Merge 5.10.125 into android12-5.10-lts

Changes in 5.10.125 s390/mm: use non-quiescing sske for KVM switch to keyed guest zonefs: fix zonefs_iomap_begin() for reads usb: gadget: u_ether: fix regression in setting fixed MAC address tcp: add some entropy in __inet_hash_connect() tcp: use different parts of the port_offset for index and offset tcp: add small random increments to the source port tcp: dynamically allocate the perturb table used by source ports tcp: increase source port perturb table to 2^16 tcp: drop the hash_32() part from the index calculation serial: core: Initialize rs485 RTS polarity already on probe arm64: mm: Don't invalidate FROM_DEVICE buffers at start of DMA transfer io_uring: add missing item types for various requests Linux 5.10.125 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: Ie3934e1f246cb92d4775dd95120957c9fc12c30f
2022-07-28 16:06:01 +02:00
parent 4e3458d6d3 6a7c3bcc3c
commit 36c687c707
8 changed files with 124 additions and 77 deletions
--- a/2
+++ b/2
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 124
+SUBLEVEL = 125
 EXTRAVERSION =
 NAME = Dare mighty things

--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -228,8 +228,6 @@ SYM_FUNC_END_PI(__dma_flush_area)
 *	- dir	- DMA direction
 */
 SYM_FUNC_START_PI(__dma_map_area)
-	cmp	w2, #DMA_FROM_DEVICE
-	b.eq	__dma_inv_area
 	b	__dma_clean_area
 SYM_FUNC_END_PI(__dma_map_area)

--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -734,7 +734,7 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	pgste_val(pgste) |= PGSTE_GR_BIT | PGSTE_GC_BIT;
 	ptev = pte_val(*ptep);
 	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
-		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
+		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 0);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -144,6 +144,11 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear)
 	unsigned long flags;
 	unsigned int old;

+	if (port->rs485.flags & SER_RS485_ENABLED) {
+		set &= ~TIOCM_RTS;
+		clear &= ~TIOCM_RTS;
+	}
+
 	spin_lock_irqsave(&port->lock, flags);
 	old = port->mctrl;
 	port->mctrl = (old & ~clear) | set;
@@ -157,23 +162,10 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear)

 static void uart_port_dtr_rts(struct uart_port *uport, int raise)
 {
-	int rs485_on = uport->rs485_config &&
-		(uport->rs485.flags & SER_RS485_ENABLED);
-	int RTS_after_send = !!(uport->rs485.flags & SER_RS485_RTS_AFTER_SEND);
-
-	if (raise) {
-		if (rs485_on && RTS_after_send) {
-			uart_set_mctrl(uport, TIOCM_DTR);
-			uart_clear_mctrl(uport, TIOCM_RTS);
-		} else {
-			uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
-		}
-	} else {
-		unsigned int clear = TIOCM_DTR;
-
-		clear |= (!rs485_on || RTS_after_send) ? TIOCM_RTS : 0;
-		uart_clear_mctrl(uport, clear);
-	}
+	if (raise)
+		uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
+	else
+		uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
 }

 /*
@@ -1109,11 +1101,6 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 		goto out;

 	if (!tty_io_error(tty)) {
-		if (uport->rs485.flags & SER_RS485_ENABLED) {
-			set &= ~TIOCM_RTS;
-			clear &= ~TIOCM_RTS;
-		}
-
 		uart_update_mctrl(uport, set, clear);
 		ret = 0;
 	}
@@ -2417,6 +2404,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state,
 		 */
 		spin_lock_irqsave(&port->lock, flags);
 		port->mctrl &= TIOCM_DTR;
+		if (port->rs485.flags & SER_RS485_ENABLED &&
+		    !(port->rs485.flags & SER_RS485_RTS_AFTER_SEND))
+			port->mctrl |= TIOCM_RTS;
 		port->ops->set_mctrl(port, port->mctrl);
 		spin_unlock_irqrestore(&port->lock, flags);

--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -773,9 +773,13 @@ struct eth_dev *gether_setup_name(struct usb_gadget *g,
 	dev->qmult = qmult;
 	snprintf(net->name, sizeof(net->name), "%s%%d", netname);

-	if (get_ether_addr(dev_addr, net->dev_addr))
+	if (get_ether_addr(dev_addr, net->dev_addr)) {
+		net->addr_assign_type = NET_ADDR_RANDOM;
 		dev_warn(&g->dev,
 			"using random %s ethernet address\n", "self");
+	} else {
+		net->addr_assign_type = NET_ADDR_SET;
+	}
 	if (get_ether_addr(host_addr, dev->host_mac))
 		dev_warn(&g->dev,
 			"using random %s ethernet address\n", "host");
@@ -832,6 +836,9 @@ struct net_device *gether_setup_name_default(const char *netname)
 	INIT_LIST_HEAD(&dev->tx_reqs);
 	INIT_LIST_HEAD(&dev->rx_reqs);

+	/* by default we always have a random MAC address */
+	net->addr_assign_type = NET_ADDR_RANDOM;
+
 	skb_queue_head_init(&dev->rx_frames);

 	/* network device setup */
@@ -869,7 +876,6 @@ int gether_register_netdev(struct net_device *net)
 	g = dev->gadget;

 	memcpy(net->dev_addr, dev->dev_mac, ETH_ALEN);
-	net->addr_assign_type = NET_ADDR_RANDOM;

 	status = register_netdev(net);
 	if (status < 0) {
@@ -909,6 +915,7 @@ int gether_set_dev_addr(struct net_device *net, const char *dev_addr)
 	if (get_ether_addr(dev_addr, new_addr))
 		return -EINVAL;
 	memcpy(dev->dev_mac, new_addr, ETH_ALEN);
+	net->addr_assign_type = NET_ADDR_SET;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(gether_set_dev_addr);
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -773,7 +773,8 @@ static const struct io_op_def io_op_defs[] = {
 		.buffer_select		= 1,
 		.needs_async_data	= 1,
 		.async_size		= sizeof(struct io_async_rw),
-		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
+		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
+					  IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_WRITEV] = {
 		.needs_file		= 1,
@@ -783,7 +784,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_async_data	= 1,
 		.async_size		= sizeof(struct io_async_rw),
 		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
-						IO_WQ_WORK_FSIZE,
+					  IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_FSYNC] = {
 		.needs_file		= 1,
@@ -794,7 +795,8 @@ static const struct io_op_def io_op_defs[] = {
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,
 		.async_size		= sizeof(struct io_async_rw),
-		.work_flags		= IO_WQ_WORK_BLKCG | IO_WQ_WORK_MM,
+		.work_flags		= IO_WQ_WORK_BLKCG | IO_WQ_WORK_MM |
+					  IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_WRITE_FIXED] = {
 		.needs_file		= 1,
@@ -803,7 +805,7 @@ static const struct io_op_def io_op_defs[] = {
 		.pollout		= 1,
 		.async_size		= sizeof(struct io_async_rw),
 		.work_flags		= IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE |
-						IO_WQ_WORK_MM,
+					  IO_WQ_WORK_MM | IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_POLL_ADD] = {
 		.needs_file		= 1,
@@ -857,7 +859,7 @@ static const struct io_op_def io_op_defs[] = {
 		.pollout		= 1,
 		.needs_async_data	= 1,
 		.async_size		= sizeof(struct io_async_connect),
-		.work_flags		= IO_WQ_WORK_MM,
+		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_FS,
 	},
 	[IORING_OP_FALLOCATE] = {
 		.needs_file		= 1,
@@ -885,7 +887,8 @@ static const struct io_op_def io_op_defs[] = {
 		.pollin			= 1,
 		.buffer_select		= 1,
 		.async_size		= sizeof(struct io_async_rw),
-		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
+		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
+					  IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_WRITE] = {
 		.needs_file		= 1,
@@ -894,7 +897,7 @@ static const struct io_op_def io_op_defs[] = {
 		.pollout		= 1,
 		.async_size		= sizeof(struct io_async_rw),
 		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
-						IO_WQ_WORK_FSIZE,
+					  IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES,
 	},
 	[IORING_OP_FADVISE] = {
 		.needs_file		= 1,
@@ -907,14 +910,16 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.pollout		= 1,
-		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
+		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
+					  IO_WQ_WORK_FS,
 	},
 	[IORING_OP_RECV] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,
 		.buffer_select		= 1,
-		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
+		.work_flags		= IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
+					  IO_WQ_WORK_FS,
 	},
 	[IORING_OP_OPENAT2] = {
 		.work_flags		= IO_WQ_WORK_FILES | IO_WQ_WORK_FS |
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -68,15 +68,49 @@ static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
 		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
 }

-static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
-			      unsigned int flags, struct iomap *iomap,
-			      struct iomap *srcmap)
+static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
+				   loff_t length, unsigned int flags,
+				   struct iomap *iomap, struct iomap *srcmap)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	loff_t isize;

-	/* All I/Os should always be within the file maximum size */
+	/*
+	 * All blocks are always mapped below EOF. If reading past EOF,
+	 * act as if there is a hole up to the file maximum size.
+	 */
+	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		iomap->length = length;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return 0;
+}
+
+static const struct iomap_ops zonefs_read_iomap_ops = {
+	.iomap_begin	= zonefs_read_iomap_begin,
+};
+
+static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
+				    loff_t length, unsigned int flags,
+				    struct iomap *iomap, struct iomap *srcmap)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+
+	/* All write I/Os should always be within the file maximum size */
 	if (WARN_ON_ONCE(offset + length > zi->i_max_size))
 		return -EIO;

@@ -86,7 +120,7 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * operation.
 	 */
 	if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
-			 (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
+			 !(flags & IOMAP_DIRECT)))
 		return -EIO;

 	/*
@@ -95,45 +129,42 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * write pointer) and unwriten beyond.
 	 */
 	mutex_lock(&zi->i_truncate_mutex);
-	isize = i_size_read(inode);
-	if (offset >= isize)
-		iomap->type = IOMAP_UNWRITTEN;
-	else
-		iomap->type = IOMAP_MAPPED;
-	if (flags & IOMAP_WRITE)
-		length = zi->i_max_size - offset;
-	else
-		length = min(length, isize - offset);
-	mutex_unlock(&zi->i_truncate_mutex);
-
-	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
-	iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
 	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
 	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_UNWRITTEN;
+		iomap->length = zi->i_max_size - iomap->offset;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);

 	return 0;
 }

-static const struct iomap_ops zonefs_iomap_ops = {
-	.iomap_begin	= zonefs_iomap_begin,
+static const struct iomap_ops zonefs_write_iomap_ops = {
+	.iomap_begin	= zonefs_write_iomap_begin,
 };

 static int zonefs_readpage(struct file *unused, struct page *page)
 {
-	return iomap_readpage(page, &zonefs_iomap_ops);
+	return iomap_readpage(page, &zonefs_read_iomap_ops);
 }

 static void zonefs_readahead(struct readahead_control *rac)
 {
-	iomap_readahead(rac, &zonefs_iomap_ops);
+	iomap_readahead(rac, &zonefs_read_iomap_ops);
 }

 /*
 * Map blocks for page writeback. This is used only on conventional zone files,
 * which implies that the page range can only be within the fixed inode size.
 */
-static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
-			     struct inode *inode, loff_t offset)
+static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
+				   struct inode *inode, loff_t offset)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);

@@ -147,12 +178,12 @@ static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
 	    offset < wpc->iomap.offset + wpc->iomap.length)
 		return 0;

-	return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
-				  IOMAP_WRITE, &wpc->iomap, NULL);
+	return zonefs_write_iomap_begin(inode, offset, zi->i_max_size - offset,
+					IOMAP_WRITE, &wpc->iomap, NULL);
 }

 static const struct iomap_writeback_ops zonefs_writeback_ops = {
-	.map_blocks		= zonefs_map_blocks,
+	.map_blocks		= zonefs_write_map_blocks,
 };

 static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
@@ -182,7 +213,8 @@ static int zonefs_swap_activate(struct swap_info_struct *sis,
 		return -EINVAL;
 	}

-	return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+	return iomap_swapfile_activate(sis, swap_file, span,
+				       &zonefs_read_iomap_ops);
 }

 static const struct address_space_operations zonefs_file_aops = {
@@ -612,7 +644,7 @@ static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)

 	/* Serialize against truncates */
 	down_read(&zi->i_mmap_sem);
-	ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
+	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
 	up_read(&zi->i_mmap_sem);

 	sb_end_pagefault(inode->i_sb);
@@ -869,7 +901,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	if (append)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
-		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
+		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
 				   &zonefs_write_dio_ops, sync);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
@@ -911,7 +943,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 	if (ret <= 0)
 		goto inode_unlock;

-	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
 	if (ret > 0)
 		iocb->ki_pos += ret;
 	else if (ret == -EIO)
@@ -1004,7 +1036,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			goto inode_unlock;
 		}
 		file_accessed(iocb->ki_filp);
-		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
+		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
 				   &zonefs_read_dio_ops, is_sync_kiocb(iocb));
 	} else {
 		ret = generic_file_read_iter(iocb, to);
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -726,12 +726,14 @@ EXPORT_SYMBOL_GPL(inet_unhash);
 * Note that we use 32bit integers (vs RFC 'short integers')
 * because 2^16 is not a multiple of num_ephemeral and this
 * property might be used by clever attacker.
- * RFC claims using TABLE_LENGTH=10 buckets gives an improvement,
- * we use 256 instead to really give more isolation and
- * privacy, this only consumes 1 KB of kernel memory.
+ * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
+ * attacks were since demonstrated, thus we use 65536 instead to really
+ * give more isolation and privacy, at the expense of 256kB of kernel
+ * memory.
 */
-#define INET_TABLE_PERTURB_SHIFT 8
-static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT];
+#define INET_TABLE_PERTURB_SHIFT 16
+#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+static u32 *table_perturb;

 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u64 port_offset,
@@ -774,10 +776,11 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	if (likely(remaining > 1))
 		remaining &= ~1U;

-	net_get_random_once(table_perturb, sizeof(table_perturb));
-	index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT);
+	net_get_random_once(table_perturb,
+			    INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+	index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);

-	offset = READ_ONCE(table_perturb[index]) + port_offset;
+	offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
 	offset %= remaining;

 	/* In first pass we try ports of @low parity.
@@ -833,6 +836,12 @@ next_port:
 	return -EADDRNOTAVAIL;

 ok:
+	/* Here we want to add a little bit of randomness to the next source
+	 * port that will be chosen. We use a max() with a random here so that
+	 * on low contention the randomness is maximal and on high contention
+	 * it may be inexistent.
+	 */
+	i = max_t(int, i, (prandom_u32() & 7) * 2);
 	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);

 	/* Head lock still held and bh's disabled */
@@ -906,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
 					    low_limit,
 					    high_limit);
 	init_hashinfo_lhash2(h);
+
+	/* this one is used for source ports of outgoing connections */
+	table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE,
+				      sizeof(*table_perturb), GFP_KERNEL);
+	if (!table_perturb)
+		panic("TCP: failed to alloc table_perturb");
 }

 int inet_hashinfo2_init_mod(struct inet_hashinfo *h)