4.9.236-rc1 review

@@ -1407,6 +1407,17 @@ static void hid_output_field(const struc
 }
 
 /*
+ * Compute the size of a report.
+ */
+static size_t hid_compute_report_size(struct hid_report *report)
+{
+	if (report->size)
+		return ((report->size - 1) >> 3) + 1;
+
+	return 0;
+}
+
+/*
  * Create a report. 'data' has to be allocated using
  * hid_alloc_report_buf() so that it has proper size.
  */

@@ -1418,7 +1429,7 @@ void hid_output_report(struct hid_report
 	if (report->id > 0)
 		*data++ = report->id;
 
-	memset(data, 0, ((report->size - 1) >> 3) + 1);
+	memset(data, 0, hid_compute_report_size(report));
 	for (n = 0; n < report->maxfield; n++)
 		hid_output_field(report->device, report->field[n], data);
 }

@@ -1545,7 +1556,7 @@ int hid_report_raw_event(struct hid_devi
 		csize--;
 	}
 
-	rsize = ((report->size - 1) >> 3) + 1;
+	rsize = hid_compute_report_size(report);
 
 	if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE)
 		rsize = HID_MAX_BUFFER_SIZE - 1;

@@ -1026,6 +1026,10 @@ static void hidinput_configure_usage(str
 	}
 
 mapped:
+	/* Mapping failed, bail out */
+	if (!bit)
+		return;
+
 	if (device->driver->input_mapped &&
 	    device->driver->input_mapped(device, hidinput, field, usage,
 					 &bit, &max) < 0) {

@@ -567,6 +567,8 @@ static int mt_touch_input_mapping(struct
 	case HID_UP_BUTTON:
 		code = BTN_MOUSE + ((usage->hid - 1) & HID_USAGE);
 		hid_map_usage(hi, usage, bit, max, EV_KEY, code);
+		if (!*bit)
+			return -1;
 		input_set_capability(hi->input, EV_KEY, code);
 		return 1;
 

70 lines not on this page · raw message

index 0af7fd311979d..587fc5c686b3c 100644
@@ -758,15 +758,18 @@ static ssize_t applesmc_light_show(struct device *dev,
 	}
 
 	ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length);
+	if (ret)
+		goto out;
 	/* newer macbooks report a single 10-bit bigendian value */
 	if (data_length == 10) {
 		left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2;
 		goto out;
 	}
 	left = buffer[2];
+
+	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	if (ret)
 		goto out;
-	ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length);
 	right = buffer[2];
 
 out:

@@ -814,12 +817,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev,
 	sprintf(newkey, fan_speed_fmt[to_option(attr)], to_index(attr));
 
 	ret = applesmc_read_key(newkey, buffer, 2);
-	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
+
+	speed = ((buffer[0] << 8 | buffer[1]) >> 2);
+	return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed);
 }
 
 static ssize_t applesmc_store_fan_speed(struct device *dev,

@@ -854,12 +856,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev,
 	u8 buffer[2];
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
+
+	manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01;
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual);
 }
 
 static ssize_t applesmc_store_fan_manual(struct device *dev,

@@ -875,10 +876,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev,
 		return -EINVAL;
 
 	ret = applesmc_read_key(FANS_MANUAL, buffer, 2);
-	val = (buffer[0] << 8 | buffer[1]);
 	if (ret)
 		goto out;
 
+	val = (buffer[0] << 8 | buffer[1]);
+
 	if (input)
 		val = val | (0x01 << to_index(attr));
 	else

@@ -954,13 +956,12 @@ static ssize_t applesmc_key_count_show(struct device *dev,
 	u32 count;
 
 	ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4);
-	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
-						((u32)buffer[2]<<8) + buffer[3];
-
 	if (ret)
 		return ret;
-	else
-		return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
+
+	count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) +
+						((u32)buffer[2]<<8) + buffer[3];
+	return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count);
 }
 
 static ssize_t applesmc_key_at_index_read_show(struct device *dev,

index 96ea6c76be6e5..63b87a8472762 100644
@@ -205,6 +205,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 

@@ -214,6 +217,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 
 static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
+	if (unlikely(ctrl->kato == 0))
+		return;
+
 	pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid);
 
 	cancel_delayed_work_sync(&ctrl->ka_work);

index e7ddb23d9bb73..e818344a052cb 100644
@@ -1773,6 +1773,7 @@ const struct file_operations ceph_file_fops = {
 	.mmap = ceph_mmap,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
+	.setlease = simple_nosetlease,
 	.flock = ceph_flock,
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl = ceph_ioctl,

index 90240dfef76a1..5889c1ed84c46 100644
@@ -28,7 +28,7 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\

@@ -36,7 +36,7 @@
 		new__ = old__ op (val);					\
 		prev__ = cmpxchg(ptr__, old__, new__);			\
 	} while (prev__ != old__);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	new__;								\
 })
 

@@ -67,7 +67,7 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\

@@ -83,7 +83,7 @@
 			: [val__] "d" (val__)				\
 			: "cc");					\
 	}								\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)

@@ -94,14 +94,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 

@@ -113,14 +113,14 @@
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_and_4(pcp, val)	arch_this_cpu_to_op(pcp, val, "lan")

@@ -135,10 +135,10 @@
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 

@@ -151,10 +151,10 @@
 ({									\
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 

@@ -170,11 +170,11 @@
 	typeof(pcp1) *p1__;						\
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	p1__ = raw_cpu_ptr(&(pcp1));					\
 	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 

index df27cefb2fa35..266f446ba331c 100644
@@ -384,8 +384,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 	int i, j;
 
 	for (i = 0; i < nr_pages; i++) {
-		err = gnttab_grant_foreign_access(dev->otherend_id,
-						  virt_to_gfn(vaddr), 0);
+		unsigned long gfn;
+
+		if (is_vmalloc_addr(vaddr))
+			gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr));
+		else
+			gfn = virt_to_gfn(vaddr);
+
+		err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "granting access to ring page");

index faae0bfe1109e..757cf48c1c5ed 100644
@@ -72,12 +72,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
-	if (chan) {
-		chan->router = ofdma->dma_router;
-		chan->route_data = route_data;
-	} else {
+	if (IS_ERR_OR_NULL(chan)) {
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
+	} else {
+		chan->router = ofdma->dma_router;
+		chan->route_data = route_data;
 	}
 
 	/*

index 3bd7ed6b6b3e1..9727afc030d8c 100644
@@ -673,8 +673,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
 
 	chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET;
 	/* store the client address if the message is going to a client */
-	if (ret == BATADV_DHCP_TO_CLIENT &&
-	    pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) {
+	if (ret == BATADV_DHCP_TO_CLIENT) {
+		if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN))
+			return BATADV_DHCP_NO;
+
 		/* check if the DHCP packet carries an Ethernet DHCP */
 		p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET;
 		if (*p != BATADV_DHCP_HTYPE_ETHERNET)

index 00123064eb26d..e545b42ab0b98 100644
@@ -451,7 +451,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac,
 			   skb->len + ETH_HLEN);
 	soft_iface->last_rx = jiffies;
 
-	netif_rx(skb);
+	if (in_interrupt())
+		netif_rx(skb);
+	else
+		netif_rx_ni(skb);
 out:
 	if (primary_if)
 		batadv_hardif_put(primary_if);

index a32cd71f94bbe..cb72b8c915c73 100644
@@ -1810,6 +1810,8 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 
 	dmac_pdev = of_find_device_by_node(dma_spec->np);
+	if (!dmac_pdev)
+		return NULL;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);

index 0ff379f0cc4a7..cb877f86f5fc9 100644
@@ -1746,7 +1746,11 @@ static void setup_scache(void)
 				printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n",
 				       scache_size >> 10,
 				       way_string[c->scache.ways], c->scache.linesz);
+
+				if (current_cpu_type() == CPU_BMIPS5000)
+					c->options |= MIPS_CPU_INCLUSIVE_CACHES;
 			}
+
 #else
 			if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT))
 				panic("Dunno how to handle MIPS32 / MIPS64 second level cache");

index 416d53f587e7c..6e36717527754 100644
@@ -236,6 +236,8 @@ static void bmips_boot_secondary(int cpu, struct task_struct *idle)
  */
 static void bmips_init_secondary(void)
 {
+	bmips_cpu_setup();
+
 	switch (current_cpu_type()) {
 	case CPU_BMIPS4350:
 	case CPU_BMIPS4380:

index 2fa1c4f2e94e0..ec460aedfc617 100644
@@ -2592,7 +2592,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
-	if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
+	if (set->udata &&
+	    nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
 		goto nla_put_failure;
 
 	desc = nla_nest_start(skb, NFTA_SET_DESC);

index c6c4477c136b9..d121c22bf9284 100644
@@ -114,7 +114,7 @@ enum nf_tables_msg_types {
  * @NFTA_LIST_ELEM: list element (NLA_NESTED)
  */
 enum nft_list_attributes {
-	NFTA_LIST_UNPEC,
+	NFTA_LIST_UNSPEC,
 	NFTA_LIST_ELEM,
 	__NFTA_LIST_MAX
 };

index 7ba9a624090fb..91e395fd0a65c 100644
@@ -119,6 +119,8 @@ static inline u8 nft_reg_load8(u32 *sreg)
 static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
 				 unsigned int len)
 {
+	if (len % NFT_REG32_SIZE)
+		dst[len / NFT_REG32_SIZE] = 0;
 	memcpy(dst, src, len);
 }
 

index b2f88617611aa..f73d47b3ffb72 100644
@@ -74,7 +74,9 @@ static void nft_payload_eval(const struct nft_expr *expr,
 	u32 *dest = &regs->data[priv->dreg];
 	int offset;
 
-	dest[priv->len / NFT_REG32_SIZE] = 0;
+	if (priv->len % NFT_REG32_SIZE)
+		dest[priv->len / NFT_REG32_SIZE] = 0;
+
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
 		if (!skb_mac_header_was_set(skb))

index 24a815997ec57..796f81106b432 100644
@@ -1990,8 +1990,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			priv->enet_ver = AE_VERSION_1;
 		else if (acpi_dev_found(hns_enet_acpi_match[1].id))
 			priv->enet_ver = AE_VERSION_2;
-		else
-			return -ENXIO;
+		else {
+			ret = -ENXIO;
+			goto out_read_prop_fail;
+		}
 
 		/* try to find port-idx-in-ae first */
 		ret = acpi_node_get_property_reference(dev->fwnode,

@@ -2003,7 +2005,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		priv->fwnode = acpi_fwnode_handle(args.adev);
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto out_read_prop_fail;
 	}
 
 	ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id);

index 93d3152752ff4..a5de56bcbac08 100644
@@ -1336,6 +1336,51 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler,
 	return error;
 }
 
+/* MDIO bus init function */
+static int ravb_mdio_init(struct ravb_private *priv)
+{
+	struct platform_device *pdev = priv->pdev;
+	struct device *dev = &pdev->dev;
+	int error;
+
+	/* Bitbang init */
+	priv->mdiobb.ops = &bb_ops;
+
+	/* MII controller setting */
+	priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
+	if (!priv->mii_bus)
+		return -ENOMEM;
+
+	/* Hook up MII support for ethtool */
+	priv->mii_bus->name = "ravb_mii";
+	priv->mii_bus->parent = dev;
+	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+		 pdev->name, pdev->id);
+
+	/* Register MDIO bus */
+	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+	if (error)
+		goto out_free_bus;
+
+	return 0;
+
+out_free_bus:
+	free_mdio_bitbang(priv->mii_bus);
+	return error;
+}
+
+/* MDIO bus release function */
+static int ravb_mdio_release(struct ravb_private *priv)
+{
+	/* Unregister mdio bus */
+	mdiobus_unregister(priv->mii_bus);
+
+	/* Free bitbang info */
+	free_mdio_bitbang(priv->mii_bus);
+
+	return 0;
+}
+
 /* Network device open function for Ethernet AVB */
 static int ravb_open(struct net_device *ndev)
 {

@@ -1344,6 +1389,13 @@ static int ravb_open(struct net_device *ndev)
 	struct device *dev = &pdev->dev;
 	int error;
 
+	/* MDIO bus init */
+	error = ravb_mdio_init(priv);
+	if (error) {
+		netdev_err(ndev, "failed to initialize MDIO\n");
+		return error;
+	}
+
 	napi_enable(&priv->napi[RAVB_BE]);
 	napi_enable(&priv->napi[RAVB_NC]);
 

@@ -1421,6 +1473,7 @@ out_free_irq:
 out_napi_off:
 	napi_disable(&priv->napi[RAVB_NC]);
 	napi_disable(&priv->napi[RAVB_BE]);
+	ravb_mdio_release(priv);
 	return error;
 }
 

@@ -1718,6 +1771,8 @@ static int ravb_close(struct net_device *ndev)
 	ravb_ring_free(ndev, RAVB_BE);
 	ravb_ring_free(ndev, RAVB_NC);
 
+	ravb_mdio_release(priv);
+
 	return 0;
 }
 

@@ -1820,51 +1875,6 @@ static const struct net_device_ops ravb_netdev_ops = {
 	.ndo_change_mtu		= eth_change_mtu,
 };
 
-/* MDIO bus init function */
-static int ravb_mdio_init(struct ravb_private *priv)
-{
-	struct platform_device *pdev = priv->pdev;
-	struct device *dev = &pdev->dev;
-	int error;
-
-	/* Bitbang init */
-	priv->mdiobb.ops = &bb_ops;
-
-	/* MII controller setting */
-	priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
-	if (!priv->mii_bus)
-		return -ENOMEM;
-
-	/* Hook up MII support for ethtool */
-	priv->mii_bus->name = "ravb_mii";
-	priv->mii_bus->parent = dev;
-	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
-		 pdev->name, pdev->id);
-
-	/* Register MDIO bus */
-	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
-	if (error)
-		goto out_free_bus;
-
-	return 0;
-
-out_free_bus:
-	free_mdio_bitbang(priv->mii_bus);
-	return error;
-}
-
-/* MDIO bus release function */
-static int ravb_mdio_release(struct ravb_private *priv)
-{
-	/* Unregister mdio bus */
-	mdiobus_unregister(priv->mii_bus);
-
-	/* Free bitbang info */
-	free_mdio_bitbang(priv->mii_bus);
-
-	return 0;
-}
-
 static const struct of_device_id ravb_match_table[] = {
 	{ .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 },
 	{ .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 },

@@ -2069,13 +2079,6 @@ static int ravb_probe(struct platform_device *pdev)
 		eth_hw_addr_random(ndev);
 	}
 
-	/* MDIO bus init */
-	error = ravb_mdio_init(priv);
-	if (error) {
-		dev_err(&pdev->dev, "failed to initialize MDIO\n");
-		goto out_dma_free;
-	}
-
 	netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64);
 	netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64);
 

@@ -2095,8 +2098,6 @@ static int ravb_probe(struct platform_device *pdev)
 out_napi_del:
 	netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
-	ravb_mdio_release(priv);
-out_dma_free:
 	dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
 			  priv->desc_bat_dma);
 

@@ -2129,7 +2130,6 @@ static int ravb_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 	netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
-	ravb_mdio_release(priv);
 	pm_runtime_disable(&pdev->dev);
 	free_netdev(ndev);
 	platform_set_drvdata(pdev, NULL);

index a22403c688c95..337cfce78aef2 100644
@@ -152,6 +152,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv)
 	if (IS_ERR(data->reset_gpio)) {
 		error = PTR_ERR(data->reset_gpio);
 		dev_err(priv->dev, "Failed to request gpio: %d\n", error);
+		mdiobus_free(bus);
 		return error;
 	}
 

index 57b375d0de292..16c08846ea0e1 100644
@@ -2677,6 +2677,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	while (burst != (1 << desc->rqcfg.brst_size))
 		desc->rqcfg.brst_size++;
 
+	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	/*
 	 * If burst size is smaller than bus width then make sure we only
 	 * transfer one at a time to avoid a burst stradling an MFIFO entry.

@@ -2684,7 +2685,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width)
 		desc->rqcfg.brst_len = 1;
 
-	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;

index 427d4dbc97354..ac03bba10e4fd 100644
@@ -1457,6 +1457,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data)
 	if (rc != 0)
 		return rc;
 
+	if (!dir_entries || !entry_length)
+		return -EIO;
+
 	/* Insert 2 bytes of directory info (count and size of entries) */
 	if (len < 2)
 		return -EINVAL;

index 421cbba9a3bc8..f451be63ab7e6 100644
@@ -7085,6 +7085,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_parse_log_pcie_link(bp);
 
+	pci_save_state(pdev);
 	return 0;
 
 init_err:

@@ -7158,6 +7159,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 			"Cannot re-enable PCI device after reset.\n");
 	} else {
 		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
 
 		if (netif_running(netdev))
 			err = bnxt_open(netdev);

index aad52e1858363..8c40d6652a9a9 100644
@@ -1748,9 +1748,9 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 			 * during ep_insert().
 			 */
 			if (list_empty(&epi->ffd.file->f_tfile_llink)) {
-				get_file(epi->ffd.file);
-				list_add(&epi->ffd.file->f_tfile_llink,
-					 &tfile_check_list);
+				if (get_file_rcu(epi->ffd.file))
+					list_add(&epi->ffd.file->f_tfile_llink,
+						 &tfile_check_list);
 			}
 		}
 	}

index 5790b35064a8d..2db6102ed5848 100644
@@ -7201,8 +7201,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp)
 
 static inline void tg3_reset_task_cancel(struct tg3 *tp)
 {
-	cancel_work_sync(&tp->reset_task);
-	tg3_flag_clear(tp, RESET_TASK_PENDING);
+	if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags))
+		cancel_work_sync(&tp->reset_task);
 	tg3_flag_clear(tp, TX_RECOVERY_PENDING);
 }
 

@@ -11174,18 +11174,27 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 0);
 	err = tg3_init_hw(tp, true);
-	if (err)
+	if (err) {
+		tg3_full_unlock(tp);
+		tp->irq_sync = 0;
+		tg3_napi_enable(tp);
+		/* Clear this flag so that tg3_reset_task_cancel() will not
+		 * call cancel_work_sync() and wait forever.
+		 */
+		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		dev_close(tp->dev);
 		goto out;
+	}
 
 	tg3_netif_start(tp);
 
-out:
 	tg3_full_unlock(tp);
 
 	if (!err)
 		tg3_phy_start(tp);
 
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
+out:
 	rtnl_unlock();
 }
 

index ac596928f6b40..ce125ec23d2a5 100644
@@ -486,12 +486,18 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
 
 	/* Enable interrupt-remapping */
 	iommu->gcmd |= DMA_GCMD_IRE;
-	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
-
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRES), sts);
 
+	/* Block compatibility-format MSIs */
+	if (sts & DMA_GSTS_CFIS) {
+		iommu->gcmd &= ~DMA_GCMD_CFI;
+		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, !(sts & DMA_GSTS_CFIS), sts);
+	}
+
 	/*
 	 * With CFI clear in the Global Command register, we should be
 	 * protected from dangerous (i.e. compatibility) interrupts

index d255d33da9eb3..02e71d461d5c5 100644
@@ -49,20 +49,21 @@ static struct temp_sensor_data omap4430_mpu_temp_sensor_data = {
 
 /*
  * Temperature values in milli degree celsius
- * ADC code values from 530 to 923
+ * ADC code values from 13 to 107, see TRM
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
  */
 static const int
 omap4430_adc_to_temp[OMAP4430_ADC_END_VALUE - OMAP4430_ADC_START_VALUE + 1] = {
-	-38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, -22000,
-	-20000, -18000, -17000, -15000, -13000, -12000, -10000, -8000, -6000,
-	-5000, -3000, -1000, 0, 2000, 3000, 5000, 6000, 8000, 10000, 12000,
-	13000, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28000, 30000,
-	32000, 33000, 35000, 37000, 38000, 40000, 42000, 43000, 45000, 47000,
-	48000, 50000, 52000, 53000, 55000, 57000, 58000, 60000, 62000, 64000,
-	66000, 68000, 70000, 71000, 73000, 75000, 77000, 78000, 80000, 82000,
-	83000, 85000, 87000, 88000, 90000, 92000, 93000, 95000, 97000, 98000,
-	100000, 102000, 103000, 105000, 107000, 109000, 111000, 113000, 115000,
-	117000, 118000, 120000, 122000, 123000,
+	-40000, -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000,
+	-22000,	-20000, -18500, -17000, -15000, -13500, -12000, -10000, -8000,
+	-6500, -5000, -3500, -1500, 0, 2000, 3500, 5000, 6500, 8500, 10000,
+	12000, 13500, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28500,
+	30000, 32000, 33500, 35000, 37000, 38500, 40000, 42000, 43500, 45000,
+	47000, 48500, 50000, 52000, 53500, 55000, 57000, 58500, 60000, 62000,
+	64000, 66000, 68000, 70000, 71500, 73500, 75000, 77000, 78500, 80000,
+	82000, 83500, 85000, 87000, 88500, 90000, 92000, 93500, 95000, 97000,
+	98500, 100000, 102000, 103500, 105000, 107000, 109000, 111000, 113000,
+	115000, 117000, 118500, 120000, 122000, 123500, 125000,
 };
 
 /* OMAP4430 data */

index 6f2de3a3356d4..86850082b24b9 100644
@@ -67,9 +67,13 @@
  * and thresholds for OMAP4430.
  */
 
-/* ADC conversion table limits */
-#define OMAP4430_ADC_START_VALUE			0
-#define OMAP4430_ADC_END_VALUE				127
+/*
+ * ADC conversion table limits. Ignore values outside the TRM listed
+ * range to avoid bogus thermal shutdowns. See omap4430 TRM chapter
+ * "18.4.10.2.3 ADC Codes Versus Temperature".
+ */
+#define OMAP4430_ADC_START_VALUE			13
+#define OMAP4430_ADC_END_VALUE				107
 /* bandgap clock limits (no control on 4430) */
 #define OMAP4430_MAX_FREQ				32768
 #define OMAP4430_MIN_FREQ				32768

index c373295f359fa..cca606609e1bc 100644
@@ -159,7 +159,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define roundup_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 1 :			\
+		((n) == 1) ? 1 :		\
 		(1UL << (ilog2((n) - 1) + 1))	\
 				   ) :		\
 	__roundup_pow_of_two(n)			\

@@ -4181,6 +4181,7 @@ static int btrfs_uuid_scan_kthread(void
 			goto skip;
 		}
 update_tree:
+		btrfs_release_path(path);
 		if (!btrfs_is_empty_uuid(root_item.uuid)) {
 			ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root,
 						  root_item.uuid,

@@ -4206,6 +4207,7 @@ update_tree:
 		}
 
 skip:
+		btrfs_release_path(path);
 		if (trans) {
 			ret = btrfs_end_transaction(trans, fs_info->uuid_root);
 			trans = NULL;

@@ -4213,7 +4215,6 @@ skip:
 				break;
 		}
 
-		btrfs_release_path(path);
 		if (key.offset < (u64)-1) {
 			key.offset++;
 		} else if (key.type < BTRFS_ROOT_ITEM_KEY) {

index b5ebb43b1824f..78d4c8c22b4ac 100644
@@ -1430,7 +1430,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 
 	if (!eb)
 		return NULL;
-	extent_buffer_get(eb);
 	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);

index 78d4c8c22b4ac..406ae49baa076 100644
@@ -1360,7 +1360,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	btrfs_tree_read_unlock_blocking(eb);
 	free_extent_buffer(eb);
 
-	extent_buffer_get(eb_rewin);
 	btrfs_tree_read_lock(eb_rewin);
 	__tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
 	WARN_ON(btrfs_header_nritems(eb_rewin) >

index 406ae49baa076..65689cbc362db 100644
@@ -1360,6 +1360,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	btrfs_tree_read_unlock_blocking(eb);
 	free_extent_buffer(eb);
 
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
+				       eb_rewin, btrfs_header_level(eb_rewin));
 	btrfs_tree_read_lock(eb_rewin);
 	__tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
 	WARN_ON(btrfs_header_nritems(eb_rewin) >

@@ -1429,7 +1431,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 
 	if (!eb)
 		return NULL;
-	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);
 		btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);

@@ -1437,6 +1438,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		btrfs_set_header_level(eb, old_root->level);
 		btrfs_set_header_generation(eb, old_generation);
 	}
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
+				       btrfs_header_level(eb));
+	btrfs_tree_read_lock(eb);
 	if (tm)
 		__tree_mod_log_rewind(root->fs_info, eb, time_seq, tm);
 	else

index 9442423979c1c..6d27d58ca4e04 100644
@@ -90,6 +90,17 @@ static inline unsigned long __copy_from_user_nocache(void *to,
 extern long probe_kernel_read(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
+/*
+ * probe_user_read(): safely attempt to read from a location in user space
+ * @dst: pointer to the buffer that shall take the data
+ * @src: address to read from
+ * @size: size of the data chunk
+ *
+ * Safely read from address @src to the buffer at @dst.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long probe_user_read(void *dst, const void __user *src, size_t size);
+
 /*
  * probe_kernel_write(): safely attempt to write to a location
  * @dst: address to write to

@@ -103,6 +114,9 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
 extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
+				     long count);
+extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
 
 /**
  * probe_kernel_address(): safely attempt to read from a location

149 lines not on this page · raw message

index 6d27d58ca4e04..cc5ba47062e87 100644
@@ -113,6 +113,18 @@ extern long probe_user_read(void *dst, const void __user *src, size_t size);
 extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
 extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
+/*
+ * probe_user_write(): safely attempt to write to a location in user space
+ * @dst: address to write to
+ * @src: pointer to the data that shall be written
+ * @size: size of the data chunk
+ *
+ * Safely write to address @dst from the buffer at @src.  If a kernel fault
+ * happens, handle that and return -EFAULT.
+ */
+extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
+
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
 				     long count);

68 lines not on this page · raw message

index fa22bb29eee6f..d6c827a9ebc56 100644
@@ -5488,9 +5488,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 	}
 }
 
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dstv,
-			       unsigned long start, unsigned long len)
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dstv,
+				       unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;

@@ -5511,7 +5511,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb,
 
 		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
-		if (copy_to_user(dst, kaddr + offset, cur)) {
+		if (probe_user_write(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
 			break;
 		}

index 9ecdc9584df77..75c03aa1800fe 100644
@@ -401,9 +401,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dst, unsigned long start,
-			       unsigned long len);
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dst, unsigned long start,
+				       unsigned long len);
 void write_extent_buffer(struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
 void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,

index eefe103c65daa..6db46daeed16b 100644
@@ -2041,9 +2041,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 		sh.len = item_len;
 		sh.transid = found_transid;
 
-		/* copy search result header */
-		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
-			ret = -EFAULT;
+		/*
+		 * Copy search result header. If we fault then loop again so we
+		 * can fault in the pages and -EFAULT there if there's a
+		 * problem. Otherwise we'll fault and then copy the buffer in
+		 * properly this next time through
+		 */
+		if (probe_user_write(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = 0;
 			goto out;
 		}
 

@@ -2051,10 +2056,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 
 		if (item_len) {
 			char __user *up = ubuf + *sk_offset;
-			/* copy the item */
-			if (read_extent_buffer_to_user(leaf, up,
-						       item_off, item_len)) {
-				ret = -EFAULT;
+			/*
+			 * Copy the item, same behavior as above, but reset the
+			 * * sk_offset so we copy the full thing again.
+			 */
+			if (read_extent_buffer_to_user_nofault(leaf, up,
+						item_off, item_len)) {
+				ret = 0;
+				*sk_offset -= sizeof(sh);
 				goto out;
 			}
 

@@ -2142,6 +2151,10 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
+		ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset);
+		if (ret)
+			break;
+
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);
 		if (ret != 0) {
 			if (ret > 0)

index 254a27295f41d..97a83d351a100 100644
@@ -923,6 +923,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */

index 97a83d351a100..6104500314d18 100644
@@ -927,7 +927,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
-	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */

index 6104500314d18..d812335600212 100644
@@ -910,6 +910,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9063, 8)},	/* Sierra Wireless EM7305 */
+	{QMI_FIXED_INTF(0x1199, 0x9063, 10)},	/* Sierra Wireless EM7305 */
 	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */

@@ -928,6 +930,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)},	/* Telewell TW-3G HSPA+ */
+	{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */

index d812335600212..74c925cd19a93 100644
@@ -890,6 +890,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2001, 0x7e3d, 4)},	/* D-Link DWM-222 A2 */
 	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x2020, 0x2060, 4)},	/* BroadMobi BM818 */

@@ -551,7 +551,8 @@ static int snd_ca0106_pcm_power_dac(stru
 		else
 			/* Power down */
 			chip->spi_dac_reg[reg] |= bit;
-		return snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]);
+		if (snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]) != 0)
+			return -ENXIO;
 	}
 	return 0;
 }

@@ -329,8 +329,8 @@ int snd_pcm_plugin_build_mulaw(struct sn
 		snd_BUG();
 		return -EINVAL;
 	}
-	if (snd_BUG_ON(!snd_pcm_format_linear(format->format)))
-		return -ENXIO;
+	if (!snd_pcm_format_linear(format->format))
+		return -EINVAL;
 
 	err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion",
 				   src_format, dst_format,

@@ -15,6 +15,7 @@ MODULE_LICENSE("GPL v2");
 #define VENDOR_DIGIDESIGN	0x00a07e
 #define MODEL_CONSOLE		0x000001
 #define MODEL_RACK		0x000002
+#define SPEC_VERSION		0x000001
 
 static int name_card(struct snd_dg00x *dg00x)
 {

@@ -185,14 +186,18 @@ static const struct ieee1394_device_id s
 	/* Both of 002/003 use the same ID. */
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_CONSOLE,
 	},
 	{
 		.match_flags = IEEE1394_MATCH_VENDOR_ID |
+			       IEEE1394_MATCH_VERSION |
 			       IEEE1394_MATCH_MODEL_ID,
 		.vendor_id = VENDOR_DIGIDESIGN,
+		.version = SPEC_VERSION,
 		.model_id = MODEL_RACK,
 	},
 	{}

@@ -88,10 +88,17 @@ static inline void bvec_iter_advance(con
 	}
 }
 
+static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter)
+{
+	iter->bi_bvec_done = 0;
+	iter->bi_idx++;
+}
+
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
-	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
+	     (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter),	\
+		     (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter)))
 
 #endif /* __LINUX_BVEC_ITER_H */

@@ -21,7 +21,6 @@
 #include <platform/simcall.h>
 
 #define SIMDISK_MAJOR 240
-#define SECTOR_SHIFT 9
 #define SIMDISK_MINORS 1
 #define MAX_SIMDISK_COUNT 10
 

@@ -25,7 +25,6 @@
 
 #include <asm/uaccess.h>
 
-#define SECTOR_SHIFT		9
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
 

@@ -51,15 +51,6 @@
 #define RBD_DEBUG	/* Activate rbd_assert() calls */
 
 /*
- * The basic unit of block I/O is a sector.  It is interpreted in a
- * number of contexts in Linux (blk, bio, genhd), but the default is
- * universally 512 bytes.  These symbols are just slightly more
- * meaningful than the bare numbers they represent.
- */
-#define	SECTOR_SHIFT	9
-#define	SECTOR_SIZE	(1ULL << SECTOR_SHIFT)
-
-/*
  * Increment the given counter and return its updated value.
  * If the counter is already 0 it will not be incremented.
  * If the counter is already at its maximum value returns

@@ -37,7 +37,6 @@ static const size_t max_zpage_size = PAG
 
 /*-- End of configurable params */
 
-#define SECTOR_SHIFT		9
 #define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
 #define ZRAM_LOGICAL_BLOCK_SHIFT 12

@@ -704,7 +704,7 @@ static ide_startstop_t cdrom_start_rw(id
 	struct request_queue *q = drive->queue;
 	int write = rq_data_dir(rq) == WRITE;
 	unsigned short sectors_per_frame =
-		queue_logical_block_size(q) >> SECTOR_BITS;
+		queue_logical_block_size(q) >> SECTOR_SHIFT;
 
 	ide_debug_log(IDE_DBG_RQ, "rq->cmd[0]: 0x%x, rq->cmd_flags: 0x%x, "
 				  "secs_per_frame: %u",

@@ -900,7 +900,7 @@ static int cdrom_read_capacity(ide_drive
 	 * end up being bogus.
 	 */
 	blocklen = be32_to_cpu(capbuf.blocklen);
-	blocklen = (blocklen >> SECTOR_BITS) << SECTOR_BITS;
+	blocklen = (blocklen >> SECTOR_SHIFT) << SECTOR_SHIFT;
 	switch (blocklen) {
 	case 512:
 	case 1024:

@@ -916,7 +916,7 @@ static int cdrom_read_capacity(ide_drive
 	}
 
 	*capacity = 1 + be32_to_cpu(capbuf.lba);
-	*sectors_per_frame = blocklen >> SECTOR_BITS;
+	*sectors_per_frame = blocklen >> SECTOR_SHIFT;
 
 	ide_debug_log(IDE_DBG_PROBE, "cap: %lu, sectors_per_frame: %lu",
 				     *capacity, *sectors_per_frame);

@@ -993,7 +993,7 @@ int ide_cd_read_toc(ide_drive_t *drive,
 	drive->probed_capacity = toc->capacity * sectors_per_frame;
 
 	blk_queue_logical_block_size(drive->queue,
-				     sectors_per_frame << SECTOR_BITS);
+				     sectors_per_frame << SECTOR_SHIFT);
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,

@@ -20,11 +20,7 @@
 
 /************************************************************************/
 
-#define SECTOR_BITS 		9
-#ifndef SECTOR_SIZE
-#define SECTOR_SIZE		(1 << SECTOR_BITS)
-#endif
-#define SECTORS_PER_FRAME	(CD_FRAMESIZE >> SECTOR_BITS)
+#define SECTORS_PER_FRAME	(CD_FRAMESIZE >> SECTOR_SHIFT)
 #define SECTOR_BUFFER_SIZE	(CD_FRAMESIZE * 32)
 
 /* Capabilities Page size including 8 bytes of Mode Page Header */

@@ -29,7 +29,6 @@ enum {
 	 * BTT instance
 	 */
 	ND_MAX_LANES = 256,
-	SECTOR_SHIFT = 9,
 	INT_LBASIZE_ALIGNMENT = 64,
 };
 

@@ -177,9 +177,6 @@
 #define MSG_SIZE        34                      /* size of message structure */
 #define MSG_REQUEST     0                       /* async. event: message */
 
-/* cacheservice defines */
-#define SECTOR_SIZE     0x200                   /* always 512 bytes per sec. */
-
 /* DPMEM constants */
 #define DPMEM_MAGIC     0xC0FFEE11
 #define IC_HEADER_BYTES 48

94 lines not on this page · raw message

@@ -576,8 +576,6 @@ extern struct ratelimit_state dm_ratelim
 #define DMEMIT(x...) sz += ((sz >= maxlen) ? \
 			  0 : scnprintf(result + sz, maxlen - sz, x))
 
-#define SECTOR_SHIFT 9
-
 /*
  * Definitions of return values from target end_io function.
  */

@@ -128,7 +128,6 @@ struct ide_io_ports {
  */
 #define PARTN_BITS	6	/* number of minor dev bits for partitions */
 #define MAX_DRIVES	2	/* per interface; 2 assumed by lots of code */
-#define SECTOR_SIZE	512
 
 /*
  * Timeouts for various operations:

@@ -9,7 +9,9 @@
  * The MS-DOS filesystem constants/structures
  */
 
+#ifndef SECTOR_SIZE
 #define SECTOR_SIZE	512		/* sector size (bytes) */
+#endif
 #define SECTOR_BITS	9		/* log2(SECTOR_SIZE) */
 #define MSDOS_DPB	(MSDOS_DPS)	/* dir entries per block */
 #define MSDOS_DPB_BITS	4		/* log2(MSDOS_DPB) */

@@ -4371,9 +4371,8 @@ static const struct ata_blacklist_entry
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */
 	{ "C300-CTFDDAC128MAG",	"0001",		ATA_HORKAGE_NONCQ, },
 
-	/* Some Sandisk SSDs lock up hard with NCQ enabled.  Reported on
-	   SD7SN6S256G and SD8SN8U256G */
-	{ "SanDisk SD[78]SN*G",	NULL,		ATA_HORKAGE_NONCQ, },
+	/* Sandisk SD7/8/9s lock up hard on large trims */
+	{ "SanDisk SD[789]*",	NULL,		ATA_HORKAGE_MAX_TRIM_128M, },
 
 	/* devices which puke on READ_NATIVE_MAX */
 	{ "HDS724040KLSA80",	"KFAOA20N",	ATA_HORKAGE_BROKEN_HPA, },

@@ -2314,6 +2314,7 @@ static unsigned int ata_scsiop_inq_89(st
 
 static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 {
+	struct ata_device *dev = args->dev;
 	u16 min_io_sectors;
 
 	rbuf[1] = 0xb0;

@@ -2339,7 +2340,12 @@ static unsigned int ata_scsiop_inq_b0(st
 	 * with the unmap bit set.
 	 */
 	if (ata_id_has_trim(args->id)) {
-		put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]);
+		u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM;
+
+		if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M)
+			max_blocks = 128 << (20 - SECTOR_SHIFT);
+
+		put_unaligned_be64(max_blocks, &rbuf[36]);
 		put_unaligned_be32(1, &rbuf[28]);
 	}
 

@@ -435,6 +435,7 @@ enum {
 	ATA_HORKAGE_NO_NCQ_LOG	= (1 << 23),	/* don't use NCQ for log read */
 	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
 	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
+	ATA_HORKAGE_MAX_TRIM_128M = (1 << 26),	/* Limit max trim size to 128M */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */

@@ -508,12 +508,16 @@ static int __create_persistent_data_obje
 					  CACHE_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(cmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(cmd->bm);
+		r = PTR_ERR(cmd->bm);
+		cmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(cmd, may_format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(cmd->bm);
+		cmd->bm = NULL;
+	}
 
 	return r;
 }

@@ -700,12 +700,16 @@ static int __create_persistent_data_obje
 					  THIN_MAX_CONCURRENT_LOCKS);
 	if (IS_ERR(pmd->bm)) {
 		DMERR("could not create block manager");
-		return PTR_ERR(pmd->bm);
+		r = PTR_ERR(pmd->bm);
+		pmd->bm = NULL;
+		return r;
 	}
 
 	r = __open_or_format_metadata(pmd, format_device);
-	if (r)
+	if (r) {
 		dm_block_manager_destroy(pmd->bm);
+		pmd->bm = NULL;
+	}
 
 	return r;
 }

@@ -625,12 +625,12 @@ static void slab_fix(struct kmem_cache *
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
-	    !check_valid_pointer(s, page, nextfree)) {
-		object_err(s, page, freelist, "Freechain corrupt");
-		freelist = NULL;
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
 		slab_fix(s, "Isolate corrupted freechain");
 		return true;
 	}

@@ -1320,7 +1320,7 @@ static inline void dec_slabs_node(struct
 							int objects) {}
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	return false;
 }

@@ -2040,7 +2040,7 @@ static void deactivate_slab(struct kmem_
 		 * 'freelist' is already corrupted.  So isolate all objects
 		 * starting at 'freelist'.
 		 */
-		if (freelist_corrupted(s, page, freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist, nextfree))
 			break;
 
 		do {

@@ -213,6 +213,32 @@ static int put_pfn(unsigned long pfn, in
 	return 0;
 }
 
+static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm,
+			    unsigned long vaddr, unsigned long *pfn,
+			    bool write_fault)
+{
+	int ret;
+
+	ret = follow_pfn(vma, vaddr, pfn);
+	if (ret) {
+		bool unlocked = false;
+
+		ret = fixup_user_fault(NULL, mm, vaddr,
+				       FAULT_FLAG_REMOTE |
+				       (write_fault ?  FAULT_FLAG_WRITE : 0),
+				       &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+
+		if (ret)
+			return ret;
+
+		ret = follow_pfn(vma, vaddr, pfn);
+	}
+
+	return ret;
+}
+
 static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
 {
 	struct page *page[1];

@@ -226,12 +252,16 @@ static int vaddr_get_pfn(unsigned long v
 
 	down_read(&current->mm->mmap_sem);
 
+retry:
 	vma = find_vma_intersection(current->mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		if (!follow_pfn(vma, vaddr, pfn) &&
-		    is_invalid_reserved_pfn(*pfn))
-			ret = 0;
+		ret = follow_fault_pfn(vma, current->mm, vaddr, pfn, prot & IOMMU_WRITE);
+		if (ret == -EAGAIN)
+			goto retry;
+
+		if (!ret && !is_invalid_reserved_pfn(*pfn))
+			ret = -EFAULT;
 	}
 
 	up_read(&current->mm->mmap_sem);

@@ -1144,6 +1144,69 @@ static ssize_t vfio_pci_write(void *devi
 	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
+static int vfio_pci_add_vma(struct vfio_pci_device *vdev,
+			    struct vm_area_struct *vma)
+{
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);
+	if (!mmap_vma)
+		return -ENOMEM;
+
+	mmap_vma->vma = vma;
+
+	mutex_lock(&vdev->vma_lock);
+	list_add(&mmap_vma->vma_next, &vdev->vma_list);
+	mutex_unlock(&vdev->vma_lock);
+
+	return 0;
+}
+
+/*
+ * Zap mmaps on open so that we can fault them in on access and therefore
+ * our vma_list only tracks mappings accessed since last zap.
+ */
+static void vfio_pci_mmap_open(struct vm_area_struct *vma)
+{
+	zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start);
+}
+
+static void vfio_pci_mmap_close(struct vm_area_struct *vma)
+{
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+	struct vfio_pci_mmap_vma *mmap_vma;
+
+	mutex_lock(&vdev->vma_lock);
+	list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) {
+		if (mmap_vma->vma == vma) {
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			break;
+		}
+	}
+	mutex_unlock(&vdev->vma_lock);
+}
+
+static int vfio_pci_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct vfio_pci_device *vdev = vma->vm_private_data;
+
+	if (vfio_pci_add_vma(vdev, vma))
+		return VM_FAULT_OOM;
+
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static const struct vm_operations_struct vfio_pci_mmap_ops = {
+	.open = vfio_pci_mmap_open,
+	.close = vfio_pci_mmap_close,
+	.fault = vfio_pci_mmap_fault,
+};
+
 static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 {
 	struct vfio_pci_device *vdev = device_data;

@@ -1209,8 +1272,14 @@ static int vfio_pci_mmap(void *device_da
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
-	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-			       req_len, vma->vm_page_prot);
+	/*
+	 * See remap_pfn_range(), called from vfio_pci_fault() but we can't
+	 * change vm_flags within the fault handler.  Set them now.
+	 */
+	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_ops = &vfio_pci_mmap_ops;
+
+	return 0;
 }
 
 static void vfio_pci_request(void *device_data, unsigned int count)

@@ -1268,6 +1337,8 @@ static int vfio_pci_probe(struct pci_dev
 	mutex_init(&vdev->igate);
 	spin_lock_init(&vdev->irqlock);
 
+	mutex_init(&vdev->vma_lock);
+	INIT_LIST_HEAD(&vdev->vma_list);
 	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
 	if (ret) {
 		vfio_iommu_group_put(group, &pdev->dev);

@@ -63,6 +63,11 @@ struct vfio_pci_dummy_resource {
 	struct list_head	res_next;
 };
 
+struct vfio_pci_mmap_vma {
+	struct vm_area_struct	*vma;
+	struct list_head	vma_next;
+};
+
 struct vfio_pci_device {
 	struct pci_dev		*pdev;
 	void __iomem		*barmap[PCI_STD_RESOURCE_END + 1];

@@ -95,6 +100,8 @@ struct vfio_pci_device {
 	struct eventfd_ctx	*err_trigger;
 	struct eventfd_ctx	*req_trigger;
 	struct list_head	dummy_resources_list;
+	struct mutex		vma_lock;
+	struct list_head	vma_list;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)

@@ -29,6 +29,7 @@
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
 #include <linux/nospec.h>
+#include <linux/mm.h>
 
 #include "vfio_pci_private.h"
 

@@ -181,6 +182,7 @@ no_mmap:
 
 static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
 static void vfio_pci_disable(struct vfio_pci_device *vdev);
+static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
 
 /*
  * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND

@@ -656,6 +658,12 @@ int vfio_pci_register_dev_region(struct
 	return 0;
 }
 
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {

@@ -729,7 +737,7 @@ static long vfio_pci_ioctl(void *device_
 		{
 			void __iomem *io;
 			size_t size;
-			u16 orig_cmd;
+			u16 cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;

@@ -749,10 +757,7 @@ static long vfio_pci_ioctl(void *device_
 			 * Is it really there?  Enable memory decode for
 			 * implicit access in pci_map_rom().
 			 */
-			pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
-			pci_write_config_word(pdev, PCI_COMMAND,
-					      orig_cmd | PCI_COMMAND_MEMORY);
-
+			cmd = vfio_pci_memory_lock_and_enable(vdev);
 			io = pci_map_rom(pdev, &size);
 			if (io) {
 				info.flags = VFIO_REGION_INFO_FLAG_READ;

@@ -760,8 +765,8 @@ static long vfio_pci_ioctl(void *device_
 			} else {
 				info.size = 0;
 			}
+			vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
-			pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
 			break;
 		}
 		case VFIO_PCI_VGA_REGION_INDEX:

@@ -909,8 +914,16 @@ static long vfio_pci_ioctl(void *device_
 		return ret;
 
 	} else if (cmd == VFIO_DEVICE_RESET) {
-		return vdev->reset_works ?
-			pci_try_reset_function(vdev->pdev) : -EINVAL;
+		int ret;
+
+		if (!vdev->reset_works)
+			return -EINVAL;
+
+		vfio_pci_zap_and_down_write_memory_lock(vdev);
+		ret = pci_try_reset_function(vdev->pdev);
+		up_write(&vdev->memory_lock);
+
+		return ret;
 
 	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
 		struct vfio_pci_hot_reset_info hdr;

@@ -990,8 +1003,9 @@ reset_info_exit:
 		int32_t *group_fds;
 		struct vfio_pci_group_entry *groups;
 		struct vfio_pci_group_info info;
+		struct vfio_devices devs = { .cur_index = 0 };
 		bool slot = false;
-		int i, count = 0, ret = 0;
+		int i, group_idx, mem_idx = 0, count = 0, ret = 0;
 
 		minsz = offsetofend(struct vfio_pci_hot_reset, count);
 

@@ -1043,9 +1057,9 @@ reset_info_exit:
 		 * user interface and store the group and iommu ID.  This
 		 * ensures the group is held across the reset.
 		 */
-		for (i = 0; i < hdr.count; i++) {
+		for (group_idx = 0; group_idx < hdr.count; group_idx++) {
 			struct vfio_group *group;
-			struct fd f = fdget(group_fds[i]);
+			struct fd f = fdget(group_fds[group_idx]);
 			if (!f.file) {
 				ret = -EBADF;
 				break;

@@ -1058,8 +1072,9 @@ reset_info_exit:
 				break;
 			}
 
-			groups[i].group = group;
-			groups[i].id = vfio_external_user_iommu_id(group);
+			groups[group_idx].group = group;
+			groups[group_idx].id =
+					vfio_external_user_iommu_id(group);
 		}
 
 		kfree(group_fds);

@@ -1078,14 +1093,65 @@ reset_info_exit:
 		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
 						    vfio_pci_validate_devs,
 						    &info, slot);
-		if (!ret)
-			/* User has access, do the reset */
-			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-				     pci_try_reset_bus(vdev->pdev->bus);
+
+		if (ret)
+			goto hot_reset_release;
+
+		devs.max_index = count;
+		devs.devices = kcalloc(count, sizeof(struct vfio_device *),
+				       GFP_KERNEL);
+		if (!devs.devices) {
+			ret = -ENOMEM;
+			goto hot_reset_release;
+		}
+
+		/*
+		 * We need to get memory_lock for each device, but devices
+		 * can share mmap_sem, therefore we need to zap and hold
+		 * the vma_lock for each device, and only then get each
+		 * memory_lock.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					    vfio_pci_try_zap_and_vma_lock_cb,
+					    &devs, slot);
+		if (ret)
+			goto hot_reset_release;
+
+		for (; mem_idx < devs.cur_index; mem_idx++) {
+			struct vfio_pci_device *tmp;
+
+			tmp = vfio_device_data(devs.devices[mem_idx]);
+
+			ret = down_write_trylock(&tmp->memory_lock);
+			if (!ret) {
+				ret = -EBUSY;
+				goto hot_reset_release;
+			}
+			mutex_unlock(&tmp->vma_lock);
+		}
+
+		/* User has access, do the reset */
+		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+				pci_try_reset_bus(vdev->pdev->bus);
 
 hot_reset_release:
-		for (i--; i >= 0; i--)
-			vfio_group_put_external_user(groups[i].group);
+		for (i = 0; i < devs.cur_index; i++) {
+			struct vfio_device *device;
+			struct vfio_pci_device *tmp;
+
+			device = devs.devices[i];
+			tmp = vfio_device_data(device);
+
+			if (i < mem_idx)
+				up_write(&tmp->memory_lock);
+			else
+				mutex_unlock(&tmp->vma_lock);
+			vfio_device_put(device);
+		}
+		kfree(devs.devices);
+
+		for (group_idx--; group_idx >= 0; group_idx--)
+			vfio_group_put_external_user(groups[group_idx].group);
 
 		kfree(groups);
 		return ret;

@@ -1144,8 +1210,126 @@ static ssize_t vfio_pci_write(void *devi
 	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
-static int vfio_pci_add_vma(struct vfio_pci_device *vdev,
-			    struct vm_area_struct *vma)
+/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
+static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
+{
+	struct vfio_pci_mmap_vma *mmap_vma, *tmp;
+
+	/*
+	 * Lock ordering:
+	 * vma_lock is nested under mmap_sem for vm_ops callback paths.
+	 * The memory_lock semaphore is used by both code paths calling
+	 * into this function to zap vmas and the vm_ops.fault callback
+	 * to protect the memory enable state of the device.
+	 *
+	 * When zapping vmas we need to maintain the mmap_sem => vma_lock
+	 * ordering, which requires using vma_lock to walk vma_list to
+	 * acquire an mm, then dropping vma_lock to get the mmap_sem and
+	 * reacquiring vma_lock.  This logic is derived from similar
+	 * requirements in uverbs_user_mmap_disassociate().
+	 *
+	 * mmap_sem must always be the top-level lock when it is taken.
+	 * Therefore we can only hold the memory_lock write lock when
+	 * vma_list is empty, as we'd need to take mmap_sem to clear
+	 * entries.  vma_list can only be guaranteed empty when holding
+	 * vma_lock, thus memory_lock is nested under vma_lock.
+	 *
+	 * This enables the vm_ops.fault callback to acquire vma_lock,
+	 * followed by memory_lock read lock, while already holding
+	 * mmap_sem without risk of deadlock.
+	 */
+	while (1) {
+		struct mm_struct *mm = NULL;
+
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock))
+				return 0;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		while (!list_empty(&vdev->vma_list)) {
+			mmap_vma = list_first_entry(&vdev->vma_list,
+						    struct vfio_pci_mmap_vma,
+						    vma_next);
+			mm = mmap_vma->vma->vm_mm;
+			if (mmget_not_zero(mm))
+				break;
+
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
+			mm = NULL;
+		}
+		if (!mm)
+			return 1;
+		mutex_unlock(&vdev->vma_lock);
+
+		if (try) {
+			if (!down_read_trylock(&mm->mmap_sem)) {
+				mmput(mm);
+				return 0;
+			}
+		} else {
+			down_read(&mm->mmap_sem);
+		}
+		if (mmget_still_valid(mm)) {
+			if (try) {
+				if (!mutex_trylock(&vdev->vma_lock)) {
+					up_read(&mm->mmap_sem);
+					mmput(mm);
+					return 0;
+				}
+			} else {
+				mutex_lock(&vdev->vma_lock);
+			}
+			list_for_each_entry_safe(mmap_vma, tmp,
+						 &vdev->vma_list, vma_next) {
+				struct vm_area_struct *vma = mmap_vma->vma;
+
+				if (vma->vm_mm != mm)
+					continue;
+
+				list_del(&mmap_vma->vma_next);
+				kfree(mmap_vma);
+
+				zap_vma_ptes(vma, vma->vm_start,
+					     vma->vm_end - vma->vm_start);
+			}
+			mutex_unlock(&vdev->vma_lock);
+		}
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
+
+void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev)
+{
+	vfio_pci_zap_and_vma_lock(vdev, false);
+	down_write(&vdev->memory_lock);
+	mutex_unlock(&vdev->vma_lock);
+}
+
+u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev)
+{
+	u16 cmd;
+
+	down_write(&vdev->memory_lock);
+	pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd);
+	if (!(cmd & PCI_COMMAND_MEMORY))
+		pci_write_config_word(vdev->pdev, PCI_COMMAND,
+				      cmd | PCI_COMMAND_MEMORY);
+
+	return cmd;
+}
+
+void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd)
+{
+	pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd);
+	up_write(&vdev->memory_lock);
+}
+
+/* Caller holds vma_lock */
+static int __vfio_pci_add_vma(struct vfio_pci_device *vdev,
+			      struct vm_area_struct *vma)
 {
 	struct vfio_pci_mmap_vma *mmap_vma;
 

@@ -1154,10 +1338,7 @@ static int vfio_pci_add_vma(struct vfio_
 		return -ENOMEM;
 
 	mmap_vma->vma = vma;
-
-	mutex_lock(&vdev->vma_lock);
 	list_add(&mmap_vma->vma_next, &vdev->vma_list);
-	mutex_unlock(&vdev->vma_lock);
 
 	return 0;
 }

@@ -1190,15 +1371,32 @@ static void vfio_pci_mmap_close(struct v
 static int vfio_pci_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct vfio_pci_device *vdev = vma->vm_private_data;
+	int ret = VM_FAULT_NOPAGE;
+
+	mutex_lock(&vdev->vma_lock);
+	down_read(&vdev->memory_lock);
+
+	if (!__vfio_pci_memory_enabled(vdev)) {
+		ret = VM_FAULT_SIGBUS;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
+
+	if (__vfio_pci_add_vma(vdev, vma)) {
+		ret = VM_FAULT_OOM;
+		mutex_unlock(&vdev->vma_lock);
+		goto up_out;
+	}
 
-	if (vfio_pci_add_vma(vdev, vma))
-		return VM_FAULT_OOM;
+	mutex_unlock(&vdev->vma_lock);
 
 	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			    vma->vm_end - vma->vm_start, vma->vm_page_prot))
-		return VM_FAULT_SIGBUS;
+		ret = VM_FAULT_SIGBUS;
 
-	return VM_FAULT_NOPAGE;
+up_out:
+	up_read(&vdev->memory_lock);
+	return ret;
 }
 
 static const struct vm_operations_struct vfio_pci_mmap_ops = {