4.9.264-rc1 review

index f9e74461bdc0..123181612595 100644
@@ -396,9 +396,16 @@ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	u64 ns;
 	unsigned long flags;
 
+	mutex_lock(&adapter->ptp_clk_mutex);
+	/* Check the ptp clock */
+	if (!adapter->ptp_clk_on) {
+		mutex_unlock(&adapter->ptp_clk_mutex);
+		return -EINVAL;
+	}
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	ns = timecounter_read(&adapter->tc);
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+	mutex_unlock(&adapter->ptp_clk_mutex);
 
 	*ts = ns_to_timespec64(ns);
 

index 4a2beef74277..86fdda16bb73 100644
@@ -65,8 +65,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mfdcr(rn)						\
 	({unsigned int rval;					\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mfdcr %0," __stringify(rn)	\
-		              : "=r" (rval));			\
+		asm volatile("mfdcr %0, %1" : "=r" (rval)	\
+			      : "n" (rn));			\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		rval = mfdcrx(rn);				\
 	else							\

@@ -76,8 +76,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mtdcr(rn, v)						\
 do {								\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mtdcr " __stringify(rn) ",%0"	\
-			      : : "r" (v)); 			\
+		asm volatile("mtdcr %0, %1"			\
+			      : : "n" (rn), "r" (v));		\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		mtdcrx(rn, v);					\
 	else							\

index 9d16743c4917..2b7786cd548f 100644
@@ -2279,7 +2279,8 @@ static int eni_init_one(struct pci_dev *pci_dev,
 	return rc;
 
 err_eni_release:
-	eni_do_release(dev);
+	dev->phy = NULL;
+	iounmap(ENI_DEV(dev)->ioaddr);
 err_unregister:
 	atm_dev_deregister(dev);
 err_free_consistent:

index 445505d9ea07..dec6c68156ee 100644
@@ -2240,6 +2240,7 @@ static int lanai_dev_open(struct atm_dev *atmdev)
 	conf1_write(lanai);
 #endif
 	iounmap(lanai->base);
+	lanai->base = NULL;
     error_pci:
 	pci_disable_device(lanai->pci);
     error:

@@ -2252,6 +2253,8 @@ static int lanai_dev_open(struct atm_dev *atmdev)
 static void lanai_dev_close(struct atm_dev *atmdev)
 {
 	struct lanai_dev *lanai = (struct lanai_dev *) atmdev->dev_data;
+	if (lanai->base==NULL)
+		return;
 	printk(KERN_INFO DEV_LABEL "(itf %d): shutting down interface\n",
 	    lanai->number);
 	lanai_timed_poll_stop(lanai);

@@ -2561,7 +2564,7 @@ static int lanai_init_one(struct pci_dev *pci,
 	struct atm_dev *atmdev;
 	int result;
 
-	lanai = kmalloc(sizeof(*lanai), GFP_KERNEL);
+	lanai = kzalloc(sizeof(*lanai), GFP_KERNEL);
 	if (lanai == NULL) {
 		printk(KERN_ERR DEV_LABEL
 		       ": couldn't allocate dev_data structure!\n");

index 36d73bf32f4f..8e2aaf774693 100644
@@ -8677,8 +8677,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter,
 	ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask);
 	err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter,
 						    input->sw_idx, queue);
-	if (!err)
-		ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
+	if (err)
+		goto err_out_w_lock;
+
+	ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
 	spin_unlock(&adapter->fdir_perfect_lock);
 
 	if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))

index 7108c68f16d3..6ee7f8d2f2d1 100644
@@ -2062,6 +2062,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/*bdx_hw_reset(priv); */
 		if (bdx_read_mac(priv)) {
 			pr_err("load MAC address failed\n");
+			err = -EFAULT;
 			goto err_out_iomap;
 		}
 		SET_NETDEV_DEV(ndev, &pdev->dev);

index fe5b0ac8c631..5bf47279f9c1 100644
@@ -3948,8 +3948,6 @@ static void niu_xmac_interrupt(struct niu *np)
 		mp->rx_mcasts += RXMAC_MC_FRM_CNT_COUNT;
 	if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
 		mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
-	if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
-		mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
 	if (val & XRXMAC_STATUS_RXHIST1_CNT_EXP)
 		mp->rx_hist_cnt1 += RXMAC_HIST_CNT1_COUNT;
 	if (val & XRXMAC_STATUS_RXHIST2_CNT_EXP)

index 267126d32ec0..4a68837e92ea 100644
@@ -33,6 +33,7 @@
  */
 #define NFS3_fhandle_sz		(1+16)
 #define NFS3_fh_sz		(NFS3_fhandle_sz)	/* shorthand */
+#define NFS3_post_op_fh_sz	(1+NFS3_fh_sz)
 #define NFS3_sattr_sz		(15)
 #define NFS3_filename_sz	(1+(NFS3_MAXNAMLEN>>2))
 #define NFS3_path_sz		(1+(NFS3_MAXPATHLEN>>2))

@@ -70,7 +71,7 @@
 #define NFS3_readlinkres_sz	(1+NFS3_post_op_attr_sz+1)
 #define NFS3_readres_sz		(1+NFS3_post_op_attr_sz+3)
 #define NFS3_writeres_sz	(1+NFS3_wcc_data_sz+4)
-#define NFS3_createres_sz	(1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
+#define NFS3_createres_sz	(1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
 #define NFS3_renameres_sz	(1+(2 * NFS3_wcc_data_sz))
 #define NFS3_linkres_sz		(1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
 #define NFS3_readdirres_sz	(1+NFS3_post_op_attr_sz+2)

index 87bf05a81db5..fc7d28edee07 100644
@@ -169,13 +169,17 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 
 	priv->rx_skbuff = kzalloc(priv->rx_ring_size * sizeof(*priv->rx_skbuff),
 				  GFP_KERNEL);
-	if (!priv->rx_skbuff)
+	if (!priv->rx_skbuff) {
+		ret = -ENOMEM;
 		goto free_ucc_pram;
+	}
 
 	priv->tx_skbuff = kzalloc(priv->tx_ring_size * sizeof(*priv->tx_skbuff),
 				  GFP_KERNEL);
-	if (!priv->tx_skbuff)
+	if (!priv->tx_skbuff) {
+		ret = -ENOMEM;
 		goto free_rx_skbuff;
+	}
 
 	priv->skb_curtx = 0;
 	priv->skb_dirtytx = 0;

index 5120a96b3a89..b2f4e8df1591 100644
@@ -210,7 +210,7 @@ static void uPD98402_int(struct atm_dev *dev)
 static int uPD98402_start(struct atm_dev *dev)
 {
 	DPRINTK("phy_start\n");
-	if (!(dev->dev_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
+	if (!(dev->phy_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
 		return -ENOMEM;
 	spin_lock_init(&PRIV(dev)->lock);
 	memset(&PRIV(dev)->sonet_stats,0,sizeof(struct k_sonet_stats));

index feb023d7eebd..40644670cff2 100644
@@ -261,7 +261,7 @@ static int idt77105_start(struct atm_dev *dev)
 {
 	unsigned long flags;
 
-	if (!(dev->dev_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
+	if (!(dev->phy_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
 		return -ENOMEM;
 	PRIV(dev)->dev = dev;
 	spin_lock_irqsave(&idt77105_priv_lock, flags);

@@ -338,7 +338,7 @@ static int idt77105_stop(struct atm_dev *dev)
                 else
                     idt77105_all = walk->next;
 	        dev->phy = NULL;
-                dev->dev_data = NULL;
+                dev->phy_data = NULL;
                 kfree(walk);
                 break;
             }

index 650f3dd6b800..f604a8fe9d2e 100644
@@ -68,12 +68,13 @@ struct u64_stats_sync {
 };
 
 
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+#define u64_stats_init(syncp)	seqcount_init(&(syncp)->seq)
+#else
 static inline void u64_stats_init(struct u64_stats_sync *syncp)
 {
-#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
-	seqcount_init(&syncp->seq);
-#endif
 }
+#endif
 
 static inline void u64_stats_update_begin(struct u64_stats_sync *syncp)
 {

index 0cebe0ca03b2..94130588ebf5 100644
@@ -5144,6 +5144,9 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
 	int ret, i;
 
+	/* You can't remove system.nfs4_acl: */
+	if (buflen == 0)
+		return -EINVAL;
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
 	if (npages > ARRAY_SIZE(pages))

index 36f660da8124..56007258c014 100644
@@ -2144,27 +2144,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
 {
 	struct syscall_get_set_args *args = data;
 	struct pt_regs *pt = args->regs;
-	unsigned long *krbs, cfm, ndirty;
+	unsigned long *krbs, cfm, ndirty, nlocals, nouts;
 	int i, count;
 
 	if (unw_unwind_to_user(info) < 0)
 		return;
 
+	/*
+	 * We get here via a few paths:
+	 * - break instruction: cfm is shared with caller.
+	 *   syscall args are in out= regs, locals are non-empty.
+	 * - epsinstruction: cfm is set by br.call
+	 *   locals don't exist.
+	 *
+	 * For both cases argguments are reachable in cfm.sof - cfm.sol.
+	 * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ]
+	 */
 	cfm = pt->cr_ifs;
+	nlocals = (cfm >> 7) & 0x7f; /* aka sol */
+	nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */
 	krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
 	ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
 
 	count = 0;
 	if (in_syscall(pt))
-		count = min_t(int, args->n, cfm & 0x7f);
+		count = min_t(int, args->n, nouts);
 
+	/* Iterate over outs. */
 	for (i = 0; i < count; i++) {
+		int j = ndirty + nlocals + i + args->i;
 		if (args->rw)
-			*ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
-				args->args[i];
+			*ia64_rse_skip_regs(krbs, j) = args->args[i];
 		else
-			args->args[i] = *ia64_rse_skip_regs(krbs,
-				ndirty + i + args->i);
+			args->args[i] = *ia64_rse_skip_regs(krbs, j);
 	}
 
 	if (!args->rw) {

index 1d0b875fec44..ec909eec0b4c 100644
@@ -35,7 +35,7 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return regs->r10 == -1 ? regs->r8:0;
+	return regs->r10 == -1 ? -regs->r8:0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,

index f5ca15622dc9..2bfa4deb8cae 100644
@@ -245,12 +245,15 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 	 * ASID.  But, userspace flushes are probably much more
 	 * important performance-wise.
 	 *
-	 * Make sure to do only a single invpcid when KAISER is
-	 * disabled and we have only a single ASID.
+	 * In the KAISER disabled case, do an INVLPG to make sure
+	 * the mapping is flushed in case it is a global one.
 	 */
-	if (kaiser_enabled)
+	if (kaiser_enabled) {
 		invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
-	invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
+		invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
+	} else {
+		asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+	}
 }
 
 static inline void __flush_tlb_all(void)

@@ -165,14 +165,18 @@ __le64 *squashfs_read_inode_lookup_table
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end
+		    || (end - start) >
+		    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= lookup_table_start ||
+	    (lookup_table_start - start) >
+	    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}

@@ -30,6 +30,7 @@
 
 /* size of metadata (inode and directory) blocks */
 #define SQUASHFS_METADATA_SIZE		8192
+#define SQUASHFS_BLOCK_OFFSET		2
 
 /* default size of block device I/O */
 #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE

@@ -110,14 +110,16 @@ __le64 *squashfs_read_id_index_table(str
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= id_table_start || (id_table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}

@@ -122,14 +122,16 @@ __le64 *squashfs_read_xattr_id_table(str
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= table_start || (table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}

index 5012e3ad1225..624f74d03a83 100644
@@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev)
 	 */
 	l3->debug_irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler,
-			       0x0, "l3-dbg-irq", l3);
+			       IRQF_NO_THREAD, "l3-dbg-irq", l3);
 	if (ret) {
 		dev_err(l3->dev, "request_irq failed for %d\n",
 			l3->debug_irq);

@@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev)
 
 	l3->app_irq = platform_get_irq(pdev, 1);
 	ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler,
-			       0x0, "l3-app-irq", l3);
+			       IRQF_NO_THREAD, "l3-app-irq", l3);
 	if (ret)
 		dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq);
 

index a4ccc3122f93..cfcbc49f4ddf 100644
@@ -70,13 +70,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 	if (likely(success)) {
 		struct vlan_pcpu_stats *pcpu_stats;
 
-		pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
+		pcpu_stats = get_cpu_ptr(vlan->pcpu_stats);
 		u64_stats_update_begin(&pcpu_stats->syncp);
 		pcpu_stats->rx_packets++;
 		pcpu_stats->rx_bytes += len;
 		if (multicast)
 			pcpu_stats->rx_multicast++;
 		u64_stats_update_end(&pcpu_stats->syncp);
+		put_cpu_ptr(vlan->pcpu_stats);
 	} else {
 		this_cpu_inc(vlan->pcpu_stats->rx_errors);
 	}

index 0c69d5858558..40b3adf7ad99 100644
@@ -588,8 +588,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port)
 	 * in bits 15:8 and the patch level in bits 7:0 which is exactly what
 	 * the REG_PHY_REVISION register layout is.
 	 */
-
-	return priv->hw_params.gphy_rev;
+	if (priv->int_phy_mask & BIT(port))
+		return priv->hw_params.gphy_rev;
+	else
+		return 0;
 }
 
 static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,

index 3c01bc43889a..46323019aa63 100644
@@ -5920,15 +5920,19 @@ static void e1000_reset_task(struct work_struct *work)
 	struct e1000_adapter *adapter;
 	adapter = container_of(work, struct e1000_adapter, reset_task);
 
+	rtnl_lock();
 	/* don't run the task if already down */
-	if (test_bit(__E1000_DOWN, &adapter->state))
+	if (test_bit(__E1000_DOWN, &adapter->state)) {
+		rtnl_unlock();
 		return;
+	}
 
 	if (!(adapter->flags & FLAG_RESTART_NOW)) {
 		e1000e_dump(adapter);
 		e_err("Reset adapter unexpectedly\n");
 	}
 	e1000e_reinit_locked(adapter);
+	rtnl_unlock();
 }
 
 /**

index 6b03c8553e59..65deaf8f3004 100644
@@ -917,6 +917,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active)
 	} else {
 		data &= ~IGP02E1000_PM_D0_LPLU;
 		ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data);
+		if (ret_val)
+			return ret_val;
 		/* LPLU and SmartSpeed are mutually exclusive.  LPLU is used
 		 * during Dx states where the power conservation is most
 		 * important.  During driver activity we should enable

index 5174e0bd75d1..625336264a44 100644
@@ -1426,6 +1426,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter)
 
 	if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) {
 		vfree(fw_dump->tmpl_hdr);
+		fw_dump->tmpl_hdr = NULL;
 
 		if (qlcnic_83xx_md_check_extended_dump_capability(adapter))
 			extended = !qlcnic_83xx_extend_md_capab(adapter);

@@ -1444,6 +1445,8 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter)
 			struct qlcnic_83xx_dump_template_hdr *hdr;
 
 			hdr = fw_dump->tmpl_hdr;
+			if (!hdr)
+				return;
 			hdr->drv_cap_mask = 0x1f;
 			fw_dump->cap_mask = 0x1f;
 			dev_info(&pdev->dev,

index d065c0e2d18e..f3e0b2124a37 100644
@@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct c_can_priv *priv = netdev_priv(dev);
+	void __iomem *addr = priv->base;
 
 	unregister_c_can_dev(dev);
 
 	free_c_can_dev(dev);
 
-	pci_iounmap(pdev, priv->base);
+	pci_iounmap(pdev, addr);
 	pci_disable_msi(pdev);
 	pci_clear_master(pdev);
 	pci_release_regions(pdev);

index 4ead5a18b794..c41ab2cb272e 100644
@@ -212,18 +212,6 @@ static const struct can_bittiming_const c_can_bittiming_const = {
 	.brp_inc = 1,
 };
 
-static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv)
-{
-	if (priv->device)
-		pm_runtime_enable(priv->device);
-}
-
-static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv)
-{
-	if (priv->device)
-		pm_runtime_disable(priv->device);
-}
-
 static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv)
 {
 	if (priv->device)

@@ -1318,7 +1306,6 @@ static const struct net_device_ops c_can_netdev_ops = {
 
 int register_c_can_dev(struct net_device *dev)
 {
-	struct c_can_priv *priv = netdev_priv(dev);
 	int err;
 
 	/* Deactivate pins to prevent DRA7 DCAN IP from being

@@ -1328,28 +1315,19 @@ int register_c_can_dev(struct net_device *dev)
 	 */
 	pinctrl_pm_select_sleep_state(dev->dev.parent);
 
-	c_can_pm_runtime_enable(priv);
-
 	dev->flags |= IFF_ECHO;	/* we support local echo */
 	dev->netdev_ops = &c_can_netdev_ops;
 
 	err = register_candev(dev);
-	if (err)
-		c_can_pm_runtime_disable(priv);
-	else
+	if (!err)
 		devm_can_led_init(dev);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_c_can_dev);
 
 void unregister_c_can_dev(struct net_device *dev)
 {
-	struct c_can_priv *priv = netdev_priv(dev);
-
 	unregister_candev(dev);
-
-	c_can_pm_runtime_disable(priv);
 }
 EXPORT_SYMBOL_GPL(unregister_c_can_dev);
 

index 717530eac70c..c6a03f565e3f 100644
@@ -29,6 +29,7 @@
 #include <linux/list.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/clk.h>
 #include <linux/of.h>
 #include <linux/of_device.h>

@@ -385,6 +386,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
+	pm_runtime_enable(priv->device);
 	ret = register_c_can_dev(dev);
 	if (ret) {
 		dev_err(&pdev->dev, "registering %s failed (err=%d)\n",

@@ -397,6 +399,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	return 0;
 
 exit_free_device:
+	pm_runtime_disable(priv->device);
 	free_c_can_dev(dev);
 exit:
 	dev_err(&pdev->dev, "probe failed\n");

@@ -407,9 +410,10 @@ exit:
 static int c_can_plat_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
+	struct c_can_priv *priv = netdev_priv(dev);
 
 	unregister_c_can_dev(dev);
-
+	pm_runtime_disable(priv->device);
 	free_c_can_dev(dev);
 
 	return 0;

index 0bd7e7164796..197c27d8f584 100644
@@ -428,9 +428,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota)
 	}
 
 	while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) {
-		if (rxfs & RXFS_RFL)
-			netdev_warn(dev, "Rx FIFO 0 Message Lost\n");
-
 		m_can_read_fifo(dev, rxfs);
 
 		quota--;

index 1a13715b9a59..f37fbc71fc1d 100644
@@ -2681,14 +2681,14 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 			continue;
 
 		for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) {
-			if (~sdata->rc_rateidx_mcs_mask[i][j]) {
+			if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) {
 				sdata->rc_has_mcs_mask[i] = true;
 				break;
 			}
 		}
 
 		for (j = 0; j < NL80211_VHT_NSS_MAX; j++) {
-			if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) {
+			if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) {
 				sdata->rc_has_vht_mcs_mask[i] = true;
 				break;
 			}

index ff2270ead2e6..84e0e7f78029 100644
@@ -406,6 +406,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i
 
 	err = register_netdev(dev);
 	if (err) {
+		/* Set disconnected flag so that disconnect() returns early. */
+		pnd->disconnected = 1;
 		usb_driver_release_interface(&usbpn_driver, data_intf);
 		goto out;
 	}

index a60e1c1b4b5e..8bd062635399 100644
@@ -3472,13 +3472,13 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
 	    ep->com.local_addr.ss_family == AF_INET) {
 		err = cxgb4_remove_server_filter(
 			ep->com.dev->rdev.lldi.ports[0], ep->stid,
-			ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+			ep->com.dev->rdev.lldi.rxq_ids[0], false);
 	} else {
 		struct sockaddr_in6 *sin6;
 		c4iw_init_wr_wait(&ep->com.wr_wait);
 		err = cxgb4_remove_server(
 				ep->com.dev->rdev.lldi.ports[0], ep->stid,
-				ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+				ep->com.dev->rdev.lldi.rxq_ids[0], true);
 		if (err)
 			goto done;
 		err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait,

index 5aa4a01f698f..c1066487c06b 100644
@@ -622,12 +622,23 @@ void acpi_bus_put_acpi_device(struct acpi_device *adev)
 	put_device(&adev->dev);
 }
 
+static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id)
+{
+	struct acpi_device_bus_id *acpi_device_bus_id;
+
+	/* Find suitable bus_id and instance number in acpi_bus_id_list. */
+	list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) {
+		if (!strcmp(acpi_device_bus_id->bus_id, dev_id))
+			return acpi_device_bus_id;
+	}
+	return NULL;
+}
+
 int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *))
 {
+	struct acpi_device_bus_id *acpi_device_bus_id;
 	int result;
-	struct acpi_device_bus_id *acpi_device_bus_id, *new_bus_id;
-	int found = 0;
 
 	if (device->handle) {
 		acpi_status status;

@@ -653,38 +664,26 @@ int acpi_device_add(struct acpi_device *device,
 	INIT_LIST_HEAD(&device->del_list);
 	mutex_init(&device->physical_node_lock);
 
-	new_bus_id = kzalloc(sizeof(struct acpi_device_bus_id), GFP_KERNEL);
-	if (!new_bus_id) {
-		pr_err(PREFIX "Memory allocation error\n");
-		result = -ENOMEM;
-		goto err_detach;
-	}
-
 	mutex_lock(&acpi_device_lock);
-	/*
-	 * Find suitable bus_id and instance number in acpi_bus_id_list
-	 * If failed, create one and link it into acpi_bus_id_list
-	 */
-	list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) {
-		if (!strcmp(acpi_device_bus_id->bus_id,
-			    acpi_device_hid(device))) {
-			acpi_device_bus_id->instance_no++;
-			found = 1;
-			kfree(new_bus_id);
-			break;
+
+	acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device));
+	if (acpi_device_bus_id) {
+		acpi_device_bus_id->instance_no++;
+	} else {
+		acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id),
+					     GFP_KERNEL);
+		if (!acpi_device_bus_id) {
+			result = -ENOMEM;
+			goto err_unlock;
 		}
-	}
-	if (!found) {
-		acpi_device_bus_id = new_bus_id;
 		acpi_device_bus_id->bus_id =
 			kstrdup_const(acpi_device_hid(device), GFP_KERNEL);
 		if (!acpi_device_bus_id->bus_id) {
-			pr_err(PREFIX "Memory allocation error for bus id\n");
+			kfree(acpi_device_bus_id);
 			result = -ENOMEM;
-			goto err_free_new_bus_id;
+			goto err_unlock;
 		}
 
-		acpi_device_bus_id->instance_no = 0;
 		list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
 	}
 	dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no);

@@ -719,13 +718,9 @@ int acpi_device_add(struct acpi_device *device,
 		list_del(&device->node);
 	list_del(&device->wakeup_list);
 
- err_free_new_bus_id:
-	if (!found)
-		kfree(new_bus_id);
-
+ err_unlock:
 	mutex_unlock(&acpi_device_lock);
 
- err_detach:
 	acpi_detach_data(device->handle, acpi_scan_drop_device);
 	return result;
 }

index eae0b278d517..56c429ea6aaf 100644
@@ -18,6 +18,8 @@
 #ifndef _ACPI_INTERNAL_H_
 #define _ACPI_INTERNAL_H_
 
+#include <linux/idr.h>
+
 #define PREFIX "ACPI: "
 
 int early_acpi_osi_init(void);

@@ -97,9 +99,11 @@ void acpi_scan_table_handler(u32 event, void *table, void *context);
 
 extern struct list_head acpi_bus_id_list;
 
+#define ACPI_MAX_DEVICE_INSTANCES	4096
+
 struct acpi_device_bus_id {
 	const char *bus_id;
-	unsigned int instance_no;
+	struct ida instance_ida;
 	struct list_head node;
 };
 

index c1066487c06b..d749fe20fbfc 100644
@@ -481,9 +481,8 @@ static void acpi_device_del(struct acpi_device *device)
 	list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node)
 		if (!strcmp(acpi_device_bus_id->bus_id,
 			    acpi_device_hid(device))) {
-			if (acpi_device_bus_id->instance_no > 0)
-				acpi_device_bus_id->instance_no--;
-			else {
+			ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no);
+			if (ida_is_empty(&acpi_device_bus_id->instance_ida)) {
 				list_del(&acpi_device_bus_id->node);
 				kfree_const(acpi_device_bus_id->bus_id);
 				kfree(acpi_device_bus_id);

@@ -634,6 +633,21 @@ static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id)
 	return NULL;
 }
 
+static int acpi_device_set_name(struct acpi_device *device,
+				struct acpi_device_bus_id *acpi_device_bus_id)
+{
+	struct ida *instance_ida = &acpi_device_bus_id->instance_ida;
+	int result;
+
+	result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL);
+	if (result < 0)
+		return result;
+
+	device->pnp.instance_no = result;
+	dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result);
+	return 0;
+}
+
 int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *))
 {

@@ -668,7 +682,9 @@ int acpi_device_add(struct acpi_device *device,
 
 	acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device));
 	if (acpi_device_bus_id) {
-		acpi_device_bus_id->instance_no++;
+		result = acpi_device_set_name(device, acpi_device_bus_id);
+		if (result)
+			goto err_unlock;
 	} else {
 		acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id),
 					     GFP_KERNEL);

@@ -684,9 +700,16 @@ int acpi_device_add(struct acpi_device *device,
 			goto err_unlock;
 		}
 
+		ida_init(&acpi_device_bus_id->instance_ida);
+
+		result = acpi_device_set_name(device, acpi_device_bus_id);
+		if (result) {
+			kfree(acpi_device_bus_id);
+			goto err_unlock;
+		}
+
 		list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
 	}
-	dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no);
 
 	if (device->parent)
 		list_add_tail(&device->node, &device->parent->children);

index c1a524de67c5..53b2a1f320f9 100644
@@ -241,6 +241,7 @@ struct acpi_pnp_type {
 
 struct acpi_device_pnp {
 	acpi_bus_id bus_id;		/* Object name */
+	int instance_no;		/* Instance number of this object */
 	struct acpi_pnp_type type;	/* ID type */
 	acpi_bus_address bus_address;	/* _ADR */
 	char *unique_id;		/* _UID */

index b87221efdf7e..51fdec9273d7 100644
@@ -248,10 +248,6 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 		queue->set = true;
 		queue->tid = buffer->tid;
 		queue->cpu = buffer->cpu;
-	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
-		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
-		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
-		return -EINVAL;
 	}
 
 	buffer->buffer_nr = queues->next_buffer_nr++;

index 8e83649f77ce..42e5677d932d 100644
@@ -932,7 +932,7 @@ static void hidg_free_inst(struct usb_function_instance *f)
 	mutex_lock(&hidg_ida_lock);
 
 	hidg_put_minor(opts->minor);
-	if (idr_is_empty(&hidg_ida.idr))
+	if (ida_is_empty(&hidg_ida))
 		ghid_cleanup();
 
 	mutex_unlock(&hidg_ida_lock);

@@ -958,7 +958,7 @@ static struct usb_function_instance *hidg_alloc_inst(void)
 
 	mutex_lock(&hidg_ida_lock);
 
-	if (idr_is_empty(&hidg_ida.idr)) {
+	if (ida_is_empty(&hidg_ida)) {
 		status = ghid_setup(NULL, HIDG_MINORS);
 		if (status)  {
 			ret = ERR_PTR(status);

@@ -971,7 +971,7 @@ static struct usb_function_instance *hidg_alloc_inst(void)
 	if (opts->minor < 0) {
 		ret = ERR_PTR(opts->minor);
 		kfree(opts);
-		if (idr_is_empty(&hidg_ida.idr))
+		if (ida_is_empty(&hidg_ida))
 			ghid_cleanup();
 		goto unlock;
 	}

index b962f24b500b..b3d036d06553 100644
@@ -1276,7 +1276,7 @@ static void gprinter_free_inst(struct usb_function_instance *f)
 	mutex_lock(&printer_ida_lock);
 
 	gprinter_put_minor(opts->minor);
-	if (idr_is_empty(&printer_ida.idr))
+	if (ida_is_empty(&printer_ida))
 		gprinter_cleanup();
 
 	mutex_unlock(&printer_ida_lock);

@@ -1300,7 +1300,7 @@ static struct usb_function_instance *gprinter_alloc_inst(void)
 
 	mutex_lock(&printer_ida_lock);
 
-	if (idr_is_empty(&printer_ida.idr)) {
+	if (ida_is_empty(&printer_ida)) {
 		status = gprinter_setup(PRINTER_MINORS);
 		if (status) {
 			ret = ERR_PTR(status);

@@ -1313,7 +1313,7 @@ static struct usb_function_instance *gprinter_alloc_inst(void)
 	if (opts->minor < 0) {
 		ret = ERR_PTR(opts->minor);
 		kfree(opts);
-		if (idr_is_empty(&printer_ida.idr))
+		if (ida_is_empty(&printer_ida))
 			gprinter_cleanup();
 		goto unlock;
 	}

index 083d61e92706..3639a28188c9 100644
@@ -195,6 +195,11 @@ static inline int ida_get_new(struct ida *ida, int *p_id)
 	return ida_get_new_above(ida, 0, p_id);
 }
 
+static inline bool ida_is_empty(struct ida *ida)
+{
+	return idr_is_empty(&ida->idr);
+}
+
 void __init idr_init_cache(void);
 
 #endif /* __IDR_H__ */

@@ -1565,8 +1565,7 @@ static void mark_wake_futex(struct wake_
 	 * memory barrier is required here to prevent the following
 	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
-	smp_wmb();
-	q->lock_ptr = NULL;
+	smp_store_release(&q->lock_ptr, NULL);
 }
 
 /*

@@ -3234,10 +3234,7 @@ static int futex_wait_requeue_pi(u32 __u
 	 * The waiter is allocated on our stack, manipulated by the requeue
 	 * code while we sleep on uaddr.
 	 */
-	debug_rt_mutex_init_waiter(&rt_waiter);
-	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&rt_waiter.tree_entry);
-	rt_waiter.task = NULL;
+	rt_mutex_init_waiter(&rt_waiter);
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))

@@ -1176,6 +1176,14 @@ void rt_mutex_adjust_pi(struct task_stru
 				   next_lock, NULL, task);
 }
 
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->task = NULL;
+}
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take

@@ -1258,9 +1266,7 @@ rt_mutex_slowlock(struct rt_mutex *lock,
 	unsigned long flags;
 	int ret = 0;
 
-	debug_rt_mutex_init_waiter(&waiter);
-	RB_CLEAR_NODE(&waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&waiter.tree_entry);
+	rt_mutex_init_waiter(&waiter);
 
 	/*
 	 * Technically we could use raw_spin_[un]lock_irq() here, but this can

@@ -103,6 +103,7 @@ extern struct task_struct *rt_mutex_next
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);

@@ -2333,20 +2333,7 @@ queue_unlock(struct futex_hash_bucket *h
 	hb_waiters_dec(hb);
 }
 
-/**
- * queue_me() - Enqueue the futex_q on the futex_hash_bucket
- * @q:	The futex_q to enqueue
- * @hb:	The destination hash bucket
- *
- * The hb->lock must be held by the caller, and is released here. A call to
- * queue_me() is typically paired with exactly one call to unqueue_me().  The
- * exceptions involve the PI related operations, which may use unqueue_me_pi()
- * or nothing if the unqueue is done as part of the wake process and the unqueue
- * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
- * an example).
- */
-static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
-	__releases(&hb->lock)
+static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
 	int prio;
 

@@ -2363,6 +2350,24 @@ static inline void queue_me(struct futex
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me().  The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
+{
+	__queue_me(q, hb);
 	spin_unlock(&hb->lock);
 }
 

@@ -2868,6 +2873,7 @@ static int futex_lock_pi(u32 __user *uad
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct task_struct *exiting = NULL;
+	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
 	int res, ret;

@@ -2928,25 +2934,52 @@ retry_private:
 		}
 	}
 
+	WARN_ON(!q.pi_state);
+
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	queue_me(&q, hb);
+	__queue_me(&q, hb);
 
-	WARN_ON(!q.pi_state);
-	/*
-	 * Block on the PI mutex:
-	 */
-	if (!trylock) {
-		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
-	} else {
+	if (trylock) {
 		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
+		goto no_block;
 	}
 
+	/*
+	 * We must add ourselves to the rt_mutex waitlist while holding hb->lock
+	 * such that the hb and rt_mutex wait lists match.
+	 */
+	rt_mutex_init_waiter(&rt_waiter);
+	ret = rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	if (ret) {
+		if (ret == 1)
+			ret = 0;
+
+		goto no_block;
+	}
+
+	spin_unlock(q.lock_ptr);
+
+	if (unlikely(to))
+		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+
+	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+
 	spin_lock(q.lock_ptr);
 	/*
+	 * If we failed to acquire the lock (signal/timeout), we must
+	 * first acquire the hb->lock before removing the lock from the
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
+	 * wait lists consistent.
+	 */
+	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+		ret = 0;
+
+no_block:
+	/*
 	 * Fixup the pi_state owner and possibly acquire the lock if we
 	 * haven't already.
 	 */

@@ -1523,19 +1523,6 @@ int __sched rt_mutex_lock_interruptible(
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
 /*
- * Futex variant with full deadlock detection.
- * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock().
- */
-int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock,
-			      struct hrtimer_sleeper *timeout)
-{
-	might_sleep();
-
-	return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE,
-				 timeout, RT_MUTEX_FULL_CHAINWALK);
-}
-
-/*
  * Futex variant, must not use fastpath.
  */
 int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)

@@ -1808,12 +1795,6 @@ int rt_mutex_wait_proxy_lock(struct rt_m
 	/* sleep on the mutex */
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
-	/*
-	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
-	 * have to fix that up.
-	 */
-	fixup_rt_mutex_waiters(lock);
-
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;

@@ -1853,6 +1834,13 @@ bool rt_mutex_cleanup_proxy_lock(struct
 		fixup_rt_mutex_waiters(lock);
 		cleanup = true;
 	}
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return cleanup;

@@ -112,7 +112,6 @@ extern int rt_mutex_wait_proxy_lock(stru
 			       struct rt_mutex_waiter *waiter);
 extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 				 struct rt_mutex_waiter *waiter);
-extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 extern int rt_mutex_futex_trylock(struct rt_mutex *l);
 extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
 

@@ -2948,20 +2948,33 @@ retry_private:
 		goto no_block;
 	}
 
+	rt_mutex_init_waiter(&rt_waiter);
+
 	/*
-	 * We must add ourselves to the rt_mutex waitlist while holding hb->lock
-	 * such that the hb and rt_mutex wait lists match.
+	 * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
+	 * hold it while doing rt_mutex_start_proxy(), because then it will
+	 * include hb->lock in the blocking chain, even through we'll not in
+	 * fact hold it while blocking. This will lead it to report -EDEADLK
+	 * and BUG when futex_unlock_pi() interleaves with this.
+	 *
+	 * Therefore acquire wait_lock while holding hb->lock, but drop the
+	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
+	 * serializes against futex_unlock_pi() as that does the exact same
+	 * lock handoff sequence.
 	 */
-	rt_mutex_init_waiter(&rt_waiter);
-	ret = rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+	spin_unlock(q.lock_ptr);
+	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+
 	if (ret) {
 		if (ret == 1)
 			ret = 0;
 
+		spin_lock(q.lock_ptr);
 		goto no_block;
 	}
 
-	spin_unlock(q.lock_ptr);
 
 	if (unlikely(to))
 		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);

@@ -2974,6 +2987,9 @@ retry_private:
 	 * first acquire the hb->lock before removing the lock from the
 	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
 	 * wait lists consistent.
+	 *
+	 * In particular; it is important that futex_unlock_pi() can not
+	 * observe this inconsistency.
 	 */
 	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
 		ret = 0;

@@ -3071,10 +3087,6 @@ retry:
 
 		get_pi_state(pi_state);
 		/*
-		 * Since modifying the wait_list is done while holding both
-		 * hb->lock and wait_lock, holding either is sufficient to
-		 * observe it.
-		 *
 		 * By taking wait_lock while still holding hb->lock, we ensure
 		 * there is no point where we hold neither; and therefore
 		 * wake_futex_pi() must observe a state consistent with what we

71 lines not on this page · raw message

@@ -104,6 +104,9 @@ extern void rt_mutex_init_proxy_locked(s
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
 extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);

@@ -3018,8 +3018,10 @@ out_unlock_put_key:
 out_put_key:
 	put_futex_key(&q.key);
 out:
-	if (to)
+	if (to) {
+		hrtimer_cancel(&to->timer);
 		destroy_hrtimer_on_stack(&to->timer);
+	}
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:

@@ -1796,12 +1796,14 @@ int rt_mutex_wait_proxy_lock(struct rt_m
 	int ret;
 
 	raw_spin_lock_irq(&lock->wait_lock);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-
 	/* sleep on the mutex */
+	set_current_state(TASK_INTERRUPTIBLE);
 	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
-
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;

@@ -1833,15 +1835,25 @@ bool rt_mutex_cleanup_proxy_lock(struct
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	/*
+	 * Do an unconditional try-lock, this deals with the lock stealing
+	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+	 * sets a NULL owner.
+	 *
+	 * We're not interested in the return value, because the subsequent
+	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+	 * we will own the lock and it will have removed the waiter. If we
+	 * failed the trylock, we're still not owner and we need to remove
+	 * ourselves.
+	 */
+	try_to_take_rt_mutex(lock, current, waiter);
+	/*
 	 * Unless we're the owner; we're still enqueued on the wait_list.
 	 * So check if we became owner, if not, take us off the wait_list.
 	 */
 	if (rt_mutex_owner(lock) != current) {
 		remove_waiter(lock, waiter);
-		fixup_rt_mutex_waiters(lock);
 		cleanup = true;
 	}
-
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.

@@ -2958,35 +2958,39 @@ retry_private:
 	 * and BUG when futex_unlock_pi() interleaves with this.
 	 *
 	 * Therefore acquire wait_lock while holding hb->lock, but drop the
-	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
-	 * serializes against futex_unlock_pi() as that does the exact same
-	 * lock handoff sequence.
+	 * latter before calling __rt_mutex_start_proxy_lock(). This
+	 * interleaves with futex_unlock_pi() -- which does a similar lock
+	 * handoff -- such that the latter can observe the futex_q::pi_state
+	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
 	spin_unlock(q.lock_ptr);
+	/*
+	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+	 * such that futex_unlock_pi() is guaranteed to observe the waiter when
+	 * it sees the futex_q::pi_state.
+	 */
 	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
 	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
 
 	if (ret) {
 		if (ret == 1)
 			ret = 0;
-
-		spin_lock(q.lock_ptr);
-		goto no_block;
+		goto cleanup;
 	}
 
-
 	if (unlikely(to))
 		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
 
 	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
+cleanup:
 	spin_lock(q.lock_ptr);
 	/*
-	 * If we failed to acquire the lock (signal/timeout), we must
+	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
 	 * first acquire the hb->lock before removing the lock from the
-	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
-	 * wait lists consistent.
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
+	 * lists consistent.
 	 *
 	 * In particular; it is important that futex_unlock_pi() can not
 	 * observe this inconsistency.

@@ -3093,6 +3097,10 @@ retry:
 		 * there is no point where we hold neither; and therefore
 		 * wake_futex_pi() must observe a state consistent with what we
 		 * observed.
+		 *
+		 * In particular; this forces __rt_mutex_start_proxy() to
+		 * complete such that we're guaranteed to observe the
+		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);

@@ -1695,12 +1695,33 @@ void rt_mutex_proxy_unlock(struct rt_mut
 	rt_mutex_set_owner(lock, NULL);
 }
 
+/**
+ * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: does _NOT_ remove the @waiter on failure; must either call
+ * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 

@@ -1718,9 +1739,6 @@ int __rt_mutex_start_proxy_lock(struct r
 		ret = 0;
 	}
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;

@@ -1732,12 +1750,18 @@ int __rt_mutex_start_proxy_lock(struct r
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
  *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
+ * on failure.
+ *
  * Returns:
  *  0 - task blocked on lock
  *  1 - acquired the lock for task, caller should wake it up
  * <0 - error
  *
- * Special API call for FUTEX_REQUEUE_PI support.
+ * Special API call for PI-futex support.
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,

@@ -1747,6 +1771,8 @@ int rt_mutex_start_proxy_lock(struct rt_
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;

@@ -1814,7 +1840,8 @@ int rt_mutex_wait_proxy_lock(struct rt_m
  * @lock:		the rt_mutex we were woken on
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
+ * rt_mutex_wait_proxy_lock().
  *
  * Unless we acquired the lock; we're still enqueued on the wait-list and can
  * in fact still be granted ownership until we're removed. Therefore we can

@@ -1553,11 +1553,7 @@ static void mark_wake_futex(struct wake_
 	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
 		return;
 
-	/*
-	 * Queue the task for later wakeup for after we've released
-	 * the hb->lock. wake_q_add() grabs reference to p.
-	 */
-	wake_q_add(wake_q, p);
+	get_task_struct(p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as

@@ -1566,6 +1562,13 @@ static void mark_wake_futex(struct wake_
 	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_store_release(&q->lock_ptr, NULL);
+
+	/*
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
+	 */
+	wake_q_add(wake_q, p);
+	put_task_struct(p);
 }
 
 /*

@@ -1407,13 +1407,15 @@ static int lookup_pi_state(u32 __user *u
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
+	int err;
 	u32 uninitialized_var(curval);
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
+	err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (unlikely(err))
+		return err;
 
 	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;

@@ -1606,10 +1608,8 @@ static int wake_futex_pi(u32 __user *uad
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
-		ret = -EFAULT;
-
-	} else if (curval != uval) {
+	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (!ret && (curval != uval)) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
 		 * try the TID->0 transition) raced with a waiter setting the

@@ -1795,32 +1795,32 @@ retry_private:
 	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-
 		double_unlock_hb(hb1, hb2);
 
-#ifndef CONFIG_MMU
-		/*
-		 * we don't get EFAULT from MMU faults if we don't have an MMU,
-		 * but we might get them from range checking
-		 */
-		ret = op_ret;
-		goto out_put_keys;
-#endif
-
-		if (unlikely(op_ret != -EFAULT)) {
+		if (!IS_ENABLED(CONFIG_MMU) ||
+		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+			/*
+			 * we don't get EFAULT from MMU faults if we don't have
+			 * an MMU, but we might get them from range checking
+			 */
 			ret = op_ret;
 			goto out_put_keys;
 		}
 
-		ret = fault_in_user_writeable(uaddr2);
-		if (ret)
-			goto out_put_keys;
+		if (op_ret == -EFAULT) {
+			ret = fault_in_user_writeable(uaddr2);
+			if (ret)
+				goto out_put_keys;
+		}
 
-		if (!(flags & FLAGS_SHARED))
+		if (!(flags & FLAGS_SHARED)) {
+			cond_resched();
 			goto retry_private;
+		}
 
 		put_futex_key(&key2);
 		put_futex_key(&key1);
+		cond_resched();
 		goto retry;
 	}
 

@@ -2516,14 +2516,17 @@ retry:
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
 
-	if (get_futex_value_locked(&uval, uaddr))
-		goto handle_fault;
+	err = get_futex_value_locked(&uval, uaddr);
+	if (err)
+		goto handle_err;
 
 	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			goto handle_fault;
+		err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+		if (err)
+			goto handle_err;
+
 		if (curval == uval)
 			break;
 		uval = curval;

@@ -2538,23 +2541,36 @@ retry:
 	return argowner == current;
 
 	/*
-	 * To handle the page fault we need to drop the locks here. That gives
-	 * the other task (either the highest priority waiter itself or the
-	 * task which stole the rtmutex) the chance to try the fixup of the
-	 * pi_state. So once we are back from handling the fault we need to
-	 * check the pi_state after reacquiring the locks and before trying to
-	 * do another fixup. When the fixup has been done already we simply
-	 * return.
+	 * In order to reschedule or handle a page fault, we need to drop the
+	 * locks here. In the case of a fault, this gives the other task
+	 * (either the highest priority waiter itself or the task which stole
+	 * the rtmutex) the chance to try the fixup of the pi_state. So once we
+	 * are back from handling the fault we need to check the pi_state after
+	 * reacquiring the locks and before trying to do another fixup. When
+	 * the fixup has been done already we simply return.
 	 *
 	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
 	 * drop hb->lock since the caller owns the hb -> futex_q relation.
 	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
-handle_fault:
+handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
-	err = fault_in_user_writeable(uaddr);
+	switch (err) {
+	case -EFAULT:
+		err = fault_in_user_writeable(uaddr);
+		break;
+
+	case -EAGAIN:
+		cond_resched();
+		err = 0;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
 
 	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);

@@ -3128,10 +3144,8 @@ retry:
 		 * A unconditional UNLOCK_PI op raced against a waiter
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
-		if (ret == -EAGAIN) {
-			put_futex_key(&key);
-			goto retry;
-		}
+		if (ret == -EAGAIN)
+			goto pi_retry;
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.

@@ -3146,9 +3160,19 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
 		spin_unlock(&hb->lock);
-		goto pi_faulted;
+		switch (ret) {
+		case -EFAULT:
+			goto pi_faulted;
+
+		case -EAGAIN:
+			goto pi_retry;
+
+		default:
+			WARN_ON_ONCE(1);
+			goto out_putkey;
+		}
 	}
 
 	/*

@@ -3162,6 +3186,11 @@ out_putkey:
 	put_futex_key(&key);
 	return ret;
 
+pi_retry:
+	put_futex_key(&key);
+	cond_resched();
+	goto retry;
+
 pi_faulted:
 	put_futex_key(&key);
 

@@ -3504,6 +3533,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
 	u32 uval, uninitialized_var(nval), mval;
+	int err;
 
 	/* Futex address must be 32bit aligned */
 	if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)

@@ -3513,42 +3543,57 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
-	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
-		/*
-		 * Ok, this dying thread is truly holding a futex
-		 * of interest. Set the OWNER_DIED bit atomically
-		 * via cmpxchg, and if the value had FUTEX_WAITERS
-		 * set, wake up a waiter (if any). (We have to do a
-		 * futex_wake() even if OWNER_DIED is already set -
-		 * to handle the rare but possible case of recursive
-		 * thread-death.) The rest of the cleanup is done in
-		 * userspace.
-		 */
-		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		/*
-		 * We are not holding a lock here, but we want to have
-		 * the pagefault_disable/enable() protection because
-		 * we want to handle the fault gracefully. If the
-		 * access fails we try to fault in the futex with R/W
-		 * verification via get_user_pages. get_user() above
-		 * does not guarantee R/W access. If that fails we
-		 * give up and leave the futex locked.
-		 */
-		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+		return 0;
+
+	/*
+	 * Ok, this dying thread is truly holding a futex
+	 * of interest. Set the OWNER_DIED bit atomically
+	 * via cmpxchg, and if the value had FUTEX_WAITERS
+	 * set, wake up a waiter (if any). (We have to do a
+	 * futex_wake() even if OWNER_DIED is already set -
+	 * to handle the rare but possible case of recursive
+	 * thread-death.) The rest of the cleanup is done in
+	 * userspace.
+	 */
+	mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+	/*
+	 * We are not holding a lock here, but we want to have
+	 * the pagefault_disable/enable() protection because
+	 * we want to handle the fault gracefully. If the
+	 * access fails we try to fault in the futex with R/W
+	 * verification via get_user_pages. get_user() above
+	 * does not guarantee R/W access. If that fails we
+	 * give up and leave the futex locked.
+	 */
+	if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+		switch (err) {
+		case -EFAULT:
 			if (fault_in_user_writeable(uaddr))
 				return -1;
 			goto retry;
-		}
-		if (nval != uval)
+
+		case -EAGAIN:
+			cond_resched();
 			goto retry;
 
-		/*
-		 * Wake robust non-PI futexes here. The wakeup of
-		 * PI futexes happens in exit_pi_state():
-		 */
-		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		default:
+			WARN_ON_ONCE(1);
+			return err;
+		}
 	}
+
+	if (nval != uval)
+		goto retry;
+
+	/*
+	 * Wake robust non-PI futexes here. The wakeup of
+	 * PI futexes happens in exit_pi_state():
+	 */
+	if (!pi && (uval & FUTEX_WAITERS))
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
 	return 0;
 }
 

@@ -26,7 +26,12 @@
 #include <asm/errno.h>
 #include <asm/sysreg.h>
 
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
+do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
 	asm volatile(							\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
 		    CONFIG_ARM64_PAN)					\

@@ -34,21 +39,26 @@
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w0, %w3, %2\n"						\
-"	cbnz	%w0, 1b\n"						\
-"	dmb	ish\n"							\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w7\n"						\
 "3:\n"									\
+"	dmb	ish\n"							\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
-"4:	mov	%w0, %w5\n"						\
+"4:	mov	%w0, %w6\n"						\
 "	b	3b\n"							\
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
 		    CONFIG_ARM64_PAN)					\
-	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
-	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "memory")
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN)			\
+	: "memory");							\
+} while (0)
 
 static inline int
 arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)

@@ -59,23 +69,23 @@ arch_futex_atomic_op_inuser(int op, int
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w3, %w4",
+		__futex_atomic_op("mov	%w3, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w3, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w3, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w3, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w3, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:

@@ -95,6 +105,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
 	u32 val, tmp;
 	u32 __user *uaddr;
 

@@ -106,21 +117,25 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
 ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
-"	sub	%w3, %w1, %w4\n"
-"	cbnz	%w3, 3f\n"
-"2:	stlxr	%w3, %w5, %2\n"
-"	cbnz	%w3, 1b\n"
-"	dmb	ish\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w8\n"
 "3:\n"
+"	dmb	ish\n"
+"4:\n"
 "	.pushsection .fixup,\"ax\"\n"
-"4:	mov	%w0, %w6\n"
-"	b	3b\n"
+"5:	mov	%w0, %w7\n"
+"	b	4b\n"
 "	.popsection\n"
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 4b)
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
 ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
-	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
-	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
 	: "memory");
 
 	*uval = val;

@@ -3526,11 +3526,16 @@ err_unlock:
 	return ret;
 }
 
+/* Constants for the pending_op argument of handle_futex_death */
+#define HANDLE_DEATH_PENDING	true
+#define HANDLE_DEATH_LIST	false
+
 /*
  * Process a futex-list entry, check whether it's owned by the
  * dying task, and do notification if so:
  */
-static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
+static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
+			      bool pi, bool pending_op)
 {
 	u32 uval, uninitialized_var(nval), mval;
 	int err;

@@ -3543,6 +3548,42 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
+	/*
+	 * Special case for regular (non PI) futexes. The unlock path in
+	 * user space has two race scenarios:
+	 *
+	 * 1. The unlock path releases the user space futex value and
+	 *    before it can execute the futex() syscall to wake up
+	 *    waiters it is killed.
+	 *
+	 * 2. A woken up waiter is killed before it can acquire the
+	 *    futex in user space.
+	 *
+	 * In both cases the TID validation below prevents a wakeup of
+	 * potential waiters which can cause these waiters to block
+	 * forever.
+	 *
+	 * In both cases the following conditions are met:
+	 *
+	 *	1) task->robust_list->list_op_pending != NULL
+	 *	   @pending_op == true
+	 *	2) User space futex value == 0
+	 *	3) Regular futex: @pi == false
+	 *
+	 * If these conditions are met, it is safe to attempt waking up a
+	 * potential waiter without touching the user space futex value and
+	 * trying to set the OWNER_DIED bit. The user space futex value is
+	 * uncontended and the rest of the user space mutex state is
+	 * consistent, so a woken waiter will just take over the
+	 * uncontended futex. Setting the OWNER_DIED bit would create
+	 * inconsistent state and malfunction of the user space owner died
+	 * handling.
+	 */
+	if (pending_op && !pi && !uval) {
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		return 0;
+	}
+
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
 		return 0;
 

@@ -3662,10 +3703,11 @@ static void exit_robust_list(struct task
 		 * A pending lock might already be on the list, so
 		 * don't process it twice:
 		 */
-		if (entry != pending)
+		if (entry != pending) {
 			if (handle_futex_death((void __user *)entry + futex_offset,
-						curr, pi))
+						curr, pi, HANDLE_DEATH_LIST))
 				return;
+		}
 		if (rc)
 			return;
 		entry = next_entry;

@@ -3679,9 +3721,10 @@ static void exit_robust_list(struct task
 		cond_resched();
 	}
 
-	if (pending)
+	if (pending) {
 		handle_futex_death((void __user *)pending + futex_offset,
-				   curr, pip);
+				   curr, pip, HANDLE_DEATH_PENDING);
+	}
 }
 
 static void futex_cleanup(struct task_struct *tsk)

@@ -3964,7 +4007,8 @@ void compat_exit_robust_list(struct task
 		if (entry != pending) {
 			void __user *uaddr = futex_uaddr(entry, futex_offset);
 
-			if (handle_futex_death(uaddr, curr, pi))
+			if (handle_futex_death(uaddr, curr, pi,
+					       HANDLE_DEATH_LIST))
 				return;
 		}
 		if (rc)