffer from the given buf, and into the destination
- * BUI format structure.  The BUI/BUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
 xfs_bui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_bui_log_format	*dst_bui_fmt)
+	struct xfs_bui_log_format	*dst,
+	const struct xfs_bui_log_format	*src)
 {
-	struct xfs_bui_log_format	*src_bui_fmt;
-	uint				len;
+	unsigned int			i;
 
-	src_bui_fmt = buf->i_addr;
-	len = xfs_bui_log_format_sizeof(src_bui_fmt->bui_nextents);
+	memcpy(dst, src, offsetof(struct xfs_bui_log_format, bui_extents));
 
-	if (buf->i_len == len) {
-		memcpy(dst_bui_fmt, src_bui_fmt, len);
-		return 0;
-	}
-	XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-	return -EFSCORRUPTED;
+	for (i = 0; i < src->bui_nextents; i++)
+		memcpy(&dst->bui_extents[i], &src->bui_extents[i],
+				sizeof(struct xfs_map_extent));
 }
 
 /*
@@ -628,23 +618,31 @@ xlog_recover_bui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_bui_log_item		*buip;
 	struct xfs_bui_log_format	*bui_formatp;
+	size_t				len;
 
 	bui_formatp = item->ri_buf[0].i_addr;
 
+	if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
 	if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
 		return -EFSCORRUPTED;
 	}
-	buip = xfs_bui_init(mp);
-	error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format);
-	if (error) {
-		xfs_bui_item_free(buip);
-		return error;
+
+	len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
 	}
+
+	buip = xfs_bui_init(mp);
+	xfs_bui_copy_format(&buip->bui_format, bui_formatp);
 	atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so

fs/xfs/xfs_buf.c

@@ -1947,6 +1947,7 @@ xfs_free_buftarg(
 	list_lru_destroy(&btp->bt_lru);
 
 	xfs_blkdev_issue_flush(btp);
+	invalidate_bdev(btp->bt_bdev);
 
 	kmem_free(btp);
 }

fs/xfs/xfs_buf_item_recover.c

@@ -23,6 +23,15 @@
 #include "xfs_dir2.h"
 #include "xfs_quota.h"
 
+/*
+ * This is the number of entries in the l_buf_cancel_table used during
+ * recovery.
+ */
+#define	XLOG_BC_TABLE_SIZE	64
+
+#define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
+	((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
+
 /*
  * This structure is used during recovery to record the buf log items which
  * have been canceled and should not be replayed.
@@ -993,3 +1002,60 @@ const struct xlog_recover_item_ops xlog_buf_item_ops = {
 	.commit_pass1		= xlog_recover_buf_commit_pass1,
 	.commit_pass2		= xlog_recover_buf_commit_pass2,
 };
+
+#ifdef DEBUG
+void
+xlog_check_buf_cancel_table(
+	struct xlog	*log)
+{
+	int		i;
+
+	for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
+		ASSERT(list_empty(&log->l_buf_cancel_table[i]));
+}
+#endif
+
+int
+xlog_alloc_buf_cancel_table(
+	struct xlog	*log)
+{
+	void		*p;
+	int		i;
+
+	ASSERT(log->l_buf_cancel_table == NULL);
+
+	p = kmalloc_array(XLOG_BC_TABLE_SIZE, sizeof(struct list_head),
+			  GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	log->l_buf_cancel_table = p;
+	for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
+		INIT_LIST_HEAD(&log->l_buf_cancel_table[i]);
+
+	return 0;
+}
+
+void
+xlog_free_buf_cancel_table(
+	struct xlog	*log)
+{
+	int		i;
+
+	if (!log->l_buf_cancel_table)
+		return;
+
+	for (i = 0; i < XLOG_BC_TABLE_SIZE; i++) {
+		struct xfs_buf_cancel	*bc;
+
+		while ((bc = list_first_entry_or_null(
+				&log->l_buf_cancel_table[i],
+				struct xfs_buf_cancel, bc_list))) {
+			list_del(&bc->bc_list);
+			kmem_free(bc);
+		}
+	}
+
+	kmem_free(log->l_buf_cancel_table);
+	log->l_buf_cancel_table = NULL;
+}

fs/xfs/xfs_error.h

@@ -62,7 +62,7 @@ extern int xfs_errortag_clearall(struct xfs_mount *mp);
 
 /*
  * XFS panic tags -- allow a call to xfs_alert_tag() be turned into
- *			a panic by setting xfs_panic_mask in a sysctl.
+ *			a panic by setting fs.xfs.panic_mask in a sysctl.
  */
 #define		XFS_NO_PTAG			0
 #define		XFS_PTAG_IFLUSH			0x00000001
@@ -75,4 +75,14 @@ extern int xfs_errortag_clearall(struct xfs_mount *mp);
 #define		XFS_PTAG_FSBLOCK_ZERO		0x00000080
 #define		XFS_PTAG_VERIFIER_ERROR		0x00000100
 
+#define		XFS_PTAG_MASK	(XFS_PTAG_IFLUSH | \
+				 XFS_PTAG_LOGRES | \
+				 XFS_PTAG_AILDELETE | \
+				 XFS_PTAG_ERROR_REPORT | \
+				 XFS_PTAG_SHUTDOWN_CORRUPT | \
+				 XFS_PTAG_SHUTDOWN_IOERROR | \
+				 XFS_PTAG_SHUTDOWN_LOGERROR | \
+				 XFS_PTAG_FSBLOCK_ZERO | \
+				 XFS_PTAG_VERIFIER_ERROR)
+
 #endif	/* __XFS_ERROR_H__ */

fs/xfs/xfs_extent_busy.c

@@ -244,6 +244,7 @@ xfs_extent_busy_update_extent(
 		 *
 		 */
 		busyp->bno = fend;
+		busyp->length = bend - fend;
 	} else if (bbno < fbno) {
 		/*
 		 * Case 8:

fs/xfs/xfs_extfree_item.c

@@ -74,7 +74,7 @@ xfs_efi_item_sizeof(
 	struct xfs_efi_log_item *efip)
 {
 	return sizeof(struct xfs_efi_log_format) +
-	       (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t);
+	       efip->efi_format.efi_nextents * sizeof(xfs_extent_t);
 }
 
 STATIC void
@@ -158,7 +158,7 @@ xfs_efi_init(
 	ASSERT(nextents > 0);
 	if (nextents > XFS_EFI_MAX_FAST_EXTENTS) {
 		size = (uint)(sizeof(struct xfs_efi_log_item) +
-			((nextents - 1) * sizeof(xfs_extent_t)));
+			(nextents * sizeof(xfs_extent_t)));
 		efip = kmem_zalloc(size, 0);
 	} else {
 		efip = kmem_cache_zalloc(xfs_efi_zone,
@@ -187,14 +187,19 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
 	xfs_efi_log_format_t *src_efi_fmt = buf->i_addr;
 	uint i;
 	uint len = sizeof(xfs_efi_log_format_t) + 
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t);  
+		src_efi_fmt->efi_nextents * sizeof(xfs_extent_t);  
 	uint len32 = sizeof(xfs_efi_log_format_32_t) + 
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t);  
+		src_efi_fmt->efi_nextents * sizeof(xfs_extent_32_t);  
 	uint len64 = sizeof(xfs_efi_log_format_64_t) + 
-		(src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t);  
+		src_efi_fmt->efi_nextents * sizeof(xfs_extent_64_t);  
 
 	if (buf->i_len == len) {
-		memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len);
+		memcpy(dst_efi_fmt, src_efi_fmt,
+		       offsetof(struct xfs_efi_log_format, efi_extents));
+		for (i = 0; i < src_efi_fmt->efi_nextents; i++)
+			memcpy(&dst_efi_fmt->efi_extents[i],
+			       &src_efi_fmt->efi_extents[i],
+			       sizeof(struct xfs_extent));
 		return 0;
 	} else if (buf->i_len == len32) {
 		xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr;
@@ -254,7 +259,7 @@ xfs_efd_item_sizeof(
 	struct xfs_efd_log_item *efdp)
 {
 	return sizeof(xfs_efd_log_format_t) +
-	       (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t);
+	       efdp->efd_format.efd_nextents * sizeof(xfs_extent_t);
 }
 
 STATIC void
@@ -330,7 +335,7 @@ xfs_trans_get_efd(
 
 	if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
 		efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) +
-				(nextents - 1) * sizeof(struct xfs_extent),
+				nextents * sizeof(struct xfs_extent),
 				0);
 	} else {
 		efdp = kmem_cache_zalloc(xfs_efd_zone,
@@ -701,6 +706,12 @@ xlog_recover_efi_commit_pass2(
 
 	efi_formatp = item->ri_buf[0].i_addr;
 
+	if (item->ri_buf[0].i_len <
+			offsetof(struct xfs_efi_log_format, efi_extents)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
 	efip = xfs_efi_init(mp, efi_formatp->efi_nextents);
 	error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format);
 	if (error) {
@@ -740,9 +751,9 @@ xlog_recover_efd_commit_pass2(
 
 	efd_formatp = item->ri_buf[0].i_addr;
 	ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) +
-		((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) ||
+		(efd_formatp->efd_nextents * sizeof(xfs_extent_32_t)))) ||
 	       (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) +
-		((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t)))));
+		(efd_formatp->efd_nextents * sizeof(xfs_extent_64_t)))));
 
 	xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id);
 	return 0;

fs/xfs/xfs_globals.c

@@ -4,6 +4,7 @@
  * All Rights Reserved.
  */
 #include "xfs.h"
+#include "xfs_error.h"
 
 /*
  * Tunable XFS parameters.  xfs_params is required even when CONFIG_SYSCTL=n,
@@ -15,7 +16,7 @@ xfs_param_t xfs_params = {
 			  /*	MIN		DFLT		MAX	*/
 	.sgid_inherit	= {	0,		0,		1	},
 	.symlink_mode	= {	0,		0,		1	},
-	.panic_mask	= {	0,		0,		256	},
+	.panic_mask	= {	0,		0,		XFS_PTAG_MASK},
 	.error_level	= {	0,		3,		11	},
 	.syncd_timer	= {	1*100,		30*100,		7200*100},
 	.stats_clear	= {	0,		0,		1	},

fs/xfs/xfs_icache.c

@@ -991,11 +991,11 @@ xfs_reclaim_inodes(
 long
 xfs_reclaim_inodes_nr(
 	struct xfs_mount	*mp,
-	int			nr_to_scan)
+	unsigned long		nr_to_scan)
 {
 	struct xfs_icwalk	icw = {
 		.icw_flags	= XFS_ICWALK_FLAG_SCAN_LIMIT,
-		.icw_scan_limit	= nr_to_scan,
+		.icw_scan_limit	= min_t(unsigned long, LONG_MAX, nr_to_scan),
 	};
 
 	if (xfs_want_reclaim_sick(mp))
@@ -1013,13 +1013,13 @@ xfs_reclaim_inodes_nr(
  * Return the number of reclaimable inodes in the filesystem for
  * the shrinker to determine how much to reclaim.
  */
-int
+long
 xfs_reclaim_inodes_count(
 	struct xfs_mount	*mp)
 {
 	struct xfs_perag	*pag;
 	xfs_agnumber_t		ag = 0;
-	int			reclaimable = 0;
+	long			reclaimable = 0;
 
 	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
 		ag = pag->pag_agno + 1;

fs/xfs/xfs_icache.h

@@ -15,7 +15,7 @@ struct xfs_icwalk {
 	kgid_t		icw_gid;
 	prid_t		icw_prid;
 	__u64		icw_min_file_size;
-	int		icw_scan_limit;
+	long		icw_scan_limit;
 };
 
 /* Flags that reflect xfs_fs_eofblocks functionality. */
@@ -49,8 +49,8 @@ void xfs_inode_free(struct xfs_inode *ip);
 void xfs_reclaim_worker(struct work_struct *work);
 
 void xfs_reclaim_inodes(struct xfs_mount *mp);
-int xfs_reclaim_inodes_count(struct xfs_mount *mp);
-long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
+long xfs_reclaim_inodes_count(struct xfs_mount *mp);
+long xfs_reclaim_inodes_nr(struct xfs_mount *mp, unsigned long nr_to_scan);
 
 void xfs_inode_mark_reclaimable(struct xfs_inode *ip);
 

fs/xfs/xfs_inode.c

@@ -3181,16 +3181,27 @@ xfs_cross_rename(
  */
 static int
 xfs_rename_alloc_whiteout(
+	struct xfs_name		*src_name,
 	struct xfs_inode	*dp,
 	struct xfs_inode	**wip)
 {
 	struct xfs_inode	*tmpfile;
+	struct qstr		name;
 	int			error;
 
 	error = xfs_create_tmpfile(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile);
 	if (error)
 		return error;
 
+	name.name = src_name->name;
+	name.len = src_name->len;
+	error = xfs_inode_init_security(VFS_I(tmpfile), VFS_I(dp), &name);
+	if (error) {
+		xfs_finish_inode_setup(tmpfile);
+		xfs_irele(tmpfile);
+		return error;
+	}
+
 	/*
 	 * Prepare the tmpfile inode as if it were created through the VFS.
 	 * Complete the inode setup and flag it as linkable.  nlink is already
@@ -3239,7 +3250,7 @@ xfs_rename(
 	 * appropriately.
 	 */
 	if (flags & RENAME_WHITEOUT) {
-		error = xfs_rename_alloc_whiteout(target_dp, &wip);
+		error = xfs_rename_alloc_whiteout(src_name, target_dp, &wip);
 		if (error)
 			return error;
 

fs/xfs/xfs_ioctl.c

@@ -830,7 +830,7 @@ xfs_bulkstat_fmt(
 static int
 xfs_bulk_ireq_setup(
 	struct xfs_mount	*mp,
-	struct xfs_bulk_ireq	*hdr,
+	const struct xfs_bulk_ireq *hdr,
 	struct xfs_ibulk	*breq,
 	void __user		*ubuffer)
 {
@@ -856,7 +856,7 @@ xfs_bulk_ireq_setup(
 
 		switch (hdr->ino) {
 		case XFS_BULK_IREQ_SPECIAL_ROOT:
-			hdr->ino = mp->m_sb.sb_rootino;
+			breq->startino = mp->m_sb.sb_rootino;
 			break;
 		default:
 			return -EINVAL;

fs/xfs/xfs_iomap.c

@@ -871,6 +871,10 @@ xfs_buffered_write_iomap_begin(
 
 	ASSERT(!XFS_IS_REALTIME_INODE(ip));
 
+	error = xfs_qm_dqattach(ip);
+	if (error)
+		return error;
+
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
@@ -974,10 +978,6 @@ xfs_buffered_write_iomap_begin(
 			allocfork = XFS_COW_FORK;
 	}
 
-	error = xfs_qm_dqattach_locked(ip, false);
-	if (error)
-		goto out_unlock;
-
 	if (eof && offset + count > XFS_ISIZE(ip)) {
 		/*
 		 * Determine the initial size of the preallocation.

fs/xfs/xfs_iops.c

@@ -71,9 +71,8 @@ xfs_initxattrs(
  * these attrs can be journalled at inode creation time (along with the
  * inode, of course, such that log replay can't cause these to be lost).
  */
-
-STATIC int
-xfs_init_security(
+int
+xfs_inode_init_security(
 	struct inode	*inode,
 	struct inode	*dir,
 	const struct qstr *qstr)
@@ -118,7 +117,7 @@ xfs_cleanup_inode(
 
 	/* Oh, the horror.
 	 * If we can't add the ACL or we fail in
-	 * xfs_init_security we must back out.
+	 * xfs_inode_init_security we must back out.
 	 * ENOSPC can hit here, among other things.
 	 */
 	xfs_dentry_to_name(&teardown, dentry);
@@ -170,7 +169,7 @@ xfs_generic_create(
 
 	inode = VFS_I(ip);
 
-	error = xfs_init_security(inode, dir, &dentry->d_name);
+	error = xfs_inode_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 
@@ -385,7 +384,7 @@ xfs_vn_symlink(
 
 	inode = VFS_I(cip);
 
-	error = xfs_init_security(inode, dir, &dentry->d_name);
+	error = xfs_inode_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 

fs/xfs/xfs_iops.h

@@ -24,4 +24,7 @@ extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap,
 extern int xfs_vn_setattr_nonsize(struct dentry *dentry, struct iattr *vap);
 extern int xfs_vn_setattr_size(struct dentry *dentry, struct iattr *vap);
 
+int xfs_inode_init_security(struct inode *inode, struct inode *dir,
+		const struct qstr *qstr);
+
 #endif /* __XFS_IOPS_H__ */

fs/xfs/xfs_log.c

@@ -349,13 +349,15 @@ xfs_log_writable(
 	struct xfs_mount	*mp)
 {
 	/*
-	 * Never write to the log on norecovery mounts, if the block device is
-	 * read-only, or if the filesystem is shutdown. Read-only mounts still
-	 * allow internal writes for log recovery and unmount purposes, so don't
-	 * restrict that case here.
+	 * Do not write to the log on norecovery mounts, if the data or log
+	 * devices are read-only, or if the filesystem is shutdown. Read-only
+	 * mounts allow internal writes for log recovery and unmount purposes,
+	 * so don't restrict that case.
 	 */
 	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
 		return false;
+	if (xfs_readonly_buftarg(mp->m_ddev_targp))
+		return false;
 	if (xfs_readonly_buftarg(mp->m_log->l_targ))
 		return false;
 	if (XFS_FORCED_SHUTDOWN(mp))

fs/xfs/xfs_log_priv.h

@@ -444,9 +444,6 @@ struct xlog {
 	uint32_t		l_iclog_roundoff;/* padding roundoff */
 };
 
-#define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
-	((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
-
 /*
  * Bits for operational state
  */

fs/xfs/xfs_log_recover.c

@@ -3229,7 +3229,7 @@ xlog_do_log_recovery(
 	xfs_daddr_t	head_blk,
 	xfs_daddr_t	tail_blk)
 {
-	int		error, i;
+	int		error;
 
 	ASSERT(head_blk != tail_blk);
 
@@ -3237,37 +3237,25 @@ xlog_do_log_recovery(
 	 * First do a pass to find all of the cancelled buf log items.
 	 * Store them in the buf_cancel_table for use in the second pass.
 	 */
-	log->l_buf_cancel_table = kmem_zalloc(XLOG_BC_TABLE_SIZE *
-						 sizeof(struct list_head),
-						 0);
-	for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
-		INIT_LIST_HEAD(&log->l_buf_cancel_table[i]);
+	error = xlog_alloc_buf_cancel_table(log);
+	if (error)
+		return error;
 
 	error = xlog_do_recovery_pass(log, head_blk, tail_blk,
 				      XLOG_RECOVER_PASS1, NULL);
-	if (error != 0) {
-		kmem_free(log->l_buf_cancel_table);
-		log->l_buf_cancel_table = NULL;
-		return error;
-	}
+	if (error != 0)
+		goto out_cancel;
+
 	/*
 	 * Then do a second pass to actually recover the items in the log.
 	 * When it is complete free the table of buf cancel items.
 	 */
 	error = xlog_do_recovery_pass(log, head_blk, tail_blk,
 				      XLOG_RECOVER_PASS2, NULL);
-#ifdef DEBUG
-	if (!error) {
-		int	i;
-
-		for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
-			ASSERT(list_empty(&log->l_buf_cancel_table[i]));
-	}
-#endif	/* DEBUG */
-
-	kmem_free(log->l_buf_cancel_table);
-	log->l_buf_cancel_table = NULL;
-
+	if (!error)
+		xlog_check_buf_cancel_table(log);
+out_cancel:
+	xlog_free_buf_cancel_table(log);
 	return error;
 }
 

fs/xfs/xfs_ondisk.h

@@ -118,10 +118,10 @@ xfs_check_ondisk_structs(void)
 	/* log structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	28);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64,	16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32,		12);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
@@ -132,6 +132,21 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format,	56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent,		16);
+
+	XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents,	16);
+	XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents,	16);
 
 	/*
 	 * The v5 superblock format extended several v4 header structures with

fs/xfs/xfs_refcount_item.c

@@ -598,28 +598,18 @@ static const struct xfs_item_ops xfs_cui_item_ops = {
 	.iop_relog	= xfs_cui_item_relog,
 };
 
-/*
- * Copy an CUI format buffer from the given buf, and into the destination
- * CUI format structure.  The CUI/CUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
 xfs_cui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_cui_log_format	*dst_cui_fmt)
+	struct xfs_cui_log_format	*dst,
+	const struct xfs_cui_log_format	*src)
 {
-	struct xfs_cui_log_format	*src_cui_fmt;
-	uint				len;
+	unsigned int			i;
 
-	src_cui_fmt = buf->i_addr;
-	len = xfs_cui_log_format_sizeof(src_cui_fmt->cui_nextents);
+	memcpy(dst, src, offsetof(struct xfs_cui_log_format, cui_extents));
 
-	if (buf->i_len == len) {
-		memcpy(dst_cui_fmt, src_cui_fmt, len);
-		return 0;
-	}
-	XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-	return -EFSCORRUPTED;
+	for (i = 0; i < src->cui_nextents; i++)
+		memcpy(&dst->cui_extents[i], &src->cui_extents[i],
+				sizeof(struct xfs_phys_extent));
 }
 
 /*
@@ -636,19 +626,26 @@ xlog_recover_cui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_cui_log_item		*cuip;
 	struct xfs_cui_log_format	*cui_formatp;
+	size_t				len;
 
 	cui_formatp = item->ri_buf[0].i_addr;
 
-	cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
-	error = xfs_cui_copy_format(&item->ri_buf[0], &cuip->cui_format);
-	if (error) {
-		xfs_cui_item_free(cuip);
-		return error;
+	if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
+	len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
 	}
+
+	cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
+	xfs_cui_copy_format(&cuip->cui_format, cui_formatp);
 	atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so

fs/xfs/xfs_rmap_item.c

@@ -154,31 +154,6 @@ xfs_rui_init(
 	return ruip;
 }
 
-/*
- * Copy an RUI format buffer from the given buf, and into the destination
- * RUI format structure.  The RUI/RUD items were designed not to need any
- * special alignment handling.
- */
-STATIC int
-xfs_rui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_rui_log_format	*dst_rui_fmt)
-{
-	struct xfs_rui_log_format	*src_rui_fmt;
-	uint				len;
-
-	src_rui_fmt = buf->i_addr;
-	len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents);
-
-	if (buf->i_len != len) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-		return -EFSCORRUPTED;
-	}
-
-	memcpy(dst_rui_fmt, src_rui_fmt, len);
-	return 0;
-}
-
 static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip)
 {
 	return container_of(lip, struct xfs_rud_log_item, rud_item);
@@ -621,6 +596,20 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
 	.iop_relog	= xfs_rui_item_relog,
 };
 
+static inline void
+xfs_rui_copy_format(
+	struct xfs_rui_log_format	*dst,
+	const struct xfs_rui_log_format	*src)
+{
+	unsigned int			i;
+
+	memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents));
+
+	for (i = 0; i < src->rui_nextents; i++)
+		memcpy(&dst->rui_extents[i], &src->rui_extents[i],
+				sizeof(struct xfs_map_extent));
+}
+
 /*
  * This routine is called to create an in-core extent rmap update
  * item from the rui format structure which was logged on disk.
@@ -635,19 +624,26 @@ xlog_recover_rui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_rui_log_item		*ruip;
 	struct xfs_rui_log_format	*rui_formatp;
+	size_t				len;
 
 	rui_formatp = item->ri_buf[0].i_addr;
 
-	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
-	error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format);
-	if (error) {
-		xfs_rui_item_free(ruip);
-		return error;
+	if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
 	}
+
+	len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
+	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
+	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
 	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
 	/*
 	 * Insert the intent into the AIL directly and drop one reference so

fs/xfs/xfs_super.c

@@ -2023,7 +2023,7 @@ xfs_init_zones(void)
 
 	xfs_efd_zone = kmem_cache_create("xfs_efd_item",
 					(sizeof(struct xfs_efd_log_item) +
-					(XFS_EFD_MAX_FAST_EXTENTS - 1) *
+					XFS_EFD_MAX_FAST_EXTENTS *
 					sizeof(struct xfs_extent)),
 					0, 0, NULL);
 	if (!xfs_efd_zone)
@@ -2031,7 +2031,7 @@ xfs_init_zones(void)
 
 	xfs_efi_zone = kmem_cache_create("xfs_efi_item",
 					 (sizeof(struct xfs_efi_log_item) +
-					 (XFS_EFI_MAX_FAST_EXTENTS - 1) *
+					 XFS_EFI_MAX_FAST_EXTENTS *
 					 sizeof(struct xfs_extent)),
 					 0, 0, NULL);
 	if (!xfs_efi_zone)

fs/xfs/xfs_trace.h

@@ -3962,7 +3962,7 @@ DECLARE_EVENT_CLASS(xfs_icwalk_class,
 		__field(uint32_t, gid)
 		__field(prid_t, prid)
 		__field(__u64, min_file_size)
-		__field(int, scan_limit)
+		__field(long, scan_limit)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
@@ -3977,7 +3977,7 @@ DECLARE_EVENT_CLASS(xfs_icwalk_class,
 		__entry->scan_limit = icw ? icw->icw_scan_limit : 0;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu scan_limit %d caller %pS",
+	TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu scan_limit %ld caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->flags,
 		  __entry->uid,

fs/xfs/xfs_trans.c

@@ -608,19 +608,12 @@ xfs_trans_unreserve_and_mod_sb(
 		ASSERT(!error);
 	}
 
-	if (idelta) {
+	if (idelta)
 		percpu_counter_add_batch(&mp->m_icount, idelta,
 					 XFS_ICOUNT_BATCH);
-		if (idelta < 0)
-			ASSERT(__percpu_counter_compare(&mp->m_icount, 0,
-							XFS_ICOUNT_BATCH) >= 0);
-	}
 
-	if (ifreedelta) {
+	if (ifreedelta)
 		percpu_counter_add(&mp->m_ifree, ifreedelta);
-		if (ifreedelta < 0)
-			ASSERT(percpu_counter_compare(&mp->m_ifree, 0) >= 0);
-	}
 
 	if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY))
 		return;

include/net/netfilter/nf_tables.h

@@ -205,7 +205,7 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
 }
 
 int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
-unsigned int nft_parse_register(const struct nlattr *attr);
+int nft_parse_register(const struct nlattr *attr, u32 *preg);
 int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg);
 
 int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len);

net/netfilter/nf_tables_api.c

@@ -8479,17 +8479,23 @@ EXPORT_SYMBOL_GPL(nft_parse_u32_check);
  *	Registers used to be 128 bit wide, these register numbers will be
  *	mapped to the corresponding 32 bit register numbers.
  */
-unsigned int nft_parse_register(const struct nlattr *attr)
+int nft_parse_register(const struct nlattr *attr, u32 *preg)
 {
 	unsigned int reg;
 
 	reg = ntohl(nla_get_be32(attr));
 	switch (reg) {
 	case NFT_REG_VERDICT...NFT_REG_4:
-		return reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		*preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE;
+		break;
+	case NFT_REG32_00...NFT_REG32_15:
+		*preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		break;
 	default:
-		return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00;
+		return -ERANGE;
 	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_parse_register);
 
@@ -8541,7 +8547,10 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len)
 	u32 reg;
 	int err;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_load(reg, len);
 	if (err < 0)
 		return err;
@@ -8610,7 +8619,10 @@ int nft_parse_register_store(const struct nft_ctx *ctx,
 	int err;
 	u32 reg;
 
-	reg = nft_parse_register(attr);
+	err = nft_parse_register(attr, &reg);
+	if (err < 0)
+		return err;
+
 	err = nft_validate_register_store(ctx, reg, data, type, len);
 	if (err < 0)
 		return err;

net/sched/Kconfig

@@ -503,17 +503,6 @@ config NET_CLS_BASIC
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_basic.
 
-config NET_CLS_TCINDEX
-	tristate "Traffic-Control Index (TCINDEX)"
-	select NET_CLS
-	help
-	  Say Y here if you want to be able to classify packets based on
-	  traffic control indices. You will want this feature if you want
-	  to implement Differentiated Services together with DSMARK.
-
-	  To compile this code as a module, choose M here: the
-	  module will be called cls_tcindex.
-
 config NET_CLS_ROUTE4
 	tristate "Routing decision (ROUTE)"
 	depends on INET

net/sched/Makefile

@@ -69,7 +69,6 @@ obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
 obj-$(CONFIG_NET_CLS_FW)	+= cls_fw.o
 obj-$(CONFIG_NET_CLS_RSVP)	+= cls_rsvp.o
-obj-$(CONFIG_NET_CLS_TCINDEX)	+= cls_tcindex.o
 obj-$(CONFIG_NET_CLS_RSVP6)	+= cls_rsvp6.o
 obj-$(CONFIG_NET_CLS_BASIC)	+= cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)	+= cls_flow.o

net/sched/cls_tcindex.c

-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * net/sched/cls_tcindex.c	Packet classifier for skb->tc_index
- *
- * Written 1998,1999 by Werner Almesberger, EPFL ICA
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <linux/refcount.h>
-#include <linux/rcupdate.h>
-#include <net/act_api.h>
-#include <net/netlink.h>
-#include <net/pkt_cls.h>
-#include <net/sch_generic.h>
-
-/*
- * Passing parameters to the root seems to be done more awkwardly than really
- * necessary. At least, u32 doesn't seem to use such dirty hacks. To be
- * verified. FIXME.
- */
-
-#define PERFECT_HASH_THRESHOLD	64	/* use perfect hash if not bigger */
-#define DEFAULT_HASH_SIZE	64	/* optimized for diffserv */
-
-
-struct tcindex_data;
-
-struct tcindex_filter_result {
-	struct tcf_exts		exts;
-	struct tcf_result	res;
-	struct tcindex_data	*p;
-	struct rcu_work		rwork;
-};
-
-struct tcindex_filter {
-	u16 key;
-	struct tcindex_filter_result result;
-	struct tcindex_filter __rcu *next;
-	struct rcu_work rwork;
-};
-
-
-struct tcindex_data {
-	struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */
-	struct tcindex_filter __rcu **h; /* imperfect hash; */
-	struct tcf_proto *tp;
-	u16 mask;		/* AND key with mask */
-	u32 shift;		/* shift ANDed key to the right */
-	u32 hash;		/* hash table size; 0 if undefined */
-	u32 alloc_hash;		/* allocated size */
-	u32 fall_through;	/* 0: only classify if explicit match */
-	refcount_t refcnt;	/* a temporary refcnt for perfect hash */
-	struct rcu_work rwork;
-};
-
-static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
-{
-	return tcf_exts_has_actions(&r->exts) || r->res.classid;
-}
-
-static void tcindex_data_get(struct tcindex_data *p)
-{
-	refcount_inc(&p->refcnt);
-}
-
-static void tcindex_data_put(struct tcindex_data *p)
-{
-	if (refcount_dec_and_test(&p->refcnt)) {
-		kfree(p->perfect);
-		kfree(p->h);
-		kfree(p);
-	}
-}
-
-static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
-						    u16 key)
-{
-	if (p->perfect) {
-		struct tcindex_filter_result *f = p->perfect + key;
-
-		return tcindex_filter_is_set(f) ? f : NULL;
-	} else if (p->h) {
-		struct tcindex_filter __rcu **fp;
-		struct tcindex_filter *f;
-
-		fp = &p->h[key % p->hash];
-		for (f = rcu_dereference_bh_rtnl(*fp);
-		     f;
-		     fp = &f->next, f = rcu_dereference_bh_rtnl(*fp))
-			if (f->key == key)
-				return &f->result;
-	}
-
-	return NULL;
-}
-
-
-static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-			    struct tcf_result *res)
-{
-	struct tcindex_data *p = rcu_dereference_bh(tp->root);
-	struct tcindex_filter_result *f;
-	int key = (skb->tc_index & p->mask) >> p->shift;
-
-	pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n",
-		 skb, tp, res, p);
-
-	f = tcindex_lookup(p, key);
-	if (!f) {
-		struct Qdisc *q = tcf_block_q(tp->chain->block);
-
-		if (!p->fall_through)
-			return -1;
-		res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key);
-		res->class = 0;
-		pr_debug("alg 0x%x\n", res->classid);
-		return 0;
-	}
-	*res = f->res;
-	pr_debug("map 0x%x\n", res->classid);
-
-	return tcf_exts_exec(skb, &f->exts, res);
-}
-
-
-static void *tcindex_get(struct tcf_proto *tp, u32 handle)
-{
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcindex_filter_result *r;
-
-	pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
-	if (p->perfect && handle >= p->alloc_hash)
-		return NULL;
-	r = tcindex_lookup(p, handle);
-	return r && tcindex_filter_is_set(r) ? r : NULL;
-}
-
-static int tcindex_init(struct tcf_proto *tp)
-{
-	struct tcindex_data *p;
-
-	pr_debug("tcindex_init(tp %p)\n", tp);
-	p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	p->mask = 0xffff;
-	p->hash = DEFAULT_HASH_SIZE;
-	p->fall_through = 1;
-	refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */
-
-	rcu_assign_pointer(tp->root, p);
-	return 0;
-}
-
-static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
-{
-	tcf_exts_destroy(&r->exts);
-	tcf_exts_put_net(&r->exts);
-	tcindex_data_put(r->p);
-}
-
-static void tcindex_destroy_rexts_work(struct work_struct *work)
-{
-	struct tcindex_filter_result *r;
-
-	r = container_of(to_rcu_work(work),
-			 struct tcindex_filter_result,
-			 rwork);
-	rtnl_lock();
-	__tcindex_destroy_rexts(r);
-	rtnl_unlock();
-}
-
-static void __tcindex_destroy_fexts(struct tcindex_filter *f)
-{
-	tcf_exts_destroy(&f->result.exts);
-	tcf_exts_put_net(&f->result.exts);
-	kfree(f);
-}
-
-static void tcindex_destroy_fexts_work(struct work_struct *work)
-{
-	struct tcindex_filter *f = container_of(to_rcu_work(work),
-						struct tcindex_filter,
-						rwork);
-
-	rtnl_lock();
-	__tcindex_destroy_fexts(f);
-	rtnl_unlock();
-}
-
-static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
-			  bool rtnl_held, struct netlink_ext_ack *extack)
-{
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcindex_filter_result *r = arg;
-	struct tcindex_filter __rcu **walk;
-	struct tcindex_filter *f = NULL;
-
-	pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p);
-	if (p->perfect) {
-		if (!r->res.class)
-			return -ENOENT;
-	} else {
-		int i;
-
-		for (i = 0; i < p->hash; i++) {
-			walk = p->h + i;
-			for (f = rtnl_dereference(*walk); f;
-			     walk = &f->next, f = rtnl_dereference(*walk)) {
-				if (&f->result == r)
-					goto found;
-			}
-		}
-		return -ENOENT;
-
-found:
-		rcu_assign_pointer(*walk, rtnl_dereference(f->next));
-	}
-	tcf_unbind_filter(tp, &r->res);
-	/* all classifiers are required to call tcf_exts_destroy() after rcu
-	 * grace period, since converted-to-rcu actions are relying on that
-	 * in cleanup() callback
-	 */
-	if (f) {
-		if (tcf_exts_get_net(&f->result.exts))
-			tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work);
-		else
-			__tcindex_destroy_fexts(f);
-	} else {
-		tcindex_data_get(p);
-
-		if (tcf_exts_get_net(&r->exts))
-			tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
-		else
-			__tcindex_destroy_rexts(r);
-	}
-
-	*last = false;
-	return 0;
-}
-
-static void tcindex_destroy_work(struct work_struct *work)
-{
-	struct tcindex_data *p = container_of(to_rcu_work(work),
-					      struct tcindex_data,
-					      rwork);
-
-	tcindex_data_put(p);
-}
-
-static inline int
-valid_perfect_hash(struct tcindex_data *p)
-{
-	return  p->hash > (p->mask >> p->shift);
-}
-
-static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
-	[TCA_TCINDEX_HASH]		= { .type = NLA_U32 },
-	[TCA_TCINDEX_MASK]		= { .type = NLA_U16 },
-	[TCA_TCINDEX_SHIFT]		= { .type = NLA_U32 },
-	[TCA_TCINDEX_FALL_THROUGH]	= { .type = NLA_U32 },
-	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
-};
-
-static int tcindex_filter_result_init(struct tcindex_filter_result *r,
-				      struct tcindex_data *p,
-				      struct net *net)
-{
-	memset(r, 0, sizeof(*r));
-	r->p = p;
-	return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT,
-			     TCA_TCINDEX_POLICE);
-}
-
-static void tcindex_free_perfect_hash(struct tcindex_data *cp);
-
-static void tcindex_partial_destroy_work(struct work_struct *work)
-{
-	struct tcindex_data *p = container_of(to_rcu_work(work),
-					      struct tcindex_data,
-					      rwork);
-
-	rtnl_lock();
-	if (p->perfect)
-		tcindex_free_perfect_hash(p);
-	kfree(p);
-	rtnl_unlock();
-}
-
-static void tcindex_free_perfect_hash(struct tcindex_data *cp)
-{
-	int i;
-
-	for (i = 0; i < cp->hash; i++)
-		tcf_exts_destroy(&cp->perfect[i].exts);
-	kfree(cp->perfect);
-}
-
-static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
-{
-	int i, err = 0;
-
-	cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result),
-			      GFP_KERNEL | __GFP_NOWARN);
-	if (!cp->perfect)
-		return -ENOMEM;
-
-	for (i = 0; i < cp->hash; i++) {
-		err = tcf_exts_init(&cp->perfect[i].exts, net,
-				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-		if (err < 0)
-			goto errout;
-		cp->perfect[i].p = cp;
-	}
-
-	return 0;
-
-errout:
-	tcindex_free_perfect_hash(cp);
-	return err;
-}
-
-static int
-tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
-		  u32 handle, struct tcindex_data *p,
-		  struct tcindex_filter_result *r, struct nlattr **tb,
-		  struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
-{
-	struct tcindex_filter_result new_filter_result, *old_r = r;
-	struct tcindex_data *cp = NULL, *oldp;
-	struct tcindex_filter *f = NULL; /* make gcc behave */
-	struct tcf_result cr = {};
-	int err, balloc = 0;
-	struct tcf_exts e;
-	bool update_h = false;
-
-	err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	if (err < 0)
-		return err;
-	err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack);
-	if (err < 0)
-		goto errout;
-
-	err = -ENOMEM;
-	/* tcindex_data attributes must look atomic to classifier/lookup so
-	 * allocate new tcindex data and RCU assign it onto root. Keeping
-	 * perfect hash and hash pointers from old data.
-	 */
-	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
-	if (!cp)
-		goto errout;
-
-	cp->mask = p->mask;
-	cp->shift = p->shift;
-	cp->hash = p->hash;
-	cp->alloc_hash = p->alloc_hash;
-	cp->fall_through = p->fall_through;
-	cp->tp = tp;
-	refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */
-
-	if (tb[TCA_TCINDEX_HASH])
-		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
-	if (tb[TCA_TCINDEX_MASK])
-		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
-	if (tb[TCA_TCINDEX_SHIFT]) {
-		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-		if (cp->shift > 16) {
-			err = -EINVAL;
-			goto errout;
-		}
-	}
-	if (!cp->hash) {
-		/* Hash not specified, use perfect hash if the upper limit
-		 * of the hashing index is below the threshold.
-		 */
-		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
-			cp->hash = (cp->mask >> cp->shift) + 1;
-		else
-			cp->hash = DEFAULT_HASH_SIZE;
-	}
-
-	if (p->perfect) {
-		int i;
-
-		if (tcindex_alloc_perfect_hash(net, cp) < 0)
-			goto errout;
-		cp->alloc_hash = cp->hash;
-		for (i = 0; i < min(cp->hash, p->hash); i++)
-			cp->perfect[i].res = p->perfect[i].res;
-		balloc = 1;
-	}
-	cp->h = p->h;
-
-	err = tcindex_filter_result_init(&new_filter_result, cp, net);
-	if (err < 0)
-		goto errout_alloc;
-	if (old_r)
-		cr = r->res;
-
-	err = -EBUSY;
-
-	/* Hash already allocated, make sure that we still meet the
-	 * requirements for the allocated hash.
-	 */
-	if (cp->perfect) {
-		if (!valid_perfect_hash(cp) ||
-		    cp->hash > cp->alloc_hash)
-			goto errout_alloc;
-	} else if (cp->h && cp->hash != cp->alloc_hash) {
-		goto errout_alloc;
-	}
-
-	err = -EINVAL;
-	if (tb[TCA_TCINDEX_FALL_THROUGH])
-		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
-
-	if (!cp->perfect && !cp->h)
-		cp->alloc_hash = cp->hash;
-
-	/* Note: this could be as restrictive as if (handle & ~(mask >> shift))
-	 * but then, we'd fail handles that may become valid after some future
-	 * mask change. While this is extremely unlikely to ever matter,
-	 * the check below is safer (and also more backwards-compatible).
-	 */
-	if (cp->perfect || valid_perfect_hash(cp))
-		if (handle >= cp->alloc_hash)
-			goto errout_alloc;
-
-
-	err = -ENOMEM;
-	if (!cp->perfect && !cp->h) {
-		if (valid_perfect_hash(cp)) {
-			if (tcindex_alloc_perfect_hash(net, cp) < 0)
-				goto errout_alloc;
-			balloc = 1;
-		} else {
-			struct tcindex_filter __rcu **hash;
-
-			hash = kcalloc(cp->hash,
-				       sizeof(struct tcindex_filter *),
-				       GFP_KERNEL);
-
-			if (!hash)
-				goto errout_alloc;
-
-			cp->h = hash;
-			balloc = 2;
-		}
-	}
-
-	if (cp->perfect) {
-		r = cp->perfect + handle;
-	} else {
-		/* imperfect area is updated in-place using rcu */
-		update_h = !!tcindex_lookup(cp, handle);
-		r = &new_filter_result;
-	}
-
-	if (r == &new_filter_result) {
-		f = kzalloc(sizeof(*f), GFP_KERNEL);
-		if (!f)
-			goto errout_alloc;
-		f->key = handle;
-		f->next = NULL;
-		err = tcindex_filter_result_init(&f->result, cp, net);
-		if (err < 0) {
-			kfree(f);
-			goto errout_alloc;
-		}
-	}
-
-	if (tb[TCA_TCINDEX_CLASSID]) {
-		cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
-		tcf_bind_filter(tp, &cr, base);
-	}
-
-	if (old_r && old_r != r) {
-		err = tcindex_filter_result_init(old_r, cp, net);
-		if (err < 0) {
-			kfree(f);
-			goto errout_alloc;
-		}
-	}
-
-	oldp = p;
-	r->res = cr;
-	tcf_exts_change(&r->exts, &e);
-
-	rcu_assign_pointer(tp->root, cp);
-
-	if (update_h) {
-		struct tcindex_filter __rcu **fp;
-		struct tcindex_filter *cf;
-
-		f->result.res = r->res;
-		tcf_exts_change(&f->result.exts, &r->exts);
-
-		/* imperfect area bucket */
-		fp = cp->h + (handle % cp->hash);
-
-		/* lookup the filter, guaranteed to exist */
-		for (cf = rcu_dereference_bh_rtnl(*fp); cf;
-		     fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp))
-			if (cf->key == (u16)handle)
-				break;
-
-		f->next = cf->next;
-
-		cf = rcu_replace_pointer(*fp, f, 1);
-		tcf_exts_get_net(&cf->result.exts);
-		tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work);
-	} else if (r == &new_filter_result) {
-		struct tcindex_filter *nfp;
-		struct tcindex_filter __rcu **fp;
-
-		f->result.res = r->res;
-		tcf_exts_change(&f->result.exts, &r->exts);
-
-		fp = cp->h + (handle % cp->hash);
-		for (nfp = rtnl_dereference(*fp);
-		     nfp;
-		     fp = &nfp->next, nfp = rtnl_dereference(*fp))
-				; /* nothing */
-
-		rcu_assign_pointer(*fp, f);
-	} else {
-		tcf_exts_destroy(&new_filter_result.exts);
-	}
-
-	if (oldp)
-		tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
-	return 0;
-
-errout_alloc:
-	if (balloc == 1)
-		tcindex_free_perfect_hash(cp);
-	else if (balloc == 2)
-		kfree(cp->h);
-	tcf_exts_destroy(&new_filter_result.exts);
-errout:
-	kfree(cp);
-	tcf_exts_destroy(&e);
-	return err;
-}
-
-static int
-tcindex_change(struct net *net, struct sk_buff *in_skb,
-	       struct tcf_proto *tp, unsigned long base, u32 handle,
-	       struct nlattr **tca, void **arg, bool ovr,
-	       bool rtnl_held, struct netlink_ext_ack *extack)
-{
-	struct nlattr *opt = tca[TCA_OPTIONS];
-	struct nlattr *tb[TCA_TCINDEX_MAX + 1];
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcindex_filter_result *r = *arg;
-	int err;
-
-	pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p,"
-	    "p %p,r %p,*arg %p\n",
-	    tp, handle, tca, arg, opt, p, r, *arg);
-
-	if (!opt)
-		return 0;
-
-	err = nla_parse_nested_deprecated(tb, TCA_TCINDEX_MAX, opt,
-					  tcindex_policy, NULL);
-	if (err < 0)
-		return err;
-
-	return tcindex_set_parms(net, tp, base, handle, p, r, tb,
-				 tca[TCA_RATE], ovr, extack);
-}
-
-static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker,
-			 bool rtnl_held)
-{
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcindex_filter *f, *next;
-	int i;
-
-	pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p);
-	if (p->perfect) {
-		for (i = 0; i < p->hash; i++) {
-			if (!p->perfect[i].res.class)
-				continue;
-			if (walker->count >= walker->skip) {
-				if (walker->fn(tp, p->perfect + i, walker) < 0) {
-					walker->stop = 1;
-					return;
-				}
-			}
-			walker->count++;
-		}
-	}
-	if (!p->h)
-		return;
-	for (i = 0; i < p->hash; i++) {
-		for (f = rtnl_dereference(p->h[i]); f; f = next) {
-			next = rtnl_dereference(f->next);
-			if (walker->count >= walker->skip) {
-				if (walker->fn(tp, &f->result, walker) < 0) {
-					walker->stop = 1;
-					return;
-				}
-			}
-			walker->count++;
-		}
-	}
-}
-
-static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
-			    struct netlink_ext_ack *extack)
-{
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	int i;
-
-	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
-
-	if (p->perfect) {
-		for (i = 0; i < p->hash; i++) {
-			struct tcindex_filter_result *r = p->perfect + i;
-
-			/* tcf_queue_work() does not guarantee the ordering we
-			 * want, so we have to take this refcnt temporarily to
-			 * ensure 'p' is freed after all tcindex_filter_result
-			 * here. Imperfect hash does not need this, because it
-			 * uses linked lists rather than an array.
-			 */
-			tcindex_data_get(p);
-
-			tcf_unbind_filter(tp, &r->res);
-			if (tcf_exts_get_net(&r->exts))
-				tcf_queue_work(&r->rwork,
-					       tcindex_destroy_rexts_work);
-			else
-				__tcindex_destroy_rexts(r);
-		}
-	}
-
-	for (i = 0; p->h && i < p->hash; i++) {
-		struct tcindex_filter *f, *next;
-		bool last;
-
-		for (f = rtnl_dereference(p->h[i]); f; f = next) {
-			next = rtnl_dereference(f->next);
-			tcindex_delete(tp, &f->result, &last, rtnl_held, NULL);
-		}
-	}
-
-	tcf_queue_work(&p->rwork, tcindex_destroy_work);
-}
-
-
-static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
-			struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
-{
-	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcindex_filter_result *r = fh;
-	struct nlattr *nest;
-
-	pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n",
-		 tp, fh, skb, t, p, r);
-	pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
-
-	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
-	if (nest == NULL)
-		goto nla_put_failure;
-
-	if (!fh) {
-		t->tcm_handle = ~0; /* whatever ... */
-		if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) ||
-		    nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) ||
-		    nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) ||
-		    nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through))
-			goto nla_put_failure;
-		nla_nest_end(skb, nest);
-	} else {
-		if (p->perfect) {
-			t->tcm_handle = r - p->perfect;
-		} else {
-			struct tcindex_filter *f;
-			struct tcindex_filter __rcu **fp;
-			int i;
-
-			t->tcm_handle = 0;
-			for (i = 0; !t->tcm_handle && i < p->hash; i++) {
-				fp = &p->h[i];
-				for (f = rtnl_dereference(*fp);
-				     !t->tcm_handle && f;
-				     fp = &f->next, f = rtnl_dereference(*fp)) {
-					if (&f->result == r)
-						t->tcm_handle = f->key;
-				}
-			}
-		}
-		pr_debug("handle = %d\n", t->tcm_handle);
-		if (r->res.class &&
-		    nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid))
-			goto nla_put_failure;
-
-		if (tcf_exts_dump(skb, &r->exts) < 0)
-			goto nla_put_failure;
-		nla_nest_end(skb, nest);
-
-		if (tcf_exts_dump_stats(skb, &r->exts) < 0)
-			goto nla_put_failure;
-	}
-
-	return skb->len;
-
-nla_put_failure:
-	nla_nest_cancel(skb, nest);
-	return -1;
-}
-
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
-			       void *q, unsigned long base)
-{
-	struct tcindex_filter_result *r = fh;
-
-	if (r && r->res.classid == classid) {
-		if (cl)
-			__tcf_bind_filter(q, &r->res, base);
-		else
-			__tcf_unbind_filter(q, &r->res);
-	}
-}
-
-static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
-	.kind		=	"tcindex",
-	.classify	=	tcindex_classify,
-	.init		=	tcindex_init,
-	.destroy	=	tcindex_destroy,
-	.get		=	tcindex_get,
-	.change		=	tcindex_change,
-	.delete		=	tcindex_delete,
-	.walk		=	tcindex_walk,
-	.dump		=	tcindex_dump,
-	.bind_class	=	tcindex_bind_class,
-	.owner		=	THIS_MODULE,
-};
-
-static int __init init_tcindex(void)
-{
-	return register_tcf_proto_ops(&cls_tcindex_ops);
-}
-
-static void __exit exit_tcindex(void)
-{
-	unregister_tcf_proto_ops(&cls_tcindex_ops);
-}
-
-module_init(init_tcindex)
-module_exit(exit_tcindex)
-MODULE_LICENSE("GPL");