5.10.140-rc1 review

@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_
 
 	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
 	if (ret < 0) {
+		audit_mark->path = NULL;
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}

@@ -107,7 +107,7 @@
 #define R1(i) (((i)>>21)&0x1f)
 #define R2(i) (((i)>>16)&0x1f)
 #define R3(i) ((i)&0x1f)
-#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1))
+#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1))
 #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0))
 #define IM5_2(i) IM((i)>>16,5)
 #define IM5_3(i) IM((i),5)

@@ -268,6 +268,7 @@ COND_SYSCALL_COMPAT(keyctl);
 
 /* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
 
 /* mm/, CONFIG_MMU only */
 COND_SYSCALL(swapon);

@@ -815,6 +815,7 @@ static int amd_gpio_suspend(struct devic
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
 	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < desc->npins; i++) {

@@ -823,7 +824,9 @@ static int amd_gpio_suspend(struct devic
 		if (!amd_gpio_should_save(gpio_dev, pin))
 			continue;
 
-		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin*4);
+		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING;
+		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
 	return 0;

@@ -833,6 +836,7 @@ static int amd_gpio_resume(struct device
 {
 	struct amd_gpio *gpio_dev = dev_get_drvdata(dev);
 	struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < desc->npins; i++) {

@@ -841,7 +845,10 @@ static int amd_gpio_resume(struct device
 		if (!amd_gpio_should_save(gpio_dev, pin))
 			continue;
 
-		writel(gpio_dev->saved_regs[i], gpio_dev->base + pin*4);
+		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+		gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING;
+		writel(gpio_dev->saved_regs[i], gpio_dev->base + pin * 4);
+		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
 	return 0;

@@ -371,7 +371,7 @@ int
 xfs_ioc_attr_list(
 	struct xfs_inode		*dp,
 	void __user			*ubuf,
-	int				bufsize,
+	size_t				bufsize,
 	int				flags,
 	struct xfs_attrlist_cursor __user *ucursor)
 {

@@ -38,8 +38,9 @@ xfs_readlink_by_handle(
 int xfs_ioc_attrmulti_one(struct file *parfilp, struct inode *inode,
 		uint32_t opcode, void __user *uname, void __user *value,
 		uint32_t *len, uint32_t flags);
-int xfs_ioc_attr_list(struct xfs_inode *dp, void __user *ubuf, int bufsize,
-	int flags, struct xfs_attrlist_cursor __user *ucursor);
+int xfs_ioc_attr_list(struct xfs_inode *dp, void __user *ubuf,
+		      size_t bufsize, int flags,
+		      struct xfs_attrlist_cursor __user *ucursor);
 
 extern struct dentry *
 xfs_handle_to_dentry(

@@ -1689,7 +1689,7 @@ xfs_ioc_getbmap(
 
 	if (bmx.bmv_count < 2)
 		return -EINVAL;
-	if (bmx.bmv_count > ULONG_MAX / recsize)
+	if (bmx.bmv_count >= INT_MAX / recsize)
 		return -ENOMEM;
 
 	buf = kvzalloc(bmx.bmv_count * sizeof(*buf), GFP_KERNEL);

@@ -22,25 +22,6 @@
 			SYNC_FILE_RANGE_WAIT_AFTER)
 
 /*
- * Do the filesystem syncing work. For simple filesystems
- * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
- * submit IO for these buffers via __sync_blockdev(). This also speeds up the
- * wait == 1 case since in that case write_inode() functions do
- * sync_dirty_buffer() and thus effectively write one block at a time.
- */
-static int __sync_filesystem(struct super_block *sb, int wait)
-{
-	if (wait)
-		sync_inodes_sb(sb);
-	else
-		writeback_inodes_sb(sb, WB_REASON_SYNC);
-
-	if (sb->s_op->sync_fs)
-		sb->s_op->sync_fs(sb, wait);
-	return __sync_blockdev(sb->s_bdev, wait);
-}
-
-/*
  * Write out and wait upon all dirty data associated with this
  * superblock.  Filesystem data as well as the underlying block
  * device.  Takes the superblock lock.

@@ -61,10 +42,25 @@ int sync_filesystem(struct super_block *
 	if (sb_rdonly(sb))
 		return 0;
 
-	ret = __sync_filesystem(sb, 0);
+	/*
+	 * Do the filesystem syncing work.  For simple filesystems
+	 * writeback_inodes_sb(sb) just dirties buffers with inodes so we have
+	 * to submit I/O for these buffers via __sync_blockdev().  This also
+	 * speeds up the wait == 1 case since in that case write_inode()
+	 * methods call sync_dirty_buffer() and thus effectively write one block
+	 * at a time.
+	 */
+	writeback_inodes_sb(sb, WB_REASON_SYNC);
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, 0);
+	ret = __sync_blockdev(sb->s_bdev, 0);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1);
+
+	sync_inodes_sb(sb);
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, 1);
+	return __sync_blockdev(sb->s_bdev, 1);
 }
 EXPORT_SYMBOL(sync_filesystem);
 

@@ -28,7 +28,7 @@
  */
 int sync_filesystem(struct super_block *sb)
 {
-	int ret;
+	int ret = 0;
 
 	/*
 	 * We need to be protected against the filesystem going from

@@ -51,15 +51,21 @@ int sync_filesystem(struct super_block *
 	 * at a time.
 	 */
 	writeback_inodes_sb(sb, WB_REASON_SYNC);
-	if (sb->s_op->sync_fs)
-		sb->s_op->sync_fs(sb, 0);
+	if (sb->s_op->sync_fs) {
+		ret = sb->s_op->sync_fs(sb, 0);
+		if (ret)
+			return ret;
+	}
 	ret = __sync_blockdev(sb->s_bdev, 0);
-	if (ret < 0)
+	if (ret)
 		return ret;
 
 	sync_inodes_sb(sb);
-	if (sb->s_op->sync_fs)
-		sb->s_op->sync_fs(sb, 1);
+	if (sb->s_op->sync_fs) {
+		ret = sb->s_op->sync_fs(sb, 1);
+		if (ret)
+			return ret;
+	}
 	return __sync_blockdev(sb->s_bdev, 1);
 }
 EXPORT_SYMBOL(sync_filesystem);

@@ -757,6 +757,7 @@ xfs_fs_sync_fs(
 	int			wait)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
+	int			error;
 
 	/*
 	 * Doing anything during the async pass would be counterproductive.

@@ -764,7 +765,10 @@ xfs_fs_sync_fs(
 	if (!wait)
 		return 0;
 
-	xfs_log_force(mp, XFS_LOG_SYNC);
+	error = xfs_log_force(mp, XFS_LOG_SYNC);
+	if (error)
+		return error;
+
 	if (laptop_mode) {
 		/*
 		 * The disk must be active because we're syncing.

@@ -1720,6 +1720,11 @@ xfs_remount_ro(
 	};
 	int			error;
 
+	/* Flush all the dirty data to disk. */
+	error = sync_filesystem(mp->m_super);
+	if (error)
+		return error;
+
 	/*
 	 * Cancel background eofb scanning so it cannot race with the final
 	 * log force+buftarg wait and deadlock the remount.

@@ -1790,8 +1795,6 @@ xfs_fc_reconfigure(
 	if (error)
 		return error;
 
-	sync_filesystem(mp->m_super);
-
 	/* inode32 -> inode64 */
 	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) &&
 	    !(new_mp->m_flags & XFS_MOUNT_SMALL_INUMS)) {

@@ -542,10 +542,6 @@ struct sched_dl_entity {
 	 * task has to wait for a replenishment to be performed at the
 	 * next firing of dl_timer.
 	 *
-	 * @dl_boosted tells if we are boosted due to DI. If so we are
-	 * outside bandwidth enforcement mechanism (but only until we
-	 * exit the critical section);
-	 *
 	 * @dl_yielded tells if task gave up the CPU before consuming
 	 * all its available runtime during the last job.
 	 *

index 603b05ed7eb4c..2cd66f3e52386 100644
@@ -3641,6 +3641,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+				xfrm_pol_put(pols[0]);
 				return 0;
 			}
 			pols[1]->curlft.use_time = ktime_get_real_seconds();

index bc0bbb1571cef..fdbd56ed4bd52 100644
@@ -1557,6 +1557,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->replay = orig->replay;
 	x->preplay = orig->preplay;
 	x->mapping_maxage = orig->mapping_maxage;
+	x->lastused = orig->lastused;
 	x->new_mapping = 0;
 	x->new_mapping_sport = 0;
 

index 2aa16a171285b..05e2710988883 100644
@@ -1701,9 +1701,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		pfk->registered |= (1<<hdr->sadb_msg_satype);
 	}
 
+	mutex_lock(&pfkey_mutex);
 	xfrm_probe_algs();
 
 	supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
+	mutex_unlock(&pfkey_mutex);
+
 	if (!supp_skb) {
 		if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
 			pfk->registered &= ~(1<<hdr->sadb_msg_satype);

index 2cd66f3e52386..0d12bdf59d4cc 100644
@@ -3164,7 +3164,7 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
 	return dst;
 
 nopol:
-	if (!(dst_orig->dev->flags & IFF_LOOPBACK) &&
+	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
 	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
 		err = -EPERM;
 		goto error;

index 9fdecd9090493..4928eaa0d4c02 100644
@@ -321,7 +321,7 @@ static int read_name_gen = 1;
 static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		struct nfs_fh *src_fh, nfs4_stateid *stateid)
 {
-	struct nfs_fattr fattr;
+	struct nfs_fattr *fattr = nfs_alloc_fattr();
 	struct file *filep, *res;
 	struct nfs_server *server;
 	struct inode *r_ino = NULL;

@@ -332,9 +332,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 
 	server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
 
-	nfs_fattr_init(&fattr);
+	if (!fattr)
+		return ERR_PTR(-ENOMEM);
 
-	status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+	status = nfs4_proc_getattr(server, src_fh, fattr, NULL, NULL);
 	if (status < 0) {
 		res = ERR_PTR(status);
 		goto out;

@@ -347,7 +348,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out;
 	snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
 
-	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
+	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr,
 			NULL);
 	if (IS_ERR(r_ino)) {
 		res = ERR_CAST(r_ino);

@@ -392,6 +393,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 out_free_name:
 	kfree(read_name);
 out:
+	nfs_free_fattr(fattr);
 	return res;
 out_stateowner:
 	nfs4_put_state_owner(sp);

index 4928eaa0d4c02..70cd0d764c447 100644
@@ -341,6 +341,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out;
 	}
 
+	if (!S_ISREG(fattr->mode)) {
+		res = ERR_PTR(-EBADF);
+		goto out;
+	}
+
 	res = ERR_PTR(-ENOMEM);
 	len = strlen(SSC_READ_NAME_BODY) + 16;
 	read_name = kzalloc(len, GFP_NOFS);

@@ -359,6 +364,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 				     r_ino->i_fop);
 	if (IS_ERR(filep)) {
 		res = ERR_CAST(filep);
+		iput(r_ino);
 		goto out_free_name;
 	}
 	filep->f_mode |= FMODE_READ;

index c5af31312e0cf..78c6648af7827 100644
@@ -1867,7 +1867,7 @@ call_encode(struct rpc_task *task)
 			break;
 		case -EKEYEXPIRED:
 			if (!task->tk_cred_retry) {
-				rpc_exit(task, task->tk_status);
+				rpc_call_rpcerror(task, task->tk_status);
 			} else {
 				task->tk_action = call_refresh;
 				task->tk_cred_retry--;

index 594368f6134f1..cb7b0aead7096 100644
@@ -1691,7 +1691,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 			VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
 			entry = pmd_to_swp_entry(orig_pmd);
-			page = pfn_to_page(swp_offset(entry));
+			page = migration_entry_to_page(entry);
 			flush_needed = 0;
 		} else
 			WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

@@ -2110,7 +2110,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		swp_entry_t entry;
 
 		entry = pmd_to_swp_entry(old_pmd);
-		page = pfn_to_page(swp_offset(entry));
+		page = migration_entry_to_page(entry);
 		write = is_write_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);

index ba98371e9d164..ef18f0d71b11b 100644
@@ -503,10 +503,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
-	bool migration = false;
+	bool migration = false, young = false, dirty = false;
 
 	if (pte_present(*pte)) {
 		page = vm_normal_page(vma, addr, *pte);
+		young = pte_young(*pte);
+		dirty = pte_dirty(*pte);
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 

@@ -540,8 +542,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte),
-		      locked, migration);
+	smaps_account(mss, page, false, young, dirty, locked, migration);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

index 11c45c8c6c164..036d92c0ad794 100644
@@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 		}
 
 		if (frametype == ROSE_CALL_REQUEST) {
-			if (!rose_loopback_neigh->dev) {
+			if (!rose_loopback_neigh->dev &&
+			    !rose_loopback_neigh->loopback) {
 				kfree_skb(skb);
 				continue;
 			}

index a0665d8ea85bc..e92535ebb5287 100644
@@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev)
 	pn53x_unregister_nfc(pn532->priv);
 	serdev_device_close(serdev);
 	pn53x_common_clean(pn532->priv);
+	del_timer_sync(&pn532->cmd_timeout);
 	kfree_skb(pn532->recv_skb);
 	kfree(pn532);
 }

index 5733526fa245c..4bb62950d92de 100644
@@ -371,6 +371,13 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
+	if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
+	    !is_power_of_2(vsi->tx_rings[qid]->count)) {
+		netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {

@@ -393,6 +400,7 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
 
+failure:
 	if (pool_failure) {
 		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
 			   pool_present ? "en" : "dis", pool_failure);

index 4bb62950d92de..59963b901be0f 100644
@@ -371,6 +371,12 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
+	if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
+		netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
 	if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
 	    !is_power_of_2(vsi->tx_rings[qid]->count)) {
 		netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");

index 304435e561170..b991f03c7e991 100644
@@ -706,6 +706,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	params->num_tc                = 1;
 	params->tunneled_offload_en = false;
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		params->vlan_strip_disable = true;
 
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 

index a78d66051a17d..25a8d029f2075 100644
@@ -414,7 +414,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	}
 
 	/* Align the address down and the size up to a page boundary */
-	addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK;
+	addr = qcom_smem_virt_to_phys(virt);
 	phys = addr & PAGE_MASK;
 	size = PAGE_ALIGN(size + addr - phys);
 	iova = phys;	/* We just want a direct mapping */

index 6137000b11c5c..73aac97fb5c96 100644
@@ -74,11 +74,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 static void moxart_mac_free_memory(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-	int i;
-
-	for (i = 0; i < RX_DESC_NUM; i++)
-		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
-				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
 		dma_free_coherent(&priv->pdev->dev,

@@ -193,6 +188,7 @@ static int moxart_mac_open(struct net_device *ndev)
 static int moxart_mac_stop(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+	int i;
 
 	napi_disable(&priv->napi);
 

@@ -204,6 +200,11 @@ static int moxart_mac_stop(struct net_device *ndev)
 	/* disable all functions */
 	writel(0, priv->base + REG_MAC_CTRL);
 
+	/* unmap areas mapped in moxart_mac_setup_desc_ring() */
+	for (i = 0; i < RX_DESC_NUM; i++)
+		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+
 	return 0;
 }
 

index 325b20729d8ba..b0f8d551b61db 100644
@@ -1988,30 +1988,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
  */
 void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
 {
-	/* check that the bond is not initialized yet */
-	if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
-				bond->dev->dev_addr)) {
-
-		BOND_AD_INFO(bond).aggregator_identifier = 0;
-
-		BOND_AD_INFO(bond).system.sys_priority =
-			bond->params.ad_actor_sys_prio;
-		if (is_zero_ether_addr(bond->params.ad_actor_system))
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->dev->dev_addr);
-		else
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->params.ad_actor_system);
+	BOND_AD_INFO(bond).aggregator_identifier = 0;
+	BOND_AD_INFO(bond).system.sys_priority =
+		bond->params.ad_actor_sys_prio;
+	if (is_zero_ether_addr(bond->params.ad_actor_system))
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->dev->dev_addr);
+	else
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->params.ad_actor_system);
 
-		/* initialize how many times this module is called in one
-		 * second (should be about every 100ms)
-		 */
-		ad_ticks_per_sec = tick_resolution;
+	/* initialize how many times this module is called in one
+	 * second (should be about every 100ms)
+	 */
+	ad_ticks_per_sec = tick_resolution;
 
-		bond_3ad_initiate_agg_selection(bond,
-						AD_AGGREGATOR_SELECTION_TIMER *
-						ad_ticks_per_sec);
-	}
+	bond_3ad_initiate_agg_selection(bond,
+					AD_AGGREGATOR_SELECTION_TIMER *
+					ad_ticks_per_sec);
 }
 
 /**

index 1cedb634f4f7b..f01078b2581ce 100644
@@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = {
 	.notifier_call	= ipvtap_device_event,
 };
 
-static int ipvtap_init(void)
+static int __init ipvtap_init(void)
 {
 	int err;
 

@@ -228,7 +228,7 @@ static int ipvtap_init(void)
 }
 module_init(ipvtap_init);
 
-static void ipvtap_exit(void)
+static void __exit ipvtap_exit(void)
 {
 	rtnl_link_unregister(&ipvtap_link_ops);
 	unregister_netdevice_notifier(&ipvtap_notifier_block);

index 3a956145a25cb..a18fb73a2b772 100644
@@ -94,10 +94,6 @@ struct ebt_table {
 	struct ebt_replace_kernel *table;
 	unsigned int valid_hooks;
 	rwlock_t lock;
-	/* e.g. could be the table explicitly only allows certain
-	 * matches, targets, ... 0 == let it in */
-	int (*check)(const struct ebt_table_info *info,
-	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
 	struct module *me;

index 32bc2821027f3..57f91efce0f73 100644
@@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)&initial_chain,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~(1 << NF_BR_BROUTING))
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table broute_table = {
 	.name		= "broute",
 	.table		= &initial_table,
 	.valid_hooks	= 1 << NF_BR_BROUTING,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 

index bcf982e12f16b..7f2e620f4978f 100644
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~FILTER_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_filter = {
 	.name		= "filter",
 	.table		= &initial_table,
 	.valid_hooks	= FILTER_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 

index 0d092773f8161..1743a105485c4 100644
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~NAT_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_nat = {
 	.name		= "nat",
 	.table		= &initial_table,
 	.valid_hooks	= NAT_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 

index d481ff24a1501..310740cc684ad 100644
@@ -999,8 +999,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 		goto free_iterate;
 	}
 
-	/* the table doesn't like it */
-	if (t->check && (ret = t->check(newinfo, repl->valid_hooks)))
+	if (repl->valid_hooks != t->valid_hooks)
 		goto free_unlock;
 
 	if (repl->num_counters && repl->num_counters != t->private->nentries) {

@@ -1186,11 +1185,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	if (ret != 0)
 		goto free_chainstack;
 
-	if (table->check && table->check(newinfo, table->valid_hooks)) {
-		ret = -EINVAL;
-		goto free_chainstack;
-	}
-
 	table->private = newinfo;
 	rwlock_init(&table->lock);
 	mutex_lock(&ebt_mutex);

index 23b80aa171dd0..819f9df9425c6 100644
@@ -599,7 +599,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req.min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req.min_vnics) * n;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			hw_resc->max_irqs -= vf_msix * n;
+			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
 	}

index 01878c16418c2..bdb07362c0ef0 100644
@@ -733,6 +733,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 {
 	enum nft_payload_bases base;
 	unsigned int offset, len;
+	int err;
 
 	if (tb[NFTA_PAYLOAD_BASE] == NULL ||
 	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||

@@ -758,8 +759,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	if (tb[NFTA_PAYLOAD_DREG] == NULL)
 		return ERR_PTR(-EINVAL);
 
-	offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
-	len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len);
+	if (err < 0)
+		return ERR_PTR(err);
 
 	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
 	    base != NFT_PAYLOAD_LL_HEADER)

index bdb07362c0ef0..551e0d6cf63d4 100644
@@ -660,17 +660,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 				const struct nlattr * const tb[])
 {
 	struct nft_payload_set *priv = nft_expr_priv(expr);
+	u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
+	int err;
 
 	priv->base        = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	priv->offset      = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len         = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
 	if (tb[NFTA_PAYLOAD_CSUM_TYPE])
-		priv->csum_type =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
-	if (tb[NFTA_PAYLOAD_CSUM_OFFSET])
-		priv->csum_offset =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET]));
+		csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
+	if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) {
+		err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX,
+					  &csum_offset);
+		if (err < 0)
+			return err;
+
+		priv->csum_offset = csum_offset;
+	}
 	if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) {
 		u32 flags;
 

@@ -681,7 +687,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 		priv->csum_flags = flags;
 	}
 
-	switch (priv->csum_type) {
+	switch (csum_type) {
 	case NFT_PAYLOAD_CSUM_NONE:
 	case NFT_PAYLOAD_CSUM_INET:
 		break;

@@ -695,6 +701,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	default:
 		return -EOPNOTSUPP;
 	}
+	priv->csum_type = csum_type;
 
 	return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
 				       priv->len);

index 30bd4b867912c..456988b5c076e 100644
@@ -1999,9 +1999,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 			      u8 policy, u32 flags)
 {
 	const struct nlattr * const *nla = ctx->nla;
+	struct nft_stats __percpu *stats = NULL;
 	struct nft_table *table = ctx->table;
 	struct nft_base_chain *basechain;
-	struct nft_stats __percpu *stats;
 	struct net *net = ctx->net;
 	char name[NFT_NAME_MAXLEN];
 	struct nft_trans *trans;

@@ -2037,7 +2037,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 				return PTR_ERR(stats);
 			}
 			rcu_assign_pointer(basechain->stats, stats);
-			static_branch_inc(&nft_counters_enabled);
 		}
 
 		err = nft_basechain_init(basechain, family, &hook, flags);

@@ -2120,6 +2119,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		goto err_unregister_hook;
 	}
 
+	if (stats)
+		static_branch_inc(&nft_counters_enabled);
+
 	table->use++;
 
 	return 0;

index d82677e83400b..720dc9fba6d4f 100644
@@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx,
 			    const struct nft_expr *expr,
 			    const struct nft_data **data)
 {
-	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
-						    (1 << NF_INET_PRE_ROUTING) |
-						    (1 << NF_INET_FORWARD));
+	unsigned int hooks;
+
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = (1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_FORWARD);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
 }
 
 static struct nft_expr_type nft_osf_type;

index 3b27926d5382c..2ee50996da8cc 100644
@@ -133,6 +133,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = {
 
 static struct nft_expr_type nft_tunnel_type __read_mostly = {
 	.name		= "tunnel",
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_get_ops,
 	.policy		= nft_tunnel_policy,
 	.maxattr	= NFTA_TUNNEL_MAX,

index b529c0e865466..47b6d05f1ae69 100644
@@ -303,10 +303,8 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (desc.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
+	if (desc.type != NFT_DATA_VALUE)
 		goto err1;
-	}
 
 	if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ))
 		return &nft_cmp_fast_ops;

index a61b5bf5aa0fb..6dd27c8cd4253 100644
@@ -67,6 +67,36 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
+					 const struct nft_chain *chain,
+					 const struct nft_regs *regs)
+{
+	enum nft_trace_types type;
+
+	switch (regs->verdict.code) {
+	case NFT_CONTINUE:
+	case NFT_RETURN:
+		type = NFT_TRACETYPE_RETURN;
+		break;
+	default:
+		type = NFT_TRACETYPE_RULE;
+		break;
+	}
+
+	__nft_trace_packet(info, chain, type);
+}
+
+static inline void nft_trace_verdict(struct nft_traceinfo *info,
+				     const struct nft_chain *chain,
+				     const struct nft_rule *rule,
+				     const struct nft_regs *regs)
+{
+	if (static_branch_unlikely(&nft_trace_enabled)) {
+		info->rule = rule;
+		__nft_trace_verdict(info, chain, regs);
+	}
+}
+
 static bool nft_payload_fast_eval(const struct nft_expr *expr,
 				  struct nft_regs *regs,
 				  const struct nft_pktinfo *pkt)

@@ -207,13 +237,13 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 		break;
 	}
 
+	nft_trace_verdict(&info, chain, rule, &regs);
+
 	switch (regs.verdict.code & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
 	case NF_STOLEN:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RULE);
 		return regs.verdict.code;
 	}
 

@@ -226,15 +256,10 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 		stackptr++;
 		fallthrough;
 	case NFT_GOTO:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RULE);
-
 		chain = regs.verdict.chain;
 		goto do_chain;
 	case NFT_CONTINUE:
 	case NFT_RETURN:
-		nft_trace_packet(&info, chain, rule,
-				 NFT_TRACETYPE_RETURN);
 		break;
 	default:
 		WARN_ON(1);

index fd10a7862fdc6..ce75121782bf7 100644
@@ -38,6 +38,14 @@ struct nft_cmp_fast_expr {
 	bool			inv;
 };
 
+struct nft_cmp16_fast_expr {
+	struct nft_data		data;
+	struct nft_data		mask;
+	u8			sreg;
+	u8			len;
+	bool			inv;
+};
+
 struct nft_immediate_expr {
 	struct nft_data		data;
 	u8			dreg;

@@ -55,6 +63,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
 }
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
+extern const struct nft_expr_ops nft_cmp16_fast_ops;
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;

index 6dd27c8cd4253..9dc18429ed875 100644
@@ -67,6 +67,20 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 	regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_cmp16_fast_eval(const struct nft_expr *expr,
+				struct nft_regs *regs)
+{
+	const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
+	const u64 *reg_data = (const u64 *)&regs->data[priv->sreg];
+	const u64 *mask = (const u64 *)&priv->mask;
+	const u64 *data = (const u64 *)&priv->data;
+
+	if (((reg_data[0] & mask[0]) == data[0] &&
+	    ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv)
+		return;
+	regs->verdict.code = NFT_BREAK;
+}
+
 static noinline void __nft_trace_verdict(struct nft_traceinfo *info,
 					 const struct nft_chain *chain,
 					 const struct nft_regs *regs)

@@ -215,6 +229,8 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, &regs);
+			else if (expr->ops == &nft_cmp16_fast_ops)
+				nft_cmp16_fast_eval(expr, &regs);
 			else if (expr->ops == &nft_bitwise_fast_ops)
 				nft_bitwise_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||

121 lines not on this page · raw message

index 47b0dba95054f..d0c648b64cd40 100644
@@ -109,22 +109,23 @@ static int nft_bitwise_init_bool(struct nft_bitwise *priv,
 		return err;
 	if (mask.type != NFT_DATA_VALUE || mask.len != priv->len) {
 		err = -EINVAL;
-		goto err1;
+		goto err_mask_release;
 	}
 
 	err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &xor,
 			    tb[NFTA_BITWISE_XOR]);
 	if (err < 0)
-		goto err1;
+		goto err_mask_release;
 	if (xor.type != NFT_DATA_VALUE || xor.len != priv->len) {
 		err = -EINVAL;
-		goto err2;
+		goto err_xor_release;
 	}
 
 	return 0;
-err2:
+
+err_xor_release:
 	nft_data_release(&priv->xor, xor.type);
-err1:
+err_mask_release:
 	nft_data_release(&priv->mask, mask.type);
 	return err;
 }

index b9948e7861f22..6c062b2509b9b 100644
@@ -178,11 +178,11 @@ struct nft_ctx {
 
 struct nft_data_desc {
 	enum nft_data_types		type;
+	unsigned int			size;
 	unsigned int			len;
 };
 
-int nft_data_init(const struct nft_ctx *ctx,
-		  struct nft_data *data, unsigned int size,
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
 		  struct nft_data_desc *desc, const struct nlattr *nla);
 void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
 void nft_data_release(const struct nft_data *data, enum nft_data_types type);

141 lines not on this page · raw message

112 lines not on this page · raw message

94 lines not on this page · raw message

index d0f67d325bdfd..fcdbc5ed3f367 100644
@@ -29,20 +29,36 @@ static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = {
 	[NFTA_IMMEDIATE_DATA]	= { .type = NLA_NESTED },
 };
 
+static enum nft_data_types nft_reg_to_type(const struct nlattr *nla)
+{
+	enum nft_data_types type;
+	u8 reg;
+
+	reg = ntohl(nla_get_be32(nla));
+	if (reg == NFT_REG_VERDICT)
+		type = NFT_DATA_VERDICT;
+	else
+		type = NFT_DATA_VALUE;
+
+	return type;
+}
+
 static int nft_immediate_init(const struct nft_ctx *ctx,
 			      const struct nft_expr *expr,
 			      const struct nlattr * const tb[])
 {
 	struct nft_immediate_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc;
+	struct nft_data_desc desc = {
+		.size	= sizeof(priv->data),
+	};
 	int err;
 
 	if (tb[NFTA_IMMEDIATE_DREG] == NULL ||
 	    tb[NFTA_IMMEDIATE_DATA] == NULL)
 		return -EINVAL;
 
-	err = nft_data_init(ctx, &priv->data, sizeof(priv->data), &desc,
-			    tb[NFTA_IMMEDIATE_DATA]);
+	desc.type = nft_reg_to_type(tb[NFTA_IMMEDIATE_DREG]);
+	err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
 	if (err < 0)
 		return err;
 

index e4a1c44d7f513..e6bbe32c323df 100644
@@ -51,7 +51,14 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 			const struct nlattr * const tb[])
 {
 	struct nft_range_expr *priv = nft_expr_priv(expr);
-	struct nft_data_desc desc_from, desc_to;
+	struct nft_data_desc desc_from = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data_from),
+	};
+	struct nft_data_desc desc_to = {
+		.type	= NFT_DATA_VALUE,
+		.size	= sizeof(priv->data_to),
+	};
 	int err;
 	u32 op;
 

@@ -61,26 +68,16 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 	    !tb[NFTA_RANGE_TO_DATA])
 		return -EINVAL;
 
-	err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
-			    &desc_from, tb[NFTA_RANGE_FROM_DATA]);
+	err = nft_data_init(NULL, &priv->data_from, &desc_from,
+			    tb[NFTA_RANGE_FROM_DATA]);
 	if (err < 0)
 		return err;
 
-	if (desc_from.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
-		goto err1;
-	}
-
-	err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to),
-			    &desc_to, tb[NFTA_RANGE_TO_DATA]);
+	err = nft_data_init(NULL, &priv->data_to, &desc_to,
+			    tb[NFTA_RANGE_TO_DATA]);
 	if (err < 0)
 		goto err1;
 
-	if (desc_to.type != NFT_DATA_VALUE) {
-		err = -EINVAL;
-		goto err2;
-	}
-
 	if (desc_from.len != desc_to.len) {
 		err = -EINVAL;
 		goto err2;

index 6c062b2509b9b..e66fee99ed3ea 100644
@@ -176,10 +176,15 @@ struct nft_ctx {
 	bool				report;
 };
 
+enum nft_data_desc_flags {
+	NFT_DATA_DESC_SETELEM	= (1 << 0),
+};
+
 struct nft_data_desc {
 	enum nft_data_types		type;
 	unsigned int			size;
 	unsigned int			len;
+	unsigned int			flags;
 };
 
 int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,

index df79ea6004a59..b36728cfc5d81 100644
@@ -4865,6 +4865,7 @@ static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
 	desc->type = dtype;
 	desc->size = NFT_DATA_VALUE_MAXLEN;
 	desc->len = set->dlen;
+	desc->flags = NFT_DATA_DESC_SETELEM;
 
 	return nft_data_init(ctx, data, desc, attr);
 }

@@ -8677,6 +8678,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 			return PTR_ERR(chain);
 		if (nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
+		if (desc->flags & NFT_DATA_DESC_SETELEM &&
+		    chain->flags & NFT_CHAIN_BINDING)
+			return -EINVAL;
 
 		chain->use++;
 		data->verdict.chain = chain;

index b36728cfc5d81..1b039476e4d6a 100644
@@ -8678,6 +8678,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 			return PTR_ERR(chain);
 		if (nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
+		if (nft_chain_is_bound(chain))
+			return -EINVAL;
 		if (desc->flags & NFT_DATA_DESC_SETELEM &&
 		    chain->flags & NFT_CHAIN_BINDING)
 			return -EINVAL;

index d35e88b5ffcbe..33a3fb04ac4df 100644
@@ -454,11 +454,12 @@ static void tcp_sndbuf_expand(struct sock *sk)
  */
 
 /* Slow part of check#2. */
-static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
+			     unsigned int skbtruesize)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
-	int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
+	int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
 	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {

@@ -471,7 +472,27 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 	return 0;
 }
 
-static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
+/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing
+ * can play nice with us, as sk_buff and skb->head might be either
+ * freed or shared with up to MAX_SKB_FRAGS segments.
+ * Only give a boost to drivers using page frag(s) to hold the frame(s),
+ * and if no payload was pulled in skb->head before reaching us.
+ */
+static u32 truesize_adjust(bool adjust, const struct sk_buff *skb)
+{
+	u32 truesize = skb->truesize;
+
+	if (adjust && !skb_headlen(skb)) {
+		truesize -= SKB_TRUESIZE(skb_end_offset(skb));
+		/* paranoid check, some drivers might be buggy */
+		if (unlikely((int)truesize < (int)skb->len))
+			truesize = skb->truesize;
+	}
+	return truesize;
+}
+
+static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
+			    bool adjust)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int room;

@@ -480,15 +501,16 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 
 	/* Check #1 */
 	if (room > 0 && !tcp_under_memory_pressure(sk)) {
+		unsigned int truesize = truesize_adjust(adjust, skb);
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
 		 * will fit to rcvbuf in future.
 		 */
-		if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
+		if (tcp_win_from_space(sk, truesize) <= skb->len)
 			incr = 2 * tp->advmss;
 		else
-			incr = __tcp_grow_window(sk, skb);
+			incr = __tcp_grow_window(sk, skb, truesize);
 
 		if (incr) {
 			incr = max_t(int, incr, 2 * skb->len);

@@ -782,7 +804,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 	tcp_ecn_check_ce(sk, skb);
 
 	if (skb->len >= 128)
-		tcp_grow_window(sk, skb);
+		tcp_grow_window(sk, skb, true);
 }
 
 /* Called to compute a smoothed rtt estimate. The data fed to this

@@ -4761,7 +4783,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		 * and trigger fast retransmit.
 		 */
 		if (tcp_is_sack(tp))
-			tcp_grow_window(sk, skb);
+			tcp_grow_window(sk, skb, true);
 		kfree_skb_partial(skb, fragstolen);
 		skb = NULL;
 		goto add_sack;

@@ -4849,7 +4871,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		 * and trigger fast retransmit.
 		 */
 		if (tcp_is_sack(tp))
-			tcp_grow_window(sk, skb);
+			tcp_grow_window(sk, skb, false);
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}

index 333131f47ac13..d31c2b9107e54 100644
@@ -2678,18 +2678,18 @@ static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_wmem ? */
 	if (proto->sysctl_wmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
 
-	return *proto->sysctl_wmem;
+	return READ_ONCE(*proto->sysctl_wmem);
 }
 
 static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_rmem ? */
 	if (proto->sysctl_rmem_offset)
-		return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+		return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
 
-	return *proto->sysctl_rmem;
+	return READ_ONCE(*proto->sysctl_rmem);
 }
 
 /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)

index dc92a67baea39..7d542eb461729 100644
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 	sk->sk_family      = PF_DECnet;
 	sk->sk_protocol    = 0;
 	sk->sk_allocation  = gfp;
-	sk->sk_sndbuf	   = sysctl_decnet_wmem[1];
-	sk->sk_rcvbuf	   = sysctl_decnet_rmem[1];
+	sk->sk_sndbuf	   = READ_ONCE(sysctl_decnet_wmem[1]);
+	sk->sk_rcvbuf	   = READ_ONCE(sysctl_decnet_rmem[1]);
 
 	/* Initialization of DECnet Session Control Port		*/
 	scp = DN_SK(sk);

index 78460eb39b3af..bfeb05f62b94f 100644
@@ -451,8 +451,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
-	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;

@@ -1711,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
-		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 	val = min(val, cap);
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 

index 33a3fb04ac4df..41b44b311e8a0 100644
@@ -425,7 +425,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
 
 	if (sk->sk_sndbuf < sndmem)
 		WRITE_ONCE(sk->sk_sndbuf,
-			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+			   min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)

@@ -460,7 +460,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
 	struct tcp_sock *tp = tcp_sk(sk);
 	/* Optimize this! */
 	int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
-	int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+	int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
 
 	while (tp->rcv_ssthresh <= window) {
 		if (truesize <= skb->len)

@@ -565,16 +565,17 @@ static void tcp_clamp_window(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
+	int rmem2;
 
 	icsk->icsk_ack.quick = 0;
+	rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
 
-	if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+	if (sk->sk_rcvbuf < rmem2 &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		WRITE_ONCE(sk->sk_rcvbuf,
-			   min(atomic_read(&sk->sk_rmem_alloc),
-			       net->ipv4.sysctl_tcp_rmem[2]));
+			   min(atomic_read(&sk->sk_rmem_alloc), rmem2));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);

@@ -736,7 +737,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 		do_div(rcvwin, tp->advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		if (rcvbuf > sk->sk_rcvbuf) {
 			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 

index 4c9274cb92d55..c90c9541996bf 100644
@@ -238,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,

index d0e91aa7b30e5..e61c85873ea2f 100644
@@ -1439,7 +1439,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 		do_div(rcvwin, advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;

@@ -1872,8 +1872,8 @@ static int mptcp_init_sock(struct sock *sk)
 		return ret;
 
 	sk_sockets_allocated_inc(sk);
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
 
 	return 0;
 }

index 38256aabf4f1d..8f3c9fbb99165 100644
@@ -504,7 +504,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
 	sk->sk_shutdown = 0;
 	sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
-	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+	sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
 	sk->sk_destruct = tipc_sock_destruct;

index 815edf7bc4390..6a90c1eb6f67e 100644
@@ -4713,14 +4713,14 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		/* Only some socketops are supported */
 		switch (optname) {
 		case SO_RCVBUF:
-			val = min_t(u32, val, sysctl_rmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 			WRITE_ONCE(sk->sk_rcvbuf,
 				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
-			val = min_t(u32, val, sysctl_wmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 			WRITE_ONCE(sk->sk_sndbuf,

index 6d9af4ef93d7a..25d25dcd0c3db 100644
@@ -887,7 +887,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_wmem_max);
+		val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 set_sndbuf:
 		/* Ensure val * 2 fits into an int, to prevent max_t()
 		 * from treating it as a negative value.

@@ -919,7 +919,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
+		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
 		break;
 
 	case SO_RCVBUFFORCE:

@@ -2974,8 +2974,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
-	sk->sk_rcvbuf		=	sysctl_rmem_default;
-	sk->sk_sndbuf		=	sysctl_wmem_default;
+	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
+	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
 	sk_set_socket(sk, sock);
 

index f77b0af3cb657..0dbf950de832f 100644
@@ -1721,7 +1721,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sk->sk_sndbuf = sysctl_wmem_default;
+	sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
 	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);

index c90c9541996bf..48fce999dc612 100644
@@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		space = max_t(u32, space, sysctl_rmem_max);
+		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);

index 16b48064f715e..daab857c52a80 100644
@@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
 	lock_sock(sk);
 	if (mode) {
 		val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
-			      sysctl_wmem_max);
+			      READ_ONCE(sysctl_wmem_max));
 		sk->sk_sndbuf = val * 2;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	} else {
 		val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
-			      sysctl_rmem_max);
+			      READ_ONCE(sysctl_rmem_max));
 		sk->sk_rcvbuf = val * 2;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}

index 637bc576fbd26..701a1afc91ff1 100644
@@ -6371,7 +6371,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		net_rps_action_and_irq_enable(sd);
 	}
 
-	napi->weight = dev_rx_weight;
+	napi->weight = READ_ONCE(dev_rx_weight);
 	while (again) {
 		struct sk_buff *skb;
 

index 2e0a4378e778a..0dfe9f255ab3a 100644
@@ -235,14 +235,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 static int proc_do_dev_weight(struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret;
+	static DEFINE_MUTEX(dev_weight_mutex);
+	int ret, weight;
 
+	mutex_lock(&dev_weight_mutex);
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (ret != 0)
-		return ret;
-
-	dev_rx_weight = weight_p * dev_weight_rx_bias;
-	dev_tx_weight = weight_p * dev_weight_tx_bias;
+	if (!ret && write) {
+		weight = READ_ONCE(weight_p);
+		WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+		WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+	}
+	mutex_unlock(&dev_weight_mutex);
 
 	return ret;
 }

index 5d5391adb667c..68f1e89430b3b 100644
@@ -403,7 +403,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 
 void __qdisc_run(struct Qdisc *q)
 {
-	int quota = dev_tx_weight;
+	int quota = READ_ONCE(dev_tx_weight);
 	int packets;
 
 	while (qdisc_restart(q, &packets)) {

index 701a1afc91ff1..215c43aecc67e 100644
@@ -4516,7 +4516,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	struct softnet_data *sd;
 	unsigned int old_flow, new_flow;
 
-	if (qlen < (netdev_max_backlog >> 1))
+	if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
 		return false;
 
 	sd = this_cpu_ptr(&softnet_data);

@@ -4564,7 +4564,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	if (!netif_running(skb->dev))
 		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
-	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
+	if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);

index 6eb2e5ec2c506..2f66f3f295630 100644
@@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 
 	cell = this_cpu_ptr(gcells->cells);
 
-	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
 drop:
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);

index 1f08ebf7d80c5..24ca49ecebea3 100644
@@ -170,7 +170,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
 {
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
-	if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog)
+	if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	__skb_queue_tail(&ctx->out_queue, skb);

index 61e6220ddd5ae..77e82033ad700 100644
@@ -782,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
-	if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
+	if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));

index 215c43aecc67e..1ea75768c5b23 100644
@@ -4795,7 +4795,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_rx(skb);
 

@@ -5156,7 +5156,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 	int ret = NET_RX_DROP;
 	__be16 type;
 
-	net_timestamp_check(!netdev_tstamp_prequeue, skb);
+	net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_receive_skb(skb);
 

@@ -5558,7 +5558,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;

@@ -5588,7 +5588,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
-		net_timestamp_check(netdev_tstamp_prequeue, skb);
+		net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 		skb_list_del_init(skb);
 		if (!skb_defer_rx_timestamp(skb))
 			list_add_tail(&skb->list, &sublist);

index e01a93f46f833..ce945c17980b9 100644
@@ -26,10 +26,16 @@
  */
 int ___ratelimit(struct ratelimit_state *rs, const char *func)
 {
+	/* Paired with WRITE_ONCE() in .proc_handler().
+	 * Changing two values seperately could be inconsistent
+	 * and some message could be lost.  (See: net_ratelimit_state).
+	 */
+	int interval = READ_ONCE(rs->interval);
+	int burst = READ_ONCE(rs->burst);
 	unsigned long flags;
 	int ret;
 
-	if (!rs->interval)
+	if (!interval)
 		return 1;
 
 	/*

@@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 	if (!rs->begin)
 		rs->begin = jiffies;
 
-	if (time_is_before_jiffies(rs->begin + rs->interval)) {
+	if (time_is_before_jiffies(rs->begin + interval)) {
 		if (rs->missed) {
 			if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
 				printk_deferred(KERN_WARNING

@@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->begin   = jiffies;
 		rs->printed = 0;
 	}
-	if (rs->burst && rs->burst > rs->printed) {
+	if (burst && burst > rs->printed) {
 		rs->printed++;
 		ret = 1;
 	} else {

index 5f773624948ff..39c5a059d1c2b 100644
@@ -15,18 +15,6 @@
 
 DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
-static int omem_charge(struct sock *sk, unsigned int size)
-{
-	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
-		atomic_add(size, &sk->sk_omem_alloc);
-		return 0;
-	}
-
-	return -ENOMEM;
-}
-
 static struct bpf_local_storage_data *
 sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 {

@@ -316,7 +304,16 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int sk_storage_charge(struct bpf_local_storage_map *smap,
 			     void *owner, u32 size)
 {
-	return omem_charge(owner, size);
+	struct sock *sk = (struct sock *)owner;
+
+	/* same check as in sock_kmalloc() */
+	if (size <= sysctl_optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+		atomic_add(size, &sk->sk_omem_alloc);
+		return 0;
+	}
+
+	return -ENOMEM;
 }
 
 static void sk_storage_uncharge(struct bpf_local_storage_map *smap,

index 39c5a059d1c2b..d67d06d6b817c 100644
@@ -304,11 +304,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int sk_storage_charge(struct bpf_local_storage_map *smap,
 			     void *owner, u32 size)
 {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
 
 	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	if (size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		atomic_add(size, &sk->sk_omem_alloc);
 		return 0;
 	}

index 6a90c1eb6f67e..4c22e6d1da746 100644
@@ -1212,10 +1212,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
-	if (filter_size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+	if (filter_size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}

@@ -1547,7 +1548,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);

@@ -1614,7 +1615,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}

index 25d25dcd0c3db..f01e71c98d5be 100644
@@ -2219,7 +2219,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    sysctl_optmem_max)
+	    READ_ONCE(sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);

@@ -2237,8 +2237,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	if ((unsigned int)size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
+
+	if ((unsigned int)size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		void *mem;
 		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.

index 22507a6a3f71c..4cc39c62af55d 100644
@@ -773,7 +773,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);

@@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);

@@ -1231,7 +1231,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > sysctl_optmem_max) {
+		if (optlen > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}

index 43a894bf9a1be..6fa118bf40cdd 100644
@@ -208,7 +208,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);

@@ -242,7 +242,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);

index 48b6438f2a3d9..635cabcf8794f 100644
@@ -4691,7 +4691,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
 	bool ret;
 
-	if (likely(sysctl_tstamp_allow_data || tsonly))
+	if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
 		return true;
 
 	read_lock_bh(&sk->sk_callback_lock);

index 716b7c5f6fdd9..36e5e75e71720 100644
@@ -31,7 +31,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly;
 
 static inline bool net_busy_loop_on(void)
 {
-	return sysctl_net_busy_poll;
+	return READ_ONCE(sysctl_net_busy_poll);
 }
 
 static inline bool sk_can_busy_loop(const struct sock *sk)

index f01e71c98d5be..1bb6a003323b3 100644
@@ -3032,7 +3032,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
-	sk->sk_ll_usec		=	sysctl_net_busy_read;
+	sk->sk_ll_usec		=	READ_ONCE(sysctl_net_busy_read);
 #endif
 
 	sk->sk_max_pacing_rate = ~0UL;