This is the 4.9.155 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAlxbDFsACgkQONu9yGCS
 aT4TmQ/+PCgz7TKTu1/Sh7ScmbSjlYFfaQ25K9NzqWDuaTOXCsvrWY4IDdbk7fxZ
 WnM8WPpTUfKaRwUVL3T32uwv/uMM8TnXN2r4dB9TH+WF/UK1ovLHQGO5zGWS9erY
 dvckRjkRuPe27KYd/sPSA7PRBiWuw1EFqcBIdAuC8OJK1knm3W95C8XVeIkVfey2
 /NFIvZELYEOCMzXwPqXbeFG553VtHVGB2GRJqEqZzqZ+JGnUCyBpCgvuwbrQ706l
 /Smvz23mmElUGzdTXr4uRPmf2g8bA3a+08/gQM4YPpZYRUMbcCVE3+KaYf3jjJPR
 Inj+cKBhF8R6JwkJayzdBJ1KbG6e6DaL2yANqNvoeYCkyP+4GNmoWKebFYklrXr/
 jn/btnJtHwSBDVufdgW6uQ039UE66Wfvvi7QrkCgTjebEyf6jU3SnB8Z7HpZZMCg
 dwgO6rHKklm6cSJTBZsIDyBd4oj19bTTvOiUcaayQXfeyjlrbWXhH6UOEBze54uT
 Ho8yjCq9r2TiO6g9mJOfkkvep1hgNVgabnOyA/papUx3my9sGkUn1Rqg1Pbm9OEF
 PV4p853t4+Qe5iBq+yXgacrCg+21q9Xg3ct6QW/c/Quz4UirR9Ayw93C4ej4rJYZ
 79/mADmkpH+A1ufP2F80UoWo0IN9oizecfYHOZ+6useUEVgIRik=
 =QoXP
 -----END PGP SIGNATURE-----

Merge 4.9.155 into android-4.9

Changes in 4.9.155
	Fix "net: ipv4: do not handle duplicate fragments as overlapping"
	fs: add the fsnotify call to vfs_iter_write
	ipv6: Consider sk_bound_dev_if when binding a socket to an address
	l2tp: copy 4 more bytes to linear part if necessary
	net/mlx4_core: Add masking for a few queries on HCA caps
	netrom: switch to sock timer API
	net/rose: fix NULL ax25_cb kernel panic
	ucc_geth: Reset BQL queue when stopping device
	net/mlx5e: Allow MAC invalidation while spoofchk is ON
	l2tp: remove l2specific_len dependency in l2tp_core
	l2tp: fix reading optional fields of L2TPv3
	ipvlan, l3mdev: fix broken l3s mode wrt local routes
	CIFS: Do not count -ENODATA as failure for query directory
	fs/dcache: Fix incorrect nr_dentry_unused accounting in shrink_dcache_sb()
	ARM: cns3xxx: Fix writing to wrong PCI config registers after alignment
	arm64: kaslr: ensure randomized quantities are clean also when kaslr is off
	arm64: hyp-stub: Forbid kprobing of the hyp-stub
	arm64: hibernate: Clean the __hyp_text to PoC after resume
	gfs2: Revert "Fix loop in gfs2_rbm_find"
	platform/x86: asus-nb-wmi: Map 0x35 to KEY_SCREENLOCK
	platform/x86: asus-nb-wmi: Drop mapping of 0x33 and 0x34 scan codes
	mmc: sdhci-iproc: handle mmc_of_parse() errors during probe
	kernel/exit.c: release ptraced tasks before zap_pid_ns_processes
	mm, oom: fix use-after-free in oom_kill_process
	mm: hwpoison: use do_send_sig_info() instead of force_sig()
	mm: migrate: don't rely on __PageMovable() of newpage after unlocking it
	cifs: Always resolve hostname before reconnecting
	drivers: core: Remove glue dirs from sysfs earlier
	fs: don't scan the inode cache before SB_BORN is set
	fanotify: fix handling of events on child sub-directory
	Linux 4.9.155

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 154
+SUBLEVEL = 155
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/arm/mach-cns3xxx/pcie.c

@@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus,
 	} else /* remote PCI bus */
 		base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
 
-	return base + (where & 0xffc) + (devfn << 12);
+	return base + where + (devfn << 12);
 }
 
 static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,

arch/arm64/kernel/hibernate.c

@@ -294,8 +294,10 @@ int swsusp_arch_suspend(void)
 		dcache_clean_range(__idmap_text_start, __idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
-		if (el2_reset_needed())
+		if (el2_reset_needed()) {
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+		}
 
 		/*
 		 * Tell the hibernation core that we've just restored

arch/arm64/kernel/hyp-stub.S

@@ -28,6 +28,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)

arch/arm64/kernel/kaslr.c

@@ -88,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,

drivers/base/core.c

@@ -862,6 +862,8 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 		return;
 
 	mutex_lock(&gdp_mutex);
+	if (!kobject_has_children(glue_dir))
+		kobject_del(glue_dir);
 	kobject_put(glue_dir);
 	mutex_unlock(&gdp_mutex);
 }

drivers/mmc/host/sdhci-iproc.c

@@ -242,7 +242,10 @@ static int sdhci_iproc_probe(struct platform_device *pdev)
 
 	iproc_host->data = iproc_data;
 
-	mmc_of_parse(host->mmc);
+	ret = mmc_of_parse(host->mmc);
+	if (ret)
+		goto err;
+
 	sdhci_get_of_property(pdev);
 
 	host->mmc->caps |= iproc_host->data->mmc_caps;

drivers/net/ethernet/freescale/ucc_geth.c

@@ -1888,6 +1888,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth)
 	u16 i, j;
 	u8 __iomem *bd;
 
+	netdev_reset_queue(ugeth->ndev);
+
 	ug_info = ugeth->ug_info;
 	uf_info = &ug_info->uf_info;
 

drivers/net/ethernet/mellanox/mlx4/fw.c

@@ -2037,9 +2037,11 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u64 qword_field;
 	u32 dword_field;
-	int err;
+	u16 word_field;
 	u8 byte_field;
+	int err;
 	static const u8 a0_dmfs_query_hw_steering[] =  {
 		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
 		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
@@ -2067,19 +2069,32 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
-	MLX4_GET(param->qpc_base,      outbox, INIT_HCA_QPC_BASE_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_QPC_BASE_OFFSET);
-	MLX4_GET(param->log_num_qps,   outbox, INIT_HCA_LOG_QP_OFFSET);
+	param->qpc_base = qword_field & ~((u64)0x1f);
-	MLX4_GET(param->srqc_base,     outbox, INIT_HCA_SRQC_BASE_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_QP_OFFSET);
-	MLX4_GET(param->log_num_srqs,  outbox, INIT_HCA_LOG_SRQ_OFFSET);
+	param->log_num_qps = byte_field & 0x1f;
-	MLX4_GET(param->cqc_base,      outbox, INIT_HCA_CQC_BASE_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_SRQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_cqs,   outbox, INIT_HCA_LOG_CQ_OFFSET);
+	param->srqc_base = qword_field & ~((u64)0x1f);
-	MLX4_GET(param->altc_base,     outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_SRQ_OFFSET);
-	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	param->log_num_srqs = byte_field & 0x1f;
-	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_CQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
+	param->cqc_base = qword_field & ~((u64)0x1f);
-	MLX4_GET(param->num_sys_eqs,   outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_CQ_OFFSET);
-	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	param->log_num_cqs = byte_field & 0x1f;
-	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	param->altc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	param->auxc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_EQC_BASE_OFFSET);
+	param->eqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_EQ_OFFSET);
+	param->log_num_eqs = byte_field & 0x1f;
+	MLX4_GET(word_field, outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
+	param->num_sys_eqs = word_field & 0xfff;
+	MLX4_GET(qword_field, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	param->rdmarc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_RD_OFFSET);
+	param->log_rd_per_qp = byte_field & 0x7;
 
 	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
 	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
@@ -2098,22 +2113,21 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* steering attributes */
 	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
-			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
-		MLX4_GET(param->log_mc_table_sz, outbox,
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
-			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
-		MLX4_GET(byte_field, outbox,
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_A0_OFFSET);
-			 INIT_HCA_FS_A0_OFFSET);
 		param->dmfs_high_steer_mode =
 			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
-			 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
-		MLX4_GET(param->log_mc_hash_sz,  outbox,
+		MLX4_GET(byte_field,  outbox, INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
-			 INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+		param->log_mc_hash_sz = byte_field & 0x1f;
-		MLX4_GET(param->log_mc_table_sz, outbox,
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
-			 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
 	}
 
 	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
@@ -2137,15 +2151,18 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
-	MLX4_GET(param->mw_enabled, outbox, INIT_HCA_TPT_MW_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_TPT_MW_OFFSET);
-	MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	param->mw_enabled = byte_field >> 7;
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	param->log_mpt_sz = byte_field & 0x3f;
 	MLX4_GET(param->mtt_base,   outbox, INIT_HCA_MTT_BASE_OFFSET);
 	MLX4_GET(param->cmpt_base,  outbox, INIT_HCA_CMPT_BASE_OFFSET);
 
 	/* UAR attributes */
 
 	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
-	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	param->log_uar_sz = byte_field & 0xf;
 
 	/* phv_check enable */
 	MLX4_GET(byte_field, outbox, INIT_HCA_CACHELINE_SZ_OFFSET);

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1216,14 +1216,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 	int err = 0;
 	u8 *smac_v;
 
-	if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) {
-		mlx5_core_warn(esw->dev,
-			       "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
-			       vport->vport);
-		return -EPERM;
-
-	}
-
 	esw_vport_cleanup_ingress_rules(esw, vport);
 
 	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
@@ -1709,13 +1701,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	mutex_lock(&esw->state_lock);
 	evport = &esw->vports[vport];
 
-	if (evport->info.spoofchk && !is_valid_ether_addr(mac)) {
+	if (evport->info.spoofchk && !is_valid_ether_addr(mac))
 		mlx5_core_warn(esw->dev,
-			       "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+			       "Set invalid MAC while spoofchk is on, vport(%d)\n",
 			       vport);
-		err = -EPERM;
-		goto unlock;
-	}
 
 	err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
 	if (err) {
@@ -1859,6 +1848,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 	pschk = evport->info.spoofchk;
 	evport->info.spoofchk = spoofchk;
+	if (pschk && !is_valid_ether_addr(evport->info.mac))
+		mlx5_core_warn(esw->dev,
+			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
+			       evport->vport);
 	if (evport->enabled && esw->mode == SRIOV_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)

drivers/net/ipvlan/ipvlan_main.c

@@ -85,12 +85,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 			err = ipvlan_register_nf_hook();
 			if (!err) {
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
-				mdev->priv_flags |= IFF_L3MDEV_MASTER;
+				mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER;
 			} else
 				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
-			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
+			mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 			ipvlan_unregister_nf_hook();
 			mdev->l3mdev_ops = NULL;
 		}
@@ -158,7 +158,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
-		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
+		dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 		ipvlan_unregister_nf_hook();
 		dev->l3mdev_ops = NULL;
 	}

drivers/platform/x86/asus-nb-wmi.c

@@ -477,8 +477,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_KEY, 0x30, { KEY_VOLUMEUP } },
 	{ KE_KEY, 0x31, { KEY_VOLUMEDOWN } },
 	{ KE_KEY, 0x32, { KEY_MUTE } },
-	{ KE_KEY, 0x33, { KEY_DISPLAYTOGGLE } }, /* LCD on */
+	{ KE_KEY, 0x35, { KEY_SCREENLOCK } },
-	{ KE_KEY, 0x34, { KEY_DISPLAY_OFF } }, /* LCD off */
 	{ KE_KEY, 0x40, { KEY_PREVIOUSSONG } },
 	{ KE_KEY, 0x41, { KEY_NEXTSONG } },
 	{ KE_KEY, 0x43, { KEY_STOPCD } }, /* Stop/Eject */

fs/cifs/connect.c

@@ -48,6 +48,7 @@
 #include "cifs_unicode.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
+#include "dns_resolve.h"
 #include "ntlmssp.h"
 #include "nterr.h"
 #include "rfc1002pdu.h"
@@ -306,6 +307,53 @@ static void cifs_prune_tlinks(struct work_struct *work);
 static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data,
 					const char *devname);
 
+/*
+ * Resolve hostname and set ip addr in tcp ses. Useful for hostnames that may
+ * get their ip addresses changed at some point.
+ *
+ * This should be called with server->srv_mutex held.
+ */
+#ifdef CONFIG_CIFS_DFS_UPCALL
+static int reconn_set_ipaddr(struct TCP_Server_Info *server)
+{
+	int rc;
+	int len;
+	char *unc, *ipaddr = NULL;
+
+	if (!server->hostname)
+		return -EINVAL;
+
+	len = strlen(server->hostname) + 3;
+
+	unc = kmalloc(len, GFP_KERNEL);
+	if (!unc) {
+		cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__);
+		return -ENOMEM;
+	}
+	snprintf(unc, len, "\\\\%s", server->hostname);
+
+	rc = dns_resolve_server_name_to_ip(unc, &ipaddr);
+	kfree(unc);
+
+	if (rc < 0) {
+		cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n",
+			 __func__, server->hostname, rc);
+		return rc;
+	}
+
+	rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr,
+				  strlen(ipaddr));
+	kfree(ipaddr);
+
+	return !rc ? -1 : 0;
+}
+#else
+static inline int reconn_set_ipaddr(struct TCP_Server_Info *server)
+{
+	return 0;
+}
+#endif
+
 /*
  * cifs tcp session reconnection
  *
@@ -403,6 +451,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		rc = generic_ip_connect(server);
 		if (rc) {
 			cifs_dbg(FYI, "reconnect error %d\n", rc);
+			rc = reconn_set_ipaddr(server);
+			if (rc) {
+				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+					 __func__, rc);
+			}
 			mutex_unlock(&server->srv_mutex);
 			msleep(3000);
 		} else {

fs/cifs/smb2pdu.c

@@ -2686,8 +2686,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
 			srch_inf->endOfSearch = true;
 			rc = 0;
-		}
+		} else
-		cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
+			cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
 		goto qdir_exit;
 	}
 

fs/dcache.c

@@ -1164,15 +1164,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
  */
 void shrink_dcache_sb(struct super_block *sb)
 {
-	long freed;
-
 	do {
 		LIST_HEAD(dispose);
 
-		freed = list_lru_walk(&sb->s_dentry_lru,
+		list_lru_walk(&sb->s_dentry_lru,
 			dentry_lru_isolate_shrink, &dispose, 1024);
-
-		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
 		cond_resched();
 	} while (list_lru_count(&sb->s_dentry_lru) > 0);

fs/gfs2/rgrp.c

@@ -1705,9 +1705,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
 			goto next_iter;
 		}
 		if (ret == -E2BIG) {
-			n += rbm->bii - initial_bii;
 			rbm->bii = 0;
 			rbm->offset = 0;
+			n += (rbm->bii - initial_bii);
 			goto res_covered_end_of_rgrp;
 		}
 		return ret;

fs/notify/fsnotify.c

@@ -101,9 +101,9 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 	parent = dget_parent(dentry);
 	p_inode = parent->d_inode;
 
-	if (unlikely(!fsnotify_inode_watches_children(p_inode)))
+	if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
 		__fsnotify_update_child_dentry_flags(p_inode);
-	else if (p_inode->i_fsnotify_mask & mask) {
+	} else if (p_inode->i_fsnotify_mask & mask & ~FS_EVENT_ON_CHILD) {
 		struct name_snapshot name;
 
 		/* we are notifying a parent so come up with the new mask which
@@ -207,6 +207,10 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 	else
 		mnt = NULL;
 
+	/* An event "on child" is not intended for a mount mark */
+	if (mask & FS_EVENT_ON_CHILD)
+		mnt = NULL;
+
 	/*
 	 * Optimization: srcu_read_lock() has a memory barrier which can
 	 * be expensive.  It protects walking the *_fsnotify_marks lists.

fs/read_write.c

@@ -389,8 +389,10 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
 	iter->type |= WRITE;
 	ret = file->f_op->write_iter(&kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
-	if (ret > 0)
+	if (ret > 0) {
 		*ppos = kiocb.ki_pos;
+		fsnotify_modify(file);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(vfs_iter_write);

fs/super.c

@@ -119,13 +119,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	sb = container_of(shrink, struct super_block, s_shrink);
 
 	/*
-	 * Don't call trylock_super as it is a potential
+	 * We don't call trylock_super() here as it is a scalability bottleneck,
-	 * scalability bottleneck. The counts could get updated
+	 * so we're exposed to partial setup state. The shrinker rwsem does not
-	 * between super_cache_count and super_cache_scan anyway.
+	 * protect filesystem operations backing list_lru_shrink_count() or
-	 * Call to super_cache_count with shrinker_rwsem held
+	 * s_op->nr_cached_objects(). Counts can change between
-	 * ensures the safety of call to list_lru_shrink_count() and
+	 * super_cache_count and super_cache_scan, so we really don't need locks
-	 * s_op->nr_cached_objects().
+	 * here.
+	 *
+	 * However, if we are currently mounting the superblock, the underlying
+	 * filesystem might be in a state of partial construction and hence it
+	 * is dangerous to access it.  trylock_super() uses a MS_BORN check to
+	 * avoid this situation, so do the same here. The memory barrier is
+	 * matched with the one in mount_fs() as we don't hold locks here.
 	 */
+	if (!(sb->s_flags & MS_BORN))
+		return 0;
+	smp_rmb();
+
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb, sc);
 
@@ -1211,6 +1221,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, struct vfsm
 	sb = root->d_sb;
 	BUG_ON(!sb);
 	WARN_ON(!sb->s_bdi);
+
+	/*
+	 * Write barrier is for super_cache_count(). We place it before setting
+	 * MS_BORN as the data dependency between the two functions is the
+	 * superblock structure contents that we just set up, not the MS_BORN
+	 * flag.
+	 */
+	smp_wmb();
 	sb->s_flags |= MS_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);

include/linux/kobject.h

@@ -113,6 +113,23 @@ extern void kobject_put(struct kobject *kobj);
 extern const void *kobject_namespace(struct kobject *kobj);
 extern char *kobject_get_path(struct kobject *kobj, gfp_t flag);
 
+/**
+ * kobject_has_children - Returns whether a kobject has children.
+ * @kobj: the object to test
+ *
+ * This will return whether a kobject has other kobjects as children.
+ *
+ * It does NOT account for the presence of attribute files, only sub
+ * directories. It also assumes there is no concurrent addition or
+ * removal of such children, and thus relies on external locking.
+ */
+static inline bool kobject_has_children(struct kobject *kobj)
+{
+	WARN_ON_ONCE(atomic_read(&kobj->kref.refcount) == 0);
+
+	return kobj->sd && kobj->sd->dir.subdirs;
+}
+
 struct kobj_type {
 	void (*release)(struct kobject *kobj);
 	const struct sysfs_ops *sysfs_ops;