Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/devicetree/bindings/net/ethernet-controller.yaml

@@ -106,6 +106,12 @@ properties:
   phy-mode:
     $ref: "#/properties/phy-connection-type"
 
+  pcs-handle:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Specifies a reference to a node representing a PCS PHY device on a MDIO
+      bus to link with an external PHY (phy-handle) if exists.
+
   phy-handle:
     $ref: /schemas/types.yaml#/definitions/phandle
     description:

Documentation/devicetree/bindings/net/micrel.txt

@@ -45,20 +45,3 @@ Optional properties:
 
 	In fiber mode, auto-negotiation is disabled and the PHY can only work in
 	100base-fx (full and half duplex) modes.
-
- - lan8814,ignore-ts: If present the PHY will not support timestamping.
-
-	This option acts as check whether Timestamping is supported by
-	hardware or not. LAN8814 phy support hardware tmestamping.
-
- - lan8814,latency_rx_10: Configures Latency value of phy in ingress at 10 Mbps.
-
- - lan8814,latency_tx_10: Configures Latency value of phy in egress at 10 Mbps.
-
- - lan8814,latency_rx_100: Configures Latency value of phy in ingress at 100 Mbps.
-
- - lan8814,latency_tx_100: Configures Latency value of phy in egress at 100 Mbps.
-
- - lan8814,latency_rx_1000: Configures Latency value of phy in ingress at 1000 Mbps.
-
- - lan8814,latency_tx_1000: Configures Latency value of phy in egress at 1000 Mbps.

Documentation/devicetree/bindings/net/xilinx_axienet.txt

@@ -26,7 +26,8 @@ Required properties:
 		  specified, the TX/RX DMA interrupts should be on that node
 		  instead, and only the Ethernet core interrupt is optionally
 		  specified here.
-- phy-handle	: Should point to the external phy device.
+- phy-handle	: Should point to the external phy device if exists. Pointing
+		  this to the PCS/PMA PHY is deprecated and should be avoided.
 		  See ethernet.txt file in the same directory.
 - xlnx,rxmem	: Set to allocated memory buffer for Rx/Tx in the hardware
 
@@ -68,6 +69,11 @@ Optional properties:
 		  required through the core's MDIO interface (i.e. always,
 		  unless the PHY is accessed through a different bus).
 
+ - pcs-handle: 	  Phandle to the internal PCS/PMA PHY in SGMII or 1000Base-X
+		  modes, where "pcs-handle" should be used to point
+		  to the PCS/PMA PHY, and "phy-handle" should point to an
+		  external PHY if exists.
+
 Example:
 	axi_ethernet_eth: ethernet@40c00000 {
 		compatible = "xlnx,axi-ethernet-1.00.a";

Documentation/networking/dsa/dsa.rst

@@ -10,21 +10,21 @@ in joining the effort.
 Design principles
 =================
 
-The Distributed Switch Architecture is a subsystem which was primarily designed
+The Distributed Switch Architecture subsystem was primarily designed to
-to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line)
+support Marvell Ethernet switches (MV88E6xxx, a.k.a. Link Street product
-using Linux, but has since evolved to support other vendors as well.
+line) using Linux, but has since evolved to support other vendors as well.
 
 The original philosophy behind this design was to be able to use unmodified
 Linux tools such as bridge, iproute2, ifconfig to work transparently whether
 they configured/queried a switch port network device or a regular network
 device.
 
-An Ethernet switch is typically comprised of multiple front-panel ports, and one
+An Ethernet switch typically comprises multiple front-panel ports and one
-or more CPU or management port. The DSA subsystem currently relies on the
+or more CPU or management ports. The DSA subsystem currently relies on the
 presence of a management port connected to an Ethernet controller capable of
 receiving Ethernet frames from the switch. This is a very common setup for all
 kinds of Ethernet switches found in Small Home and Office products: routers,
-gateways, or even top-of-the rack switches. This host Ethernet controller will
+gateways, or even top-of-rack switches. This host Ethernet controller will
 be later referred to as "master" and "cpu" in DSA terminology and code.
 
 The D in DSA stands for Distributed, because the subsystem has been designed
@@ -33,14 +33,14 @@ using upstream and downstream Ethernet links between switches. These specific
 ports are referred to as "dsa" ports in DSA terminology and code. A collection
 of multiple switches connected to each other is called a "switch tree".
 
-For each front-panel port, DSA will create specialized network devices which are
+For each front-panel port, DSA creates specialized network devices which are
 used as controlling and data-flowing endpoints for use by the Linux networking
 stack. These specialized network interfaces are referred to as "slave" network
 interfaces in DSA terminology and code.
 
 The ideal case for using DSA is when an Ethernet switch supports a "switch tag"
 which is a hardware feature making the switch insert a specific tag for each
-Ethernet frames it received to/from specific ports to help the management
+Ethernet frame it receives to/from specific ports to help the management
 interface figure out:
 
 - what port is this frame coming from
@@ -125,7 +125,7 @@ other switches from the same fabric, and in this case, the outermost switch
 ports must decapsulate the packet.
 
 Note that in certain cases, it might be the case that the tagging format used
-by a leaf switch (not connected directly to the CPU) to not be the same as what
+by a leaf switch (not connected directly to the CPU) is not the same as what
 the network stack sees. This can be seen with Marvell switch trees, where the
 CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA)
 format, but the DSA links are configured to use the shorter (without Ethertype)
@@ -270,21 +270,21 @@ These interfaces are specialized in order to:
   to/from specific switch ports
 - query the switch for ethtool operations: statistics, link state,
   Wake-on-LAN, register dumps...
-- external/internal PHY management: link, auto-negotiation etc.
+- manage external/internal PHY: link, auto-negotiation, etc.
 
 These slave network devices have custom net_device_ops and ethtool_ops function
 pointers which allow DSA to introduce a level of layering between the networking
-stack/ethtool, and the switch driver implementation.
+stack/ethtool and the switch driver implementation.
 
 Upon frame transmission from these slave network devices, DSA will look up which
-switch tagging protocol is currently registered with these network devices, and
+switch tagging protocol is currently registered with these network devices and
 invoke a specific transmit routine which takes care of adding the relevant
 switch tag in the Ethernet frames.
 
 These frames are then queued for transmission using the master network device
-``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the
+``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the
 Ethernet switch will be able to process these incoming frames from the
-management interface and delivers these frames to the physical switch port.
+management interface and deliver them to the physical switch port.
 
 Graphical representation
 ------------------------
@@ -330,9 +330,9 @@ MDIO reads/writes towards specific PHY addresses. In most MDIO-connected
 switches, these functions would utilize direct or indirect PHY addressing mode
 to return standard MII registers from the switch builtin PHYs, allowing the PHY
 library and/or to return link status, link partner pages, auto-negotiation
-results etc..
+results, etc.
 
-For Ethernet switches which have both external and internal MDIO busses, the
+For Ethernet switches which have both external and internal MDIO buses, the
 slave MII bus can be utilized to mux/demux MDIO reads and writes towards either
 internal or external MDIO devices this switch might be connected to: internal
 PHYs, external PHYs, or even external switches.
@@ -349,7 +349,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as
   table indication (when cascading switches)
 
 - ``dsa_platform_data``: platform device configuration data which can reference
-  a collection of dsa_chip_data structure if multiples switches are cascaded,
+  a collection of dsa_chip_data structures if multiple switches are cascaded,
   the master network device this switch tree is attached to needs to be
   referenced
 
@@ -426,7 +426,7 @@ logic basically looks like this:
   "phy-handle" property, if found, this PHY device is created and registered
   using ``of_phy_connect()``
 
-- if Device Tree is used, and the PHY device is "fixed", that is, conforms to
+- if Device Tree is used and the PHY device is "fixed", that is, conforms to
   the definition of a non-MDIO managed PHY as defined in
   ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered
   and connected transparently using the special fixed MDIO bus driver
@@ -481,7 +481,7 @@ Device Tree
 DSA features a standardized binding which is documented in
 ``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper
 functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query
-per-port PHY specific details: interface connection, MDIO bus location etc..
+per-port PHY specific details: interface connection, MDIO bus location, etc.
 
 Driver development
 ==================
@@ -509,7 +509,7 @@ Switch configuration
 
 - ``setup``: setup function for the switch, this function is responsible for setting
   up the ``dsa_switch_ops`` private structure with all it needs: register maps,
-  interrupts, mutexes, locks etc.. This function is also expected to properly
+  interrupts, mutexes, locks, etc. This function is also expected to properly
   configure the switch to separate all network interfaces from each other, that
   is, they should be isolated by the switch hardware itself, typically by creating
   a Port-based VLAN ID for each port and allowing only the CPU port and the
@@ -526,13 +526,13 @@ PHY devices and link management
 - ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs,
   if the PHY library PHY driver needs to know about information it cannot obtain
   on its own (e.g.: coming from switch memory mapped registers), this function
-  should return a 32-bits bitmask of "flags", that is private between the switch
+  should return a 32-bit bitmask of "flags" that is private between the switch
   driver and the Ethernet PHY driver in ``drivers/net/phy/\*``.
 
 - ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read
   the switch port MDIO registers. If unavailable, return 0xffff for each read.
   For builtin switch Ethernet PHYs, this function should allow reading the link
-  status, auto-negotiation results, link partner pages etc..
+  status, auto-negotiation results, link partner pages, etc.
 
 - ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write
   to the switch port MDIO registers. If unavailable return a negative error
@@ -554,7 +554,7 @@ Ethtool operations
 ------------------
 
 - ``get_strings``: ethtool function used to query the driver's strings, will
-  typically return statistics strings, private flags strings etc.
+  typically return statistics strings, private flags strings, etc.
 
 - ``get_ethtool_stats``: ethtool function used to query per-port statistics and
   return their values. DSA overlays slave network devices general statistics:
@@ -564,7 +564,7 @@ Ethtool operations
 - ``get_sset_count``: ethtool function used to query the number of statistics items
 
 - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this
-  function may, for certain implementations also query the master network device
+  function may for certain implementations also query the master network device
   Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN
 
 - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port,
@@ -607,14 +607,14 @@ Power management
   in a fully active state
 
 - ``port_enable``: function invoked by the DSA slave network device ndo_open
-  function when a port is administratively brought up, this function should be
+  function when a port is administratively brought up, this function should
-  fully enabling a given switch port. DSA takes care of marking the port with
+  fully enable a given switch port. DSA takes care of marking the port with
   ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it
   was not, and propagating these changes down to the hardware
 
 - ``port_disable``: function invoked by the DSA slave network device ndo_close
-  function when a port is administratively brought down, this function should be
+  function when a port is administratively brought down, this function should
-  fully disabling a given switch port. DSA takes care of marking the port with
+  fully disable a given switch port. DSA takes care of marking the port with
   ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is
   disabled while being a bridge member
 
@@ -622,12 +622,12 @@ Bridge layer
 ------------
 
 - ``port_bridge_join``: bridge layer function invoked when a given switch port is
-  added to a bridge, this function should be doing the necessary at the switch
+  added to a bridge, this function should do what's necessary at the switch
-  level to permit the joining port from being added to the relevant logical
+  level to permit the joining port to be added to the relevant logical
   domain for it to ingress/egress traffic with other members of the bridge.
 
 - ``port_bridge_leave``: bridge layer function invoked when a given switch port is
-  removed from a bridge, this function should be doing the necessary at the
+  removed from a bridge, this function should do what's necessary at the
   switch level to deny the leaving port from ingress/egress traffic from the
   remaining bridge members. When the port leaves the bridge, it should be aged
   out at the switch hardware for the switch to (re) learn MAC addresses behind
@@ -663,7 +663,7 @@ Bridge layer
   point for drivers that need to configure the hardware for enabling this
   feature.
 
-- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoken when a driver
+- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver
   leaves a bridge port which had the TX forwarding offload feature enabled.
 
 Bridge VLAN filtering

arch/x86/power/cpu.c

@@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt)
 	struct saved_msr *end = msr + ctxt->saved_msrs.num;
 
 	while (msr < end) {
-		msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q);
+		if (msr->valid)
+			rdmsrl(msr->info.msr_no, msr->info.reg.q);
 		msr++;
 	}
 }
@@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num)
 	}
 
 	for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) {
+		u64 dummy;
+
 		msr_array[i].info.msr_no	= msr_id[j];
-		msr_array[i].valid		= false;
+		msr_array[i].valid		= !rdmsrl_safe(msr_id[j], &dummy);
 		msr_array[i].info.reg.q		= 0;
 	}
 	saved_msrs->num   = total_num;
@@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c)
 	return ret;
 }
 
+static void pm_save_spec_msr(void)
+{
+	u32 spec_msr_id[] = {
+		MSR_IA32_SPEC_CTRL,
+		MSR_IA32_TSX_CTRL,
+		MSR_TSX_FORCE_ABORT,
+		MSR_IA32_MCU_OPT_CTRL,
+		MSR_AMD64_LS_CFG,
+	};
+
+	msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id));
+}
+
 static int pm_check_save_msr(void)
 {
 	dmi_check_system(msr_save_dmi_table);
 	pm_cpu_check(msr_save_cpu_table);
+	pm_save_spec_msr();
 
 	return 0;
 }

drivers/ata/Kconfig

@@ -115,14 +115,16 @@ config SATA_AHCI
 
 	  If unsure, say N.
 
-config SATA_LPM_POLICY
+config SATA_MOBILE_LPM_POLICY
 	int "Default SATA Link Power Management policy for low power chipsets"
 	range 0 4
 	default 0
 	depends on SATA_AHCI
 	help
 	  Select the Default SATA Link Power Management (LPM) policy to use
-	  for chipsets / "South Bridges" designated as supporting low power.
+	  for chipsets / "South Bridges" supporting low-power modes. Such
+	  chipsets are typically found on most laptops but desktops and
+	  servers now also widely use chipsets supporting low power modes.
 
 	  The value set has the following meanings:
 		0 => Keep firmware settings

drivers/ata/ahci.c

@@ -1595,7 +1595,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports,
 static void ahci_update_initial_lpm_policy(struct ata_port *ap,
 					   struct ahci_host_priv *hpriv)
 {
-	int policy = CONFIG_SATA_LPM_POLICY;
+	int policy = CONFIG_SATA_MOBILE_LPM_POLICY;
 
 
 	/* Ignore processing for chipsets that don't use policy */

drivers/ata/ahci.h

@@ -236,7 +236,7 @@ enum {
 	AHCI_HFLAG_NO_WRITE_TO_RO	= (1 << 24), /* don't write to read
 							only registers */
 	AHCI_HFLAG_USE_LPM_POLICY	= (1 << 25), /* chipset that should use
-							SATA_LPM_POLICY
+							SATA_MOBILE_LPM_POLICY
 							as default lpm_policy */
 	AHCI_HFLAG_SUSPEND_PHYS		= (1 << 26), /* handle PHYs during
 							suspend/resume */

drivers/ata/libata-core.c

@@ -4014,6 +4014,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*MX100*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "Samsung SSD 840 EVO*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
+						ATA_HORKAGE_NO_DMA_LOG |
+						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Samsung SSD 840*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Samsung SSD 850*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |

drivers/ata/libata-sff.c

@@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt);
 
 void ata_sff_lost_interrupt(struct ata_port *ap)
 {
-	u8 status;
+	u8 status = 0;
 	struct ata_queued_cmd *qc;
 
 	/* Only one outstanding command per SFF channel */

drivers/ata/sata_dwc_460ex.c

@@ -137,7 +137,11 @@ struct sata_dwc_device {
 #endif
 };
 
-#define SATA_DWC_QCMD_MAX	32
+/*
+ * Allow one extra special slot for commands and DMA management
+ * to account for libata internal commands.
+ */
+#define SATA_DWC_QCMD_MAX	(ATA_MAX_QUEUE + 1)
 
 struct sata_dwc_device_port {
 	struct sata_dwc_device	*hsdev;

drivers/char/random.c

@@ -437,11 +437,8 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS],
  * This shouldn't be set by functions like add_device_randomness(),
  * where we can't trust the buffer passed to it is guaranteed to be
  * unpredictable (so it might not have any entropy at all).
- *
- * Returns the number of bytes processed from input, which is bounded
- * by CRNG_INIT_CNT_THRESH if account is true.
  */
-static size_t crng_pre_init_inject(const void *input, size_t len, bool account)
+static void crng_pre_init_inject(const void *input, size_t len, bool account)
 {
 	static int crng_init_cnt = 0;
 	struct blake2s_state hash;
@@ -452,18 +449,15 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account)
 	spin_lock_irqsave(&base_crng.lock, flags);
 	if (crng_init != 0) {
 		spin_unlock_irqrestore(&base_crng.lock, flags);
-		return 0;
+		return;
 	}
 
-	if (account)
-		len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt);
-
 	blake2s_update(&hash, base_crng.key, sizeof(base_crng.key));
 	blake2s_update(&hash, input, len);
 	blake2s_final(&hash, base_crng.key);
 
 	if (account) {
-		crng_init_cnt += len;
+		crng_init_cnt += min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt);
 		if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
 			++base_crng.generation;
 			crng_init = 1;
@@ -474,8 +468,6 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account)
 
 	if (crng_init == 1)
 		pr_notice("fast init done\n");
-
-	return len;
 }
 
 static void _get_random_bytes(void *buf, size_t nbytes)
@@ -531,7 +523,6 @@ EXPORT_SYMBOL(get_random_bytes);
 
 static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 {
-	bool large_request = nbytes > 256;
 	ssize_t ret = 0;
 	size_t len;
 	u32 chacha_state[CHACHA_STATE_WORDS];
@@ -540,22 +531,23 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 	if (!nbytes)
 		return 0;
 
-	len = min_t(size_t, 32, nbytes);
+	/*
-	crng_make_state(chacha_state, output, len);
+	 * Immediately overwrite the ChaCha key at index 4 with random
-
+	 * bytes, in case userspace causes copy_to_user() below to sleep
-	if (copy_to_user(buf, output, len))
+	 * forever, so that we still retain forward secrecy in that case.
-		return -EFAULT;
+	 */
-	nbytes -= len;
+	crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE);
-	buf += len;
+	/*
-	ret += len;
+	 * However, if we're doing a read of len <= 32, we don't need to
-
+	 * use chacha_state after, so we can simply return those bytes to
-	while (nbytes) {
+	 * the user directly.
-		if (large_request && need_resched()) {
+	 */
-			if (signal_pending(current))
+	if (nbytes <= CHACHA_KEY_SIZE) {
-				break;
+		ret = copy_to_user(buf, &chacha_state[4], nbytes) ? -EFAULT : nbytes;
-			schedule();
+		goto out_zero_chacha;
-		}
+	}
 
+	do {
 		chacha20_block(chacha_state, output);
 		if (unlikely(chacha_state[12] == 0))
 			++chacha_state[13];
@@ -569,10 +561,18 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes)
 		nbytes -= len;
 		buf += len;
 		ret += len;
-	}
 
-	memzero_explicit(chacha_state, sizeof(chacha_state));
+		BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0);
+		if (!(ret % PAGE_SIZE) && nbytes) {
+			if (signal_pending(current))
+				break;
+			cond_resched();
+		}
+	} while (nbytes);
+
 	memzero_explicit(output, sizeof(output));
+out_zero_chacha:
+	memzero_explicit(chacha_state, sizeof(chacha_state));
 	return ret;
 }
 
@@ -1141,12 +1141,9 @@ void add_hwgenerator_randomness(const void *buffer, size_t count,
 				size_t entropy)
 {
 	if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) {
-		size_t ret = crng_pre_init_inject(buffer, count, true);
+		crng_pre_init_inject(buffer, count, true);
-		mix_pool_bytes(buffer, ret);
+		mix_pool_bytes(buffer, count);
-		count -= ret;
+		return;
-		buffer += ret;
-		if (!count || crng_init == 0)
-			return;
 	}
 
 	/*
@@ -1545,6 +1542,13 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes,
 {
 	static int maxwarn = 10;
 
+	/*
+	 * Opportunistically attempt to initialize the RNG on platforms that
+	 * have fast cycle counters, but don't (for now) require it to succeed.
+	 */
+	if (!crng_ready())
+		try_to_generate_entropy();
+
 	if (!crng_ready() && maxwarn > 0) {
 		maxwarn--;
 		if (__ratelimit(&urandom_warning))

drivers/hv/channel_mgmt.c

@@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
 	 * execute:
 	 *
 	 *  (a) In the "normal (i.e., not resuming from hibernation)" path,
-	 *      the full barrier in smp_store_mb() guarantees that the store
+	 *      the full barrier in virt_store_mb() guarantees that the store
 	 *      is propagated to all CPUs before the add_channel_work work
 	 *      is queued.  In turn, add_channel_work is queued before the
 	 *      channel's ring buffer is allocated/initialized and the
@@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
 	 *      recv_int_page before retrieving the channel pointer from the
 	 *      array of channels.
 	 *
-	 *  (b) In the "resuming from hibernation" path, the smp_store_mb()
+	 *  (b) In the "resuming from hibernation" path, the virt_store_mb()
 	 *      guarantees that the store is propagated to all CPUs before
 	 *      the VMBus connection is marked as ready for the resume event
 	 *      (cf. check_ready_for_resume_event()).  The interrupt handler
 	 *      of the VMBus driver and vmbus_chan_sched() can not run before
 	 *      vmbus_bus_resume() has completed execution (cf. resume_noirq).
 	 */
-	smp_store_mb(
+	virt_store_mb(
 		vmbus_connection.channels[channel->offermsg.child_relid],
 		channel);
 }

drivers/hv/hv_balloon.c

@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
+#include <linux/count_zeros.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memory.h>
 #include <linux/notifier.h>
@@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm)
 	struct dm_status status;
 	unsigned long now = jiffies;
 	unsigned long last_post = last_post_time;
+	unsigned long num_pages_avail, num_pages_committed;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
@@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm)
 	 * num_pages_onlined) as committed to the host, otherwise it can try
 	 * asking us to balloon them out.
 	 */
-	status.num_avail = si_mem_available();
+	num_pages_avail = si_mem_available();
-	status.num_committed = vm_memory_committed() +
+	num_pages_committed = vm_memory_committed() +
 		dm->num_pages_ballooned +
 		(dm->num_pages_added > dm->num_pages_onlined ?
 		 dm->num_pages_added - dm->num_pages_onlined : 0) +
 		compute_balloon_floor();
 
-	trace_balloon_status(status.num_avail, status.num_committed,
+	trace_balloon_status(num_pages_avail, num_pages_committed,
 			     vm_memory_committed(), dm->num_pages_ballooned,
 			     dm->num_pages_added, dm->num_pages_onlined);
+
+	/* Convert numbers of pages into numbers of HV_HYP_PAGEs. */
+	status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE;
+	status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE;
+
 	/*
 	 * If our transaction ID is no longer current, just don't
 	 * send the status. This can happen if we were interrupted
@@ -1653,6 +1660,38 @@ static void disable_page_reporting(void)
 	}
 }
 
+static int ballooning_enabled(void)
+{
+	/*
+	 * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE),
+	 * since currently it's unclear to us whether an unballoon request can
+	 * make sure all page ranges are guest page size aligned.
+	 */
+	if (PAGE_SIZE != HV_HYP_PAGE_SIZE) {
+		pr_info("Ballooning disabled because page size is not 4096 bytes\n");
+		return 0;
+	}
+
+	return 1;
+}
+
+static int hot_add_enabled(void)
+{
+	/*
+	 * Disable hot add on ARM64, because we currently rely on
+	 * memory_add_physaddr_to_nid() to get a node id of a hot add range,
+	 * however ARM64's memory_add_physaddr_to_nid() always return 0 and
+	 * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for
+	 * add_memory().
+	 */
+	if (IS_ENABLED(CONFIG_ARM64)) {
+		pr_info("Memory hot add disabled on ARM64\n");
+		return 0;
+	}
+
+	return 1;
+}
+
 static int balloon_connect_vsp(struct hv_device *dev)
 {
 	struct dm_version_request version_req;
@@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev)
 	 * currently still requires the bits to be set, so we have to add code
 	 * to fail the host's hot-add and balloon up/down requests, if any.
 	 */
-	cap_msg.caps.cap_bits.balloon = 1;
+	cap_msg.caps.cap_bits.balloon = ballooning_enabled();
-	cap_msg.caps.cap_bits.hot_add = 1;
+	cap_msg.caps.cap_bits.hot_add = hot_add_enabled();
 
 	/*
 	 * Specify our alignment requirements as it relates

drivers/hv/hv_common.c

@@ -20,6 +20,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query)
 }
 EXPORT_SYMBOL_GPL(hv_query_ext_cap);
 
+void hv_setup_dma_ops(struct device *dev, bool coherent)
+{
+	/*
+	 * Hyper-V does not offer a vIOMMU in the guest
+	 * VM, so pass 0/NULL for the IOMMU settings
+	 */
+	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+}
+EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
+
 bool hv_is_hibernation_supported(void)
 {
 	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);

drivers/hv/ring_buffer.c

@@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
 {
 	u32 priv_read_loc = rbi->priv_read_index;
-	u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index);
+	u32 write_loc;
+
+	/*
+	 * The Hyper-V host writes the packet data, then uses
+	 * store_release() to update the write_index.  Use load_acquire()
+	 * here to prevent loads of the packet data from being re-ordered
+	 * before the read of the write_index and potentially getting
+	 * stale data.
+	 */
+	write_loc = virt_load_acquire(&rbi->ring_buffer->write_index);
 
 	if (write_loc >= priv_read_loc)
 		return write_loc - priv_read_loc;

drivers/hv/vmbus_drv.c

@@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 
 	/*
 	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * doing hv_kmsg_dump() with kmsg data later, don't do the notification
-	 * the notification here.
+	 * here.
 	 */
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
 	    && hyperv_report_reg()) {
@@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 
 	/*
 	 * Hyper-V should be notified only once about a panic.  If we will be
-	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * doing hv_kmsg_dump() with kmsg data later, don't do the notification
-	 * the notification here.
+	 * here.
 	 */
 	if (hyperv_report_reg())
 		hyperv_report_panic(regs, val, true);
@@ -920,6 +920,21 @@ static int vmbus_probe(struct device *child_device)
 	return ret;
 }
 
+/*
+ * vmbus_dma_configure -- Configure DMA coherence for VMbus device
+ */
+static int vmbus_dma_configure(struct device *child_device)
+{
+	/*
+	 * On ARM64, propagate the DMA coherence setting from the top level
+	 * VMbus ACPI device to the child VMbus device being added here.
+	 * On x86/x64 coherence is assumed and these calls have no effect.
+	 */
+	hv_setup_dma_ops(child_device,
+		device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT);
+	return 0;
+}
+
 /*
  * vmbus_remove - Remove a vmbus device
  */
@@ -1040,6 +1055,7 @@ static struct bus_type  hv_bus = {
 	.remove =		vmbus_remove,
 	.probe =		vmbus_probe,
 	.uevent =		vmbus_uevent,
+	.dma_configure =	vmbus_dma_configure,
 	.dev_groups =		vmbus_dev_groups,
 	.drv_groups =		vmbus_drv_groups,
 	.bus_groups =		vmbus_bus_groups,
@@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void)
 	if (ret)
 		goto err_connect;
 
+	if (hv_is_isolation_supported())
+		sysctl_record_panic_msg = 0;
+
 	/*
 	 * Only register if the crash MSRs are available
 	 */
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		u64 hyperv_crash_ctl;
 		/*
-		 * Sysctl registration is not fatal, since by default
+		 * Panic message recording (sysctl_record_panic_msg)
-		 * reporting is enabled.
+		 * is enabled by default in non-isolated guests and
+		 * disabled by default in isolated guests; the panic
+		 * message recording won't be available in isolated
+		 * guests should the following registration fail.
 		 */
 		hv_ctl_table_hdr = register_sysctl_table(hv_root_table);
 		if (!hv_ctl_table_hdr)
@@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	child_device_obj->device.parent = &hv_acpi_dev->dev;
 	child_device_obj->device.release = vmbus_device_release;
 
+	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
+	child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
+	dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
+
 	/*
 	 * Register with the LDM. This will kick off the driver/device
 	 * binding...which will eventually call vmbus_match() and vmbus_probe()
@@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	}
 	hv_debug_add_dev_dir(child_device_obj);
 
-	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
-	child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
-	dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
 	return 0;
 
 err_kset_unregister:
@@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 	hv_acpi_dev = device;
 
+	/*
+	 * Older versions of Hyper-V for ARM64 fail to include the _CCA
+	 * method on the top level VMbus device in the DSDT. But devices
+	 * are hardware coherent in all current Hyper-V use cases, so fix
+	 * up the ACPI device to behave as if _CCA is present and indicates
+	 * hardware coherence.
+	 */
+	ACPI_COMPANION_SET(&device->dev, device);
+	if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) &&
+	    device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) {
+		pr_info("No ACPI _CCA found; assuming coherent device I/O\n");
+		device->flags.cca_seen = true;
+		device->flags.coherent_dma = true;
+	}
+
 	result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
 					vmbus_walk_resources, NULL);
 
@@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void)
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		kmsg_dump_unregister(&hv_kmsg_dumper);
 		unregister_die_notifier(&hyperv_die_block);
-		atomic_notifier_chain_unregister(&panic_notifier_list,
-						 &hyperv_panic_block);
 	}
 
+	/*
+	 * The panic notifier is always registered, hence we should
+	 * also unconditionally unregister it here as well.
+	 */
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &hyperv_panic_block);
+
 	free_page((unsigned long)hv_panic_page);
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -3253,6 +3253,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		}
 		qidx = bp->tc_to_qidx[j];
 		ring->queue_id = bp->q_info[qidx].queue_id;
+		spin_lock_init(&txr->xdp_tx_lock);
 		if (i < bp->tx_nr_rings_xdp)
 			continue;
 		if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
@@ -10338,6 +10339,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (irq_re_init)
 		udp_tunnel_nic_reset_ntf(bp->dev);
 
+	if (bp->tx_nr_rings_xdp < num_possible_cpus()) {
+		if (!static_key_enabled(&bnxt_xdp_locking_key))
+			static_branch_enable(&bnxt_xdp_locking_key);
+	} else if (static_key_enabled(&bnxt_xdp_locking_key)) {
+		static_branch_disable(&bnxt_xdp_locking_key);
+	}
 	set_bit(BNXT_STATE_OPEN, &bp->state);
 	bnxt_enable_int(bp);
 	/* Enable TX queues */

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -593,7 +593,8 @@ struct nqe_cn {
 #define BNXT_MAX_MTU		9500
 #define BNXT_MAX_PAGE_MODE_MTU	\
 	((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN -	\
-	 XDP_PACKET_HEADROOM)
+	 XDP_PACKET_HEADROOM - \
+	 SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
 
 #define BNXT_MIN_PKT_SIZE	52
 
@@ -800,6 +801,8 @@ struct bnxt_tx_ring_info {
 	u32			dev_state;
 
 	struct bnxt_ring_struct	tx_ring_struct;
+	/* Synchronize simultaneous xdp_xmit on same ring */
+	spinlock_t		xdp_tx_lock;
 };
 
 #define BNXT_LEGACY_COAL_CMPL_PARAMS					\

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

@@ -20,6 +20,8 @@
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
+DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
+
 struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 				   struct bnxt_tx_ring_info *txr,
 				   dma_addr_t mapping, u32 len)
@@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 	ring = smp_processor_id() % bp->tx_nr_rings_xdp;
 	txr = &bp->tx_ring[ring];
 
+	if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING)
+		return -EINVAL;
+
+	if (static_branch_unlikely(&bnxt_xdp_locking_key))
+		spin_lock(&txr->xdp_tx_lock);
+
 	for (i = 0; i < num_frames; i++) {
 		struct xdp_frame *xdp = frames[i];
 
-		if (!txr || !bnxt_tx_avail(bp, txr) ||
+		if (!bnxt_tx_avail(bp, txr))
-		    !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP))
 			break;
 
 		mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len,
@@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 		bnxt_db_write(bp, &txr->tx_db, txr->tx_prod);
 	}
 
+	if (static_branch_unlikely(&bnxt_xdp_locking_key))
+		spin_unlock(&txr->xdp_tx_lock);
+
 	return nxmit;
 }
 

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h

@@ -10,6 +10,8 @@
 #ifndef BNXT_XDP_H
 #define BNXT_XDP_H
 
+DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
+
 struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 				   struct bnxt_tx_ring_info *txr,
 				   dma_addr_t mapping, u32 len);

drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c

@@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 	base = of_iomap(node, 0);
 	if (!base) {
 		err = -ENOMEM;
-		goto err_close;
+		goto err_put;
 	}
 
 	err = fsl_mc_allocate_irqs(mc_dev);
@@ -210,6 +210,8 @@ err_free_mc_irq:
 	fsl_mc_free_irqs(mc_dev);
 err_unmap:
 	iounmap(base);
+err_put:
+	of_node_put(node);
 err_close:
 	dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
 err_free_mcp:

drivers/net/ethernet/fungible/funcore/fun_dev.c

@@ -586,8 +586,8 @@ static int fun_get_dev_limits(struct fun_dev *fdev)
 	/* Calculate the max QID based on SQ/CQ/doorbell counts.
 	 * SQ/CQ doorbells alternate.
 	 */
-	num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) /
+	num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) >>
-		  (fdev->db_stride * 4);
+		  (2 + NVME_CAP_STRIDE(fdev->cap_reg));
 	fdev->max_qid = min3(cq_count, sq_count, num_dbs / 2) - 1;
 	fdev->kern_end_qid = fdev->max_qid + 1;
 	return 0;

drivers/net/ethernet/intel/ice/ice.h

@@ -301,7 +301,6 @@ enum ice_vsi_state {
 	ICE_VSI_NETDEV_REGISTERED,
 	ICE_VSI_UMAC_FLTR_CHANGED,
 	ICE_VSI_MMAC_FLTR_CHANGED,
-	ICE_VSI_VLAN_FLTR_CHANGED,
 	ICE_VSI_PROMISC_CHANGED,
 	ICE_VSI_STATE_NBITS		/* must be last */
 };
@@ -672,7 +671,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev)
 
 static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi)
 {
-	return !!vsi->xdp_prog;
+	return !!READ_ONCE(vsi->xdp_prog);
 }
 
 static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)

drivers/net/ethernet/intel/ice/ice_fltr.c

@@ -58,7 +58,16 @@ int
 ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 			      u8 promisc_mask)
 {
-	return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false);
+	struct ice_pf *pf = hw->back;
+	int result;
+
+	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false);
+	if (result)
+		dev_err(ice_pf_to_dev(pf),
+			"Error setting promisc mode on VSI %i (rc=%d)\n",
+			vsi->vsi_num, result);
+
+	return result;
 }
 
 /**
@@ -73,7 +82,16 @@ int
 ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 				u8 promisc_mask)
 {
-	return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true);
+	struct ice_pf *pf = hw->back;
+	int result;
+
+	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true);
+	if (result)
+		dev_err(ice_pf_to_dev(pf),
+			"Error clearing promisc mode on VSI %i (rc=%d)\n",
+			vsi->vsi_num, result);
+
+	return result;
 }
 
 /**
@@ -87,7 +105,16 @@ int
 ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 			   u16 vid)
 {
-	return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
+	struct ice_pf *pf = hw->back;
+	int result;
+
+	result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
+	if (result)
+		dev_err(ice_pf_to_dev(pf),
+			"Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n",
+			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
+
+	return result;
 }
 
 /**
@@ -101,7 +128,16 @@ int
 ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 			 u16 vid)
 {
-	return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
+	struct ice_pf *pf = hw->back;
+	int result;
+
+	result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
+	if (result)
+		dev_err(ice_pf_to_dev(pf),
+			"Error setting promisc mode on VSI %i for VID %u (rc=%d)\n",
+			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
+
+	return result;
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -1480,6 +1480,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->tx_tstamps = &pf->ptp.port.tx;
 		ring->dev = dev;
 		ring->count = vsi->num_tx_desc;
+		ring->txq_teid = ICE_INVAL_TEID;
 		if (dvm_ena)
 			ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2;
 		else
@@ -2983,6 +2984,8 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		}
 	}
 
+	if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi))
+		ice_clear_dflt_vsi(pf->first_sw);
 	ice_fltr_remove_all(vsi);
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);

drivers/net/ethernet/intel/ice/ice_main.c

@@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
 static bool ice_vsi_fltr_changed(struct ice_vsi *vsi)
 {
 	return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) ||
-	       test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) ||
+	       test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state);
-	       test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state);
 }
 
 /**
@@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m)
 	if (vsi->type != ICE_VSI_PF)
 		return 0;
 
-	if (ice_vsi_has_non_zero_vlans(vsi))
+	if (ice_vsi_has_non_zero_vlans(vsi)) {
-		status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m);
+		promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX);
-	else
+		status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi,
-		status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0);
+						       promisc_m);
+	} else {
+		status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
+						  promisc_m, 0);
+	}
+
 	return status;
 }
 
@@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m)
 	if (vsi->type != ICE_VSI_PF)
 		return 0;
 
-	if (ice_vsi_has_non_zero_vlans(vsi))
+	if (ice_vsi_has_non_zero_vlans(vsi)) {
-		status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m);
+		promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX);
-	else
+		status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi,
-		status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0);
+							 promisc_m);
+	} else {
+		status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+						    promisc_m, 0);
+	}
+
 	return status;
 }
 
@@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	u32 changed_flags = 0;
-	u8 promisc_m;
 	int err;
 
 	if (!vsi->netdev)
@@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	if (ice_vsi_fltr_changed(vsi)) {
 		clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state);
 		clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state);
-		clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state);
 
 		/* grab the netdev's addr_list_lock */
 		netif_addr_lock_bh(netdev);
@@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	/* check for changes in promiscuous modes */
 	if (changed_flags & IFF_ALLMULTI) {
 		if (vsi->current_netdev_flags & IFF_ALLMULTI) {
-			if (ice_vsi_has_non_zero_vlans(vsi))
+			err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS);
-				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
-			else
-				promisc_m = ICE_MCAST_PROMISC_BITS;
-
-			err = ice_set_promisc(vsi, promisc_m);
 			if (err) {
-				netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n",
-					   vsi->vsi_num);
 				vsi->current_netdev_flags &= ~IFF_ALLMULTI;
 				goto out_promisc;
 			}
 		} else {
 			/* !(vsi->current_netdev_flags & IFF_ALLMULTI) */
-			if (ice_vsi_has_non_zero_vlans(vsi))
+			err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS);
-				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
-			else
-				promisc_m = ICE_MCAST_PROMISC_BITS;
-
-			err = ice_clear_promisc(vsi, promisc_m);
 			if (err) {
-				netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n",
-					   vsi->vsi_num);
 				vsi->current_netdev_flags |= IFF_ALLMULTI;
 				goto out_promisc;
 			}
@@ -2569,7 +2562,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		spin_lock_init(&xdp_ring->tx_lock);
 		for (j = 0; j < xdp_ring->count; j++) {
 			tx_desc = ICE_TX_DESC(xdp_ring, j);
-			tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE);
+			tx_desc->cmd_type_offset_bsz = 0;
 		}
 	}
 
@@ -2765,8 +2758,10 @@ free_qmap:
 
 	ice_for_each_xdp_txq(vsi, i)
 		if (vsi->xdp_rings[i]) {
-			if (vsi->xdp_rings[i]->desc)
+			if (vsi->xdp_rings[i]->desc) {
+				synchronize_rcu();
 				ice_free_tx_ring(vsi->xdp_rings[i]);
+			}
 			kfree_rcu(vsi->xdp_rings[i], rcu);
 			vsi->xdp_rings[i] = NULL;
 		}
@@ -3488,6 +3483,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (!vid)
 		return 0;
 
+	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state))
+		usleep_range(1000, 2000);
+
+	/* Add multicast promisc rule for the VLAN ID to be added if
+	 * all-multicast is currently enabled.
+	 */
+	if (vsi->current_netdev_flags & IFF_ALLMULTI) {
+		ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
+					       ICE_MCAST_VLAN_PROMISC_BITS,
+					       vid);
+		if (ret)
+			goto finish;
+	}
+
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
 	/* Add a switch rule for this VLAN ID so its corresponding VLAN tagged
@@ -3495,8 +3504,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	 */
 	vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0);
 	ret = vlan_ops->add_vlan(vsi, &vlan);
-	if (!ret)
+	if (ret)
-		set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state);
+		goto finish;
+
+	/* If all-multicast is currently enabled and this VLAN ID is only one
+	 * besides VLAN-0 we have to update look-up type of multicast promisc
+	 * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN.
+	 */
+	if ((vsi->current_netdev_flags & IFF_ALLMULTI) &&
+	    ice_vsi_num_non_zero_vlans(vsi) == 1) {
+		ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+					   ICE_MCAST_PROMISC_BITS, 0);
+		ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
+					 ICE_MCAST_VLAN_PROMISC_BITS, 0);
+	}
+
+finish:
+	clear_bit(ICE_CFG_BUSY, vsi->state);
 
 	return ret;
 }
@@ -3522,6 +3546,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (!vid)
 		return 0;
 
+	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state))
+		usleep_range(1000, 2000);
+
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
 	/* Make sure VLAN delete is successful before updating VLAN
@@ -3530,10 +3557,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0);
 	ret = vlan_ops->del_vlan(vsi, &vlan);
 	if (ret)
-		return ret;
+		goto finish;
 
-	set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state);
+	/* Remove multicast promisc rule for the removed VLAN ID if
-	return 0;
+	 * all-multicast is enabled.
+	 */
+	if (vsi->current_netdev_flags & IFF_ALLMULTI)
+		ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+					   ICE_MCAST_VLAN_PROMISC_BITS, vid);
+
+	if (!ice_vsi_has_non_zero_vlans(vsi)) {
+		/* Update look-up type of multicast promisc rule for VLAN 0
+		 * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when
+		 * all-multicast is enabled and VLAN 0 is the only VLAN rule.
+		 */
+		if (vsi->current_netdev_flags & IFF_ALLMULTI) {
+			ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+						   ICE_MCAST_VLAN_PROMISC_BITS,
+						   0);
+			ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
+						 ICE_MCAST_PROMISC_BITS, 0);
+		}
+	}
+
+finish:
+	clear_bit(ICE_CFG_BUSY, vsi->state);
+
+	return ret;
 }
 
 /**
@@ -5475,16 +5525,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 
 	/* Add filter for new MAC. If filter exists, return success */
 	err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI);
-	if (err == -EEXIST)
+	if (err == -EEXIST) {
 		/* Although this MAC filter is already present in hardware it's
 		 * possible in some cases (e.g. bonding) that dev_addr was
 		 * modified outside of the driver and needs to be restored back
 		 * to this value.
 		 */
 		netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac);
-	else if (err)
+
+		return 0;
+	} else if (err) {
 		/* error if the new filter addition failed */
 		err = -EADDRNOTAVAIL;
+	}
 
 err_update_filters:
 	if (err) {

drivers/net/ethernet/intel/ice/ice_virtchnl.c

@@ -1358,9 +1358,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
 				goto error_param;
 			}
 
-			/* Skip queue if not enabled */
 			if (!test_bit(vf_q_id, vf->txq_ena))
-				continue;
+				dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n",
+					vf_q_id, vsi->vsi_num);
 
 			ice_fill_txq_meta(vsi, ring, &txq_meta);
 

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (ice_is_xdp_ena_vsi(vsi)) {
+		synchronize_rcu();
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
@@ -918,7 +920,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *ring;
 
-	if (test_bit(ICE_DOWN, vsi->state))
+	if (test_bit(ICE_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
 	if (!ice_is_xdp_ena_vsi(vsi))

drivers/net/ethernet/marvell/mv643xx_eth.c

@@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 	}
 
 	ret = of_get_mac_address(pnp, ppd.mac_addr);
-	if (ret)
+	if (ret == -EPROBE_DEFER)
 		return ret;
 
 	mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size);

drivers/net/ethernet/micrel/Kconfig

@@ -28,6 +28,7 @@ config KS8842
 config KS8851
 	tristate "Micrel KS8851 SPI"
 	depends on SPI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MII
 	select CRC32
 	select EEPROM_93CX6
@@ -39,6 +40,7 @@ config KS8851
 config KS8851_MLL
 	tristate "Micrel KS8851 MLL"
 	depends on HAS_IOMEM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MII
 	select CRC32
 	select EEPROM_93CX6

drivers/net/ethernet/myricom/myri10ge/myri10ge.c

@@ -2903,11 +2903,9 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb,
 		status = myri10ge_xmit(curr, dev);
 		if (status != 0) {
 			dev_kfree_skb_any(curr);
-			if (segs != NULL) {
+			skb_list_walk_safe(next, curr, next) {
-				curr = segs;
-				segs = next;
 				curr->next = NULL;
-				dev_kfree_skb_any(segs);
+				dev_kfree_skb_any(curr);
 			}
 			goto drop;
 		}

drivers/net/ethernet/qlogic/qed/qed_debug.c

@@ -489,7 +489,7 @@ struct split_type_defs {
 
 #define STATIC_DEBUG_LINE_DWORDS	9
 
-#define NUM_COMMON_GLOBAL_PARAMS	11
+#define NUM_COMMON_GLOBAL_PARAMS	10
 
 #define MAX_RECURSION_DEPTH		10
 

drivers/net/ethernet/qlogic/qede/qede_fp.c

@@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq,
 	buf = page_address(bd->data) + bd->page_offset;
 	skb = build_skb(buf, rxq->rx_buf_seg_size);
 
+	if (unlikely(!skb))
+		return NULL;
+
 	skb_reserve(skb, pad);
 	skb_put(skb, len);
 

drivers/net/ethernet/sfc/efx_channels.c

@@ -786,6 +786,85 @@ void efx_remove_channels(struct efx_nic *efx)
 	kfree(efx->xdp_tx_queues);
 }
 
+static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number,
+				struct efx_tx_queue *tx_queue)
+{
+	if (xdp_queue_number >= efx->xdp_tx_queue_count)
+		return -EINVAL;
+
+	netif_dbg(efx, drv, efx->net_dev,
+		  "Channel %u TXQ %u is XDP %u, HW %u\n",
+		  tx_queue->channel->channel, tx_queue->label,
+		  xdp_queue_number, tx_queue->queue);
+	efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
+	return 0;
+}
+
+static void efx_set_xdp_channels(struct efx_nic *efx)
+{
+	struct efx_tx_queue *tx_queue;
+	struct efx_channel *channel;
+	unsigned int next_queue = 0;
+	int xdp_queue_number = 0;
+	int rc;
+
+	/* We need to mark which channels really have RX and TX
+	 * queues, and adjust the TX queue numbers if we have separate
+	 * RX-only and TX-only channels.
+	 */
+	efx_for_each_channel(channel, efx) {
+		if (channel->channel < efx->tx_channel_offset)
+			continue;
+
+		if (efx_channel_is_xdp_tx(channel)) {
+			efx_for_each_channel_tx_queue(tx_queue, channel) {
+				tx_queue->queue = next_queue++;
+				rc = efx_set_xdp_tx_queue(efx, xdp_queue_number,
+							  tx_queue);
+				if (rc == 0)
+					xdp_queue_number++;
+			}
+		} else {
+			efx_for_each_channel_tx_queue(tx_queue, channel) {
+				tx_queue->queue = next_queue++;
+				netif_dbg(efx, drv, efx->net_dev,
+					  "Channel %u TXQ %u is HW %u\n",
+					  channel->channel, tx_queue->label,
+					  tx_queue->queue);
+			}
+
+			/* If XDP is borrowing queues from net stack, it must
+			 * use the queue with no csum offload, which is the
+			 * first one of the channel
+			 * (note: tx_queue_by_type is not initialized yet)
+			 */
+			if (efx->xdp_txq_queues_mode ==
+			    EFX_XDP_TX_QUEUES_BORROWED) {
+				tx_queue = &channel->tx_queue[0];
+				rc = efx_set_xdp_tx_queue(efx, xdp_queue_number,
+							  tx_queue);
+				if (rc == 0)
+					xdp_queue_number++;
+			}
+		}
+	}
+	WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED &&
+		xdp_queue_number != efx->xdp_tx_queue_count);
+	WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED &&
+		xdp_queue_number > efx->xdp_tx_queue_count);
+
+	/* If we have more CPUs than assigned XDP TX queues, assign the already
+	 * existing queues to the exceeding CPUs
+	 */
+	next_queue = 0;
+	while (xdp_queue_number < efx->xdp_tx_queue_count) {
+		tx_queue = efx->xdp_tx_queues[next_queue++];
+		rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
+		if (rc == 0)
+			xdp_queue_number++;
+	}
+}
+
 int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 {
 	struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
@@ -857,6 +936,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 		efx_init_napi_channel(efx->channel[i]);
 	}
 
+	efx_set_xdp_channels(efx);
 out:
 	/* Destroy unused channel structures */
 	for (i = 0; i < efx->n_channels; i++) {
@@ -889,26 +969,9 @@ rollback:
 	goto out;
 }
 
-static inline int
-efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number,
-		     struct efx_tx_queue *tx_queue)
-{
-	if (xdp_queue_number >= efx->xdp_tx_queue_count)
-		return -EINVAL;
-
-	netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
-		  tx_queue->channel->channel, tx_queue->label,
-		  xdp_queue_number, tx_queue->queue);
-	efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
-	return 0;
-}
-
 int efx_set_channels(struct efx_nic *efx)
 {
-	struct efx_tx_queue *tx_queue;
 	struct efx_channel *channel;
-	unsigned int next_queue = 0;
-	int xdp_queue_number;
 	int rc;
 
 	efx->tx_channel_offset =
@@ -926,61 +989,14 @@ int efx_set_channels(struct efx_nic *efx)
 			return -ENOMEM;
 	}
 
-	/* We need to mark which channels really have RX and TX
-	 * queues, and adjust the TX queue numbers if we have separate
-	 * RX-only and TX-only channels.
-	 */
-	xdp_queue_number = 0;
 	efx_for_each_channel(channel, efx) {
 		if (channel->channel < efx->n_rx_channels)
 			channel->rx_queue.core_index = channel->channel;
 		else
 			channel->rx_queue.core_index = -1;
-
-		if (channel->channel >= efx->tx_channel_offset) {
-			if (efx_channel_is_xdp_tx(channel)) {
-				efx_for_each_channel_tx_queue(tx_queue, channel) {
-					tx_queue->queue = next_queue++;
-					rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
-					if (rc == 0)
-						xdp_queue_number++;
-				}
-			} else {
-				efx_for_each_channel_tx_queue(tx_queue, channel) {
-					tx_queue->queue = next_queue++;
-					netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n",
-						  channel->channel, tx_queue->label,
-						  tx_queue->queue);
-				}
-
-				/* If XDP is borrowing queues from net stack, it must use the queue
-				 * with no csum offload, which is the first one of the channel
-				 * (note: channel->tx_queue_by_type is not initialized yet)
-				 */
-				if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) {
-					tx_queue = &channel->tx_queue[0];
-					rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
-					if (rc == 0)
-						xdp_queue_number++;
-				}
-			}
-		}
 	}
-	WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED &&
-		xdp_queue_number != efx->xdp_tx_queue_count);
-	WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED &&
-		xdp_queue_number > efx->xdp_tx_queue_count);
 
-	/* If we have more CPUs than assigned XDP TX queues, assign the already
+	efx_set_xdp_channels(efx);
-	 * existing queues to the exceeding CPUs
-	 */
-	next_queue = 0;
-	while (xdp_queue_number < efx->xdp_tx_queue_count) {
-		tx_queue = efx->xdp_tx_queues[next_queue++];
-		rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
-		if (rc == 0)
-			xdp_queue_number++;
-	}
 
 	rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
 	if (rc)
@@ -1124,7 +1140,7 @@ void efx_start_channels(struct efx_nic *efx)
 	struct efx_rx_queue *rx_queue;
 	struct efx_channel *channel;
 
-	efx_for_each_channel(channel, efx) {
+	efx_for_each_channel_rev(channel, efx) {
 		efx_for_each_channel_tx_queue(tx_queue, channel) {
 			efx_init_tx_queue(tx_queue);
 			atomic_inc(&efx->active_queues);

drivers/net/ethernet/sfc/rx_common.c

@@ -150,6 +150,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue)
 	struct efx_nic *efx = rx_queue->efx;
 	int i;
 
+	if (unlikely(!rx_queue->page_ring))
+		return;
+
 	/* Unmap and release the pages in the recycle ring. Remove the ring. */
 	for (i = 0; i <= rx_queue->page_ptr_mask; i++) {
 		struct page *page = rx_queue->page_ring[i];

drivers/net/ethernet/sfc/tx.c

@@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs,
 	if (unlikely(!tx_queue))
 		return -EINVAL;
 
+	if (!tx_queue->initialised)
+		return -EINVAL;
+
 	if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED)
 		HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu);
 

drivers/net/ethernet/sfc/tx_common.c

@@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 	netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
 		  "shutting down TX queue %d\n", tx_queue->queue);
 
+	tx_queue->initialised = false;
+
 	if (!tx_queue->buffer)
 		return;
 

drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c

@@ -205,7 +205,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
 
-struct pci_driver loongson_dwmac_driver = {
+static struct pci_driver loongson_dwmac_driver = {
 	.name = "dwmac-loongson-pci",
 	.id_table = loongson_dwmac_id_table,
 	.probe = loongson_dwmac_probe,

drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c

@@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	plat->phylink_node = np;
 
 	/* Get max speed of operation from device tree */
-	if (of_property_read_u32(np, "max-speed", &plat->max_speed))
+	of_property_read_u32(np, "max-speed", &plat->max_speed);
-		plat->max_speed = -1;
 
 	plat->bus_id = of_alias_get_id(np, "ethernet");
 	if (plat->bus_id < 0)

drivers/net/ethernet/xilinx/xilinx_axienet.h

@@ -433,8 +433,6 @@ struct axienet_local {
 	struct net_device *ndev;
 	struct device *dev;
 
-	struct device_node *phy_node;
-
 	struct phylink *phylink;
 	struct phylink_config phylink_config;
 

drivers/net/ethernet/xilinx/xilinx_axienet_main.c

@@ -2064,25 +2064,33 @@ static int axienet_probe(struct platform_device *pdev)
 	if (ret)
 		goto cleanup_clk;
 
-	lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	ret = axienet_mdio_setup(lp);
-	if (lp->phy_node) {
+	if (ret)
-		ret = axienet_mdio_setup(lp);
+		dev_warn(&pdev->dev,
-		if (ret)
+			 "error registering MDIO bus: %d\n", ret);
-			dev_warn(&pdev->dev,
+
-				 "error registering MDIO bus: %d\n", ret);
-	}
 	if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII ||
 	    lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) {
-		if (!lp->phy_node) {
+		np = of_parse_phandle(pdev->dev.of_node, "pcs-handle", 0);
-			dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n");
+		if (!np) {
+			/* Deprecated: Always use "pcs-handle" for pcs_phy.
+			 * Falling back to "phy-handle" here is only for
+			 * backward compatibility with old device trees.
+			 */
+			np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+		}
+		if (!np) {
+			dev_err(&pdev->dev, "pcs-handle (preferred) or phy-handle required for 1000BaseX/SGMII\n");
 			ret = -EINVAL;
 			goto cleanup_mdio;
 		}
-		lp->pcs_phy = of_mdio_find_device(lp->phy_node);
+		lp->pcs_phy = of_mdio_find_device(np);
 		if (!lp->pcs_phy) {
 			ret = -EPROBE_DEFER;
+			of_node_put(np);
 			goto cleanup_mdio;
 		}
+		of_node_put(np);
 		lp->pcs.ops = &axienet_pcs_ops;
 		lp->pcs.poll = true;
 	}
@@ -2125,8 +2133,6 @@ cleanup_mdio:
 		put_device(&lp->pcs_phy->dev);
 	if (lp->mii_bus)
 		axienet_mdio_teardown(lp);
-	of_node_put(lp->phy_node);
-
 cleanup_clk:
 	clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks);
 	clk_disable_unprepare(lp->axi_clk);
@@ -2155,9 +2161,6 @@ static int axienet_remove(struct platform_device *pdev)
 	clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks);
 	clk_disable_unprepare(lp->axi_clk);
 
-	of_node_put(lp->phy_node);
-	lp->phy_node = NULL;
-
 	free_netdev(ndev);
 
 	return 0;

drivers/net/mctp/mctp-i2c.c

@@ -553,7 +553,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01;
 	mhdr->ver = 0x01;
 
-	return 0;
+	return sizeof(struct mctp_i2c_hdr);
 }
 
 static int mctp_i2c_tx_thread(void *data)

drivers/net/mdio/mdio-mscc-miim.c

@@ -107,6 +107,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum)
 	u32 val;
 	int ret;
 
+	if (regnum & MII_ADDR_C45)
+		return -EOPNOTSUPP;
+
 	ret = mscc_miim_wait_pending(bus);
 	if (ret)
 		goto out;
@@ -150,6 +153,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id,
 	struct mscc_miim_dev *miim = bus->priv;
 	int ret;
 
+	if (regnum & MII_ADDR_C45)
+		return -EOPNOTSUPP;
+
 	ret = mscc_miim_wait_pending(bus);
 	if (ret < 0)
 		goto out;

drivers/net/phy/micrel.c

@@ -99,15 +99,6 @@
 #define PTP_TIMESTAMP_EN_PDREQ_			BIT(2)
 #define PTP_TIMESTAMP_EN_PDRES_			BIT(3)
 
-#define PTP_RX_LATENCY_1000			0x0224
-#define PTP_TX_LATENCY_1000			0x0225
-
-#define PTP_RX_LATENCY_100			0x0222
-#define PTP_TX_LATENCY_100			0x0223
-
-#define PTP_RX_LATENCY_10			0x0220
-#define PTP_TX_LATENCY_10			0x0221
-
 #define PTP_TX_PARSE_L2_ADDR_EN			0x0284
 #define PTP_RX_PARSE_L2_ADDR_EN			0x0244
 
@@ -268,15 +259,6 @@ struct lan8814_ptp_rx_ts {
 	u16 seq_id;
 };
 
-struct kszphy_latencies {
-	u16 rx_10;
-	u16 tx_10;
-	u16 rx_100;
-	u16 tx_100;
-	u16 rx_1000;
-	u16 tx_1000;
-};
-
 struct kszphy_ptp_priv {
 	struct mii_timestamper mii_ts;
 	struct phy_device *phydev;
@@ -296,7 +278,6 @@ struct kszphy_ptp_priv {
 
 struct kszphy_priv {
 	struct kszphy_ptp_priv ptp_priv;
-	struct kszphy_latencies latencies;
 	const struct kszphy_type *type;
 	int led_mode;
 	bool rmii_ref_clk_sel;
@@ -304,14 +285,6 @@ struct kszphy_priv {
 	u64 stats[ARRAY_SIZE(kszphy_hw_stats)];
 };
 
-static struct kszphy_latencies lan8814_latencies = {
-	.rx_10		= 0x22AA,
-	.tx_10		= 0x2E4A,
-	.rx_100		= 0x092A,
-	.tx_100		= 0x02C1,
-	.rx_1000	= 0x01AD,
-	.tx_1000	= 0x00C9,
-};
 static const struct kszphy_type ksz8021_type = {
 	.led_mode_reg		= MII_KSZPHY_CTRL_2,
 	.has_broadcast_disable	= true,
@@ -2618,55 +2591,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev)
 	return 0;
 }
 
-static int lan8814_read_status(struct phy_device *phydev)
-{
-	struct kszphy_priv *priv = phydev->priv;
-	struct kszphy_latencies *latencies = &priv->latencies;
-	int err;
-	int regval;
-
-	err = genphy_read_status(phydev);
-	if (err)
-		return err;
-
-	switch (phydev->speed) {
-	case SPEED_1000:
-		lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_1000,
-				      latencies->rx_1000);
-		lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_1000,
-				      latencies->tx_1000);
-		break;
-	case SPEED_100:
-		lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_100,
-				      latencies->rx_100);
-		lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_100,
-				      latencies->tx_100);
-		break;
-	case SPEED_10:
-		lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_10,
-				      latencies->rx_10);
-		lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_10,
-				      latencies->tx_10);
-		break;
-	default:
-		break;
-	}
-
-	/* Make sure the PHY is not broken. Read idle error count,
-	 * and reset the PHY if it is maxed out.
-	 */
-	regval = phy_read(phydev, MII_STAT1000);
-	if ((regval & 0xFF) == 0xFF) {
-		phy_init_hw(phydev);
-		phydev->link = 0;
-		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
-			phydev->drv->config_intr(phydev);
-		return genphy_config_aneg(phydev);
-	}
-
-	return 0;
-}
-
 static int lan8814_config_init(struct phy_device *phydev)
 {
 	int val;
@@ -2690,30 +2614,8 @@ static int lan8814_config_init(struct phy_device *phydev)
 	return 0;
 }
 
-static void lan8814_parse_latency(struct phy_device *phydev)
-{
-	const struct device_node *np = phydev->mdio.dev.of_node;
-	struct kszphy_priv *priv = phydev->priv;
-	struct kszphy_latencies *latency = &priv->latencies;
-	u32 val;
-
-	if (!of_property_read_u32(np, "lan8814,latency_rx_10", &val))
-		latency->rx_10 = val;
-	if (!of_property_read_u32(np, "lan8814,latency_tx_10", &val))
-		latency->tx_10 = val;
-	if (!of_property_read_u32(np, "lan8814,latency_rx_100", &val))
-		latency->rx_100 = val;
-	if (!of_property_read_u32(np, "lan8814,latency_tx_100", &val))
-		latency->tx_100 = val;
-	if (!of_property_read_u32(np, "lan8814,latency_rx_1000", &val))
-		latency->rx_1000 = val;
-	if (!of_property_read_u32(np, "lan8814,latency_tx_1000", &val))
-		latency->tx_1000 = val;
-}
-
 static int lan8814_probe(struct phy_device *phydev)
 {
-	const struct device_node *np = phydev->mdio.dev.of_node;
 	struct kszphy_priv *priv;
 	u16 addr;
 	int err;
@@ -2724,13 +2626,10 @@ static int lan8814_probe(struct phy_device *phydev)
 
 	priv->led_mode = -1;
 
-	priv->latencies = lan8814_latencies;
-
 	phydev->priv = priv;
 
 	if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) ||
-	    !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING) ||
+	    !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING))
-	    of_property_read_bool(np, "lan8814,ignore-ts"))
 		return 0;
 
 	/* Strap-in value for PHY address, below register read gives starting
@@ -2746,7 +2645,6 @@ static int lan8814_probe(struct phy_device *phydev)
 			return err;
 	}
 
-	lan8814_parse_latency(phydev);
 	lan8814_ptp_init(phydev);
 
 	return 0;
@@ -2928,7 +2826,7 @@ static struct phy_driver ksphy_driver[] = {
 	.config_init	= lan8814_config_init,
 	.probe		= lan8814_probe,
 	.soft_reset	= genphy_soft_reset,
-	.read_status	= lan8814_read_status,
+	.read_status	= ksz9031_read_status,
 	.get_sset_count	= kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,

drivers/net/slip/slip.c

@@ -469,7 +469,7 @@ static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	spin_lock(&sl->lock);
 
 	if (netif_queue_stopped(dev)) {
-		if (!netif_running(dev))
+		if (!netif_running(dev) || !sl->tty)
 			goto out;
 
 		/* May be we must check transmitter timeout here ?

drivers/net/usb/aqc111.c

@@ -1102,10 +1102,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	if (start_of_descs != desc_offset)
 		goto err;
 
-	/* self check desc_offset from header*/
+	/* self check desc_offset from header and make sure that the
-	if (desc_offset >= skb_len)
+	 * bounds of the metadata array are inside the SKB
+	 */
+	if (pkt_count * 2 + desc_offset >= skb_len)
 		goto err;
 
+	/* Packets must not overlap the metadata array */
+	skb_trim(skb, desc_offset);
+
 	if (pkt_count == 0)
 		goto err;
 

drivers/net/vrf.c

@@ -1265,6 +1265,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
 	eth = (struct ethhdr *)skb->data;
 
 	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
 
 	/* we set the ethernet destination and the source addresses to the
 	 * address of the VRF device.
@@ -1294,9 +1295,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
  */
 static int vrf_add_mac_header_if_unset(struct sk_buff *skb,
 				       struct net_device *vrf_dev,
-				       u16 proto)
+				       u16 proto, struct net_device *orig_dev)
 {
-	if (skb_mac_header_was_set(skb))
+	if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev))
 		return 0;
 
 	return vrf_prepare_mac_header(skb, vrf_dev, proto);
@@ -1402,6 +1403,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 
 	/* if packet is NDISC then keep the ingress interface */
 	if (!is_ndisc) {
+		struct net_device *orig_dev = skb->dev;
+
 		vrf_rx_stats(vrf_dev, skb->len);
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
@@ -1410,7 +1413,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 			int err;
 
 			err = vrf_add_mac_header_if_unset(skb, vrf_dev,
-							  ETH_P_IPV6);
+							  ETH_P_IPV6,
+							  orig_dev);
 			if (likely(!err)) {
 				skb_push(skb, skb->mac_len);
 				dev_queue_xmit_nit(skb, vrf_dev);
@@ -1440,6 +1444,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 				  struct sk_buff *skb)
 {
+	struct net_device *orig_dev = skb->dev;
+
 	skb->dev = vrf_dev;
 	skb->skb_iif = vrf_dev->ifindex;
 	IPCB(skb)->flags |= IPSKB_L3SLAVE;
@@ -1460,7 +1466,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 	if (!list_empty(&vrf_dev->ptype_all)) {
 		int err;
 
-		err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP);
+		err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP,
+						  orig_dev);
 		if (likely(!err)) {
 			skb_push(skb, skb->mac_len);
 			dev_queue_xmit_nit(skb, vrf_dev);

drivers/pci/controller/pci-hyperv.c

@@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev,
 	hbus->bridge->domain_nr = dom;
 #ifdef CONFIG_X86
 	hbus->sysdata.domain = dom;
+#elif defined(CONFIG_ARM64)
+	/*
+	 * Set the PCI bus parent to be the corresponding VMbus
+	 * device. Then the VMbus device will be assigned as the
+	 * ACPI companion in pcibios_root_bridge_prepare() and
+	 * pci_dma_configure() will propagate device coherence
+	 * information to devices created on the bus.
+	 */
+	hbus->sysdata.parent = hdev->device.parent;
 #endif
 
 	hbus->hdev = hdev;

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -163,6 +163,7 @@ struct mlx5_vdpa_net {
 	u32 cur_num_vqs;
 	struct notifier_block nb;
 	struct vdpa_callback config_cb;
+	struct mlx5_vdpa_wq_ent cvq_ent;
 };
 
 static void free_resources(struct mlx5_vdpa_net *ndev);
@@ -1658,6 +1659,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
 	mvdev = wqent->mvdev;
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 	cvq = &mvdev->cvq;
+
+	mutex_lock(&ndev->reslock);
+
+	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
+		goto out;
+
 	if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)))
 		goto out;
 
@@ -1696,9 +1703,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
 
 		if (vringh_need_notify_iotlb(&cvq->vring))
 			vringh_notify(&cvq->vring);
+
+		queue_work(mvdev->wq, &wqent->work);
+		break;
 	}
+
 out:
-	kfree(wqent);
+	mutex_unlock(&ndev->reslock);
 }
 
 static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
@@ -1706,7 +1717,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	struct mlx5_vdpa_virtqueue *mvq;
-	struct mlx5_vdpa_wq_ent *wqent;
 
 	if (!is_index_valid(mvdev, idx))
 		return;
@@ -1715,13 +1725,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
 		if (!mvdev->wq || !mvdev->cvq.ready)
 			return;
 
-		wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
+		queue_work(mvdev->wq, &ndev->cvq_ent.work);
-		if (!wqent)
-			return;
-
-		wqent->mvdev = mvdev;
-		INIT_WORK(&wqent->work, mlx5_cvq_kick_handler);
-		queue_work(mvdev->wq, &wqent->work);
 		return;
 	}
 
@@ -2180,7 +2184,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
 		goto err_mr;
 
 	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
-		return 0;
+		goto err_mr;
 
 	restore_channels_info(ndev);
 	err = setup_driver(mvdev);
@@ -2195,12 +2199,14 @@ err_mr:
 	return err;
 }
 
+/* reslock must be held for this function */
 static int setup_driver(struct mlx5_vdpa_dev *mvdev)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
 
-	mutex_lock(&ndev->reslock);
+	WARN_ON(!mutex_is_locked(&ndev->reslock));
+
 	if (ndev->setup) {
 		mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n");
 		err = 0;
@@ -2230,7 +2236,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev)
 		goto err_fwd;
 	}
 	ndev->setup = true;
-	mutex_unlock(&ndev->reslock);
 
 	return 0;
 
@@ -2241,23 +2246,23 @@ err_tir:
 err_rqt:
 	teardown_virtqueues(ndev);
 out:
-	mutex_unlock(&ndev->reslock);
 	return err;
 }
 
+/* reslock must be held for this function */
 static void teardown_driver(struct mlx5_vdpa_net *ndev)
 {
-	mutex_lock(&ndev->reslock);
+
+	WARN_ON(!mutex_is_locked(&ndev->reslock));
+
 	if (!ndev->setup)
-		goto out;
+		return;
 
 	remove_fwd_to_tir(ndev);
 	destroy_tir(ndev);
 	destroy_rqt(ndev);
 	teardown_virtqueues(ndev);
 	ndev->setup = false;
-out:
-	mutex_unlock(&ndev->reslock);
 }
 
 static void clear_vqs_ready(struct mlx5_vdpa_net *ndev)
@@ -2278,6 +2283,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 
 	print_status(mvdev, status, true);
 
+	mutex_lock(&ndev->reslock);
+
 	if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) {
 		if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
 			err = setup_driver(mvdev);
@@ -2287,16 +2294,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 			}
 		} else {
 			mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n");
-			return;
+			goto err_clear;
 		}
 	}
 
 	ndev->mvdev.status = status;
+	mutex_unlock(&ndev->reslock);
 	return;
 
 err_setup:
 	mlx5_vdpa_destroy_mr(&ndev->mvdev);
 	ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED;
+err_clear:
+	mutex_unlock(&ndev->reslock);
 }
 
 static int mlx5_vdpa_reset(struct vdpa_device *vdev)
@@ -2306,6 +2316,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 
 	print_status(mvdev, 0, true);
 	mlx5_vdpa_info(mvdev, "performing device reset\n");
+
+	mutex_lock(&ndev->reslock);
 	teardown_driver(ndev);
 	clear_vqs_ready(ndev);
 	mlx5_vdpa_destroy_mr(&ndev->mvdev);
@@ -2318,6 +2330,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 		if (mlx5_vdpa_create_mr(mvdev, NULL))
 			mlx5_vdpa_warn(mvdev, "create MR failed\n");
 	}
+	mutex_unlock(&ndev->reslock);
 
 	return 0;
 }
@@ -2353,19 +2366,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
 static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	bool change_map;
 	int err;
 
+	mutex_lock(&ndev->reslock);
+
 	err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
 	if (err) {
 		mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
-		return err;
+		goto err;
 	}
 
 	if (change_map)
-		return mlx5_vdpa_change_map(mvdev, iotlb);
+		err = mlx5_vdpa_change_map(mvdev, iotlb);
 
-	return 0;
+err:
+	mutex_unlock(&ndev->reslock);
+	return err;
 }
 
 static void mlx5_vdpa_free(struct vdpa_device *vdev)
@@ -2740,6 +2758,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	if (err)
 		goto err_mr;
 
+	ndev->cvq_ent.mvdev = mvdev;
+	INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler);
 	mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq");
 	if (!mvdev->wq) {
 		err = -ENOMEM;

drivers/virtio/virtio.c

@@ -526,9 +526,8 @@ int virtio_device_restore(struct virtio_device *dev)
 			goto err;
 	}
 
-	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
+	/* Finally, tell the device we're all set */
-	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
+	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
-		virtio_device_ready(dev);
 
 	virtio_config_enable(dev);
 

fs/btrfs/extent_io.h

@@ -118,7 +118,7 @@ struct btrfs_bio_ctrl {
  */
 struct extent_changeset {
 	/* How many bytes are set/cleared in this operation */
-	unsigned int bytes_changed;
+	u64 bytes_changed;
 
 	/* Changed ranges */
 	struct ulist range_changed;

fs/btrfs/file.c

@@ -2957,8 +2957,9 @@ out:
 	return ret;
 }
 
-static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len)
 {
+	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_state *cached_state = NULL;
@@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		goto out_only_mutex;
 	}
 
+	ret = file_modified(file);
+	if (ret)
+		goto out_only_mutex;
+
 	lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode)));
 	lockend = round_down(offset + len,
 			     btrfs_inode_sectorsize(BTRFS_I(inode))) - 1;
@@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		return -EOPNOTSUPP;
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return btrfs_punch_hole(inode, offset, len);
+		return btrfs_punch_hole(file, offset, len);
 
 	/*
 	 * Only trigger disk allocation, don't trigger qgroup reserve
@@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode,
 			goto out;
 	}
 
+	ret = file_modified(file);
+	if (ret)
+		goto out;
+
 	/*
 	 * TODO: Move these two operations after we have checked
 	 * accurate reserved space, or fallocate can still fail but

fs/btrfs/inode.c

@@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 	int ret = 0;
 
 	if (btrfs_is_free_space_inode(inode)) {
-		WARN_ON_ONCE(1);
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -4488,6 +4487,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 			   dest->root_key.objectid);
 		return -EPERM;
 	}
+	if (atomic_read(&dest->nr_swapfiles)) {
+		spin_unlock(&dest->root_item_lock);
+		btrfs_warn(fs_info,
+			   "attempt to delete subvolume %llu with active swapfile",
+			   root->root_key.objectid);
+		return -EPERM;
+	}
 	root_flags = btrfs_root_flags(&dest->root_item);
 	btrfs_set_root_flags(&dest->root_item,
 			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
@@ -11107,8 +11113,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	 * set. We use this counter to prevent snapshots. We must increment it
 	 * before walking the extents because we don't want a concurrent
 	 * snapshot to run after we've already checked the extents.
+	 *
+	 * It is possible that subvolume is marked for deletion but still not
+	 * removed yet. To prevent this race, we check the root status before
+	 * activating the swapfile.
 	 */
+	spin_lock(&root->root_item_lock);
+	if (btrfs_root_dead(root)) {
+		spin_unlock(&root->root_item_lock);
+
+		btrfs_exclop_finish(fs_info);
+		btrfs_warn(fs_info,
+		"cannot activate swapfile because subvolume %llu is being deleted",
+			root->root_key.objectid);
+		return -EPERM;
+	}
 	atomic_inc(&root->nr_swapfiles);
+	spin_unlock(&root->root_item_lock);
 
 	isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);
 

fs/btrfs/ioctl.c

@@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em)
 }
 
 static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
-				     bool locked)
+				     u32 extent_thresh, u64 newer_than, bool locked)
 {
 	struct extent_map *next;
 	bool ret = false;
@@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 		return false;
 
 	/*
-	 * We want to check if the next extent can be merged with the current
+	 * Here we need to pass @newer_then when checking the next extent, or
-	 * one, which can be an extent created in a past generation, so we pass
+	 * we will hit a case we mark current extent for defrag, but the next
-	 * a minimum generation of 0 to defrag_lookup_extent().
+	 * one will not be a target.
+	 * This will just cause extra IO without really reducing the fragments.
 	 */
-	next = defrag_lookup_extent(inode, em->start + em->len, 0, locked);
+	next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked);
 	/* No more em or hole */
 	if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
 		goto out;
@@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 	 */
 	if (next->len >= get_extent_max_capacity(em))
 		goto out;
+	/* Skip older extent */
+	if (next->generation < newer_than)
+		goto out;
+	/* Also check extent size */
+	if (next->len >= extent_thresh)
+		goto out;
+
 	ret = true;
 out:
 	free_extent_map(next);
@@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 			goto next;
 
 		next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
-							  locked);
+						extent_thresh, newer_than, locked);
 		if (!next_mergeable) {
 			struct defrag_target_range *last;
 

fs/btrfs/volumes.c

@@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path)
 	path_put(&path);
 }
 
-static int btrfs_rm_dev_item(struct btrfs_device *device)
+static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans,
+			     struct btrfs_device *device)
 {
 	struct btrfs_root *root = device->fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct btrfs_trans_handle *trans;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans)) {
-		btrfs_free_path(path);
-		return PTR_ERR(trans);
-	}
 	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
@@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device)
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
-		btrfs_abort_transaction(trans, ret);
-		btrfs_end_transaction(trans);
 		goto out;
 	}
 
 	ret = btrfs_del_item(trans, root, path);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		btrfs_end_transaction(trans);
-	}
-
 out:
 	btrfs_free_path(path);
-	if (!ret)
-		ret = btrfs_commit_transaction(trans);
 	return ret;
 }
 
@@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
 		    struct block_device **bdev, fmode_t *mode)
 {
+	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
@@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1);
 	if (ret)
-		goto out;
+		return ret;
 
 	device = btrfs_find_device(fs_info->fs_devices, args);
 	if (!device) {
@@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 			ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
 		else
 			ret = -ENOENT;
-		goto out;
+		return ret;
 	}
 
 	if (btrfs_pinned_by_swapfile(fs_info, device)) {
 		btrfs_warn_in_rcu(fs_info,
 		  "cannot remove device %s (devid %llu) due to active swapfile",
 				  rcu_str_deref(device->name), device->devid);
-		ret = -ETXTBSY;
+		return -ETXTBSY;
-		goto out;
 	}
 
-	if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
+	if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
-		ret = BTRFS_ERROR_DEV_TGT_REPLACE;
+		return BTRFS_ERROR_DEV_TGT_REPLACE;
-		goto out;
-	}
 
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
-	    fs_info->fs_devices->rw_devices == 1) {
+	    fs_info->fs_devices->rw_devices == 1)
-		ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
+		return BTRFS_ERROR_DEV_ONLY_WRITABLE;
-		goto out;
-	}
 
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		mutex_lock(&fs_info->chunk_mutex);
@@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	if (ret)
 		goto error_undo;
 
-	/*
+	trans = btrfs_start_transaction(fs_info->chunk_root, 0);
-	 * TODO: the superblock still includes this device in its num_devices
+	if (IS_ERR(trans)) {
-	 * counter although write_all_supers() is not locked out. This
+		ret = PTR_ERR(trans);
-	 * could give a filesystem state which requires a degraded mount.
-	 */
-	ret = btrfs_rm_dev_item(device);
-	if (ret)
 		goto error_undo;
+	}
+
+	ret = btrfs_rm_dev_item(trans, device);
+	if (ret) {
+		/* Any error in dev item removal is critical */
+		btrfs_crit(fs_info,
+			   "failed to remove device item for devid %llu: %d",
+			   device->devid, ret);
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	btrfs_scrub_cancel_dev(device);
@@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		free_fs_devices(cur_devices);
 	}
 
-out:
+	ret = btrfs_commit_transaction(trans);
+
 	return ret;
 
 error_undo:
@@ -2240,7 +2231,7 @@ error_undo:
 		device->fs_devices->rw_devices++;
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
-	goto out;
+	return ret;
 }
 
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)

fs/btrfs/zoned.c

@@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
 
 	map = em->map_lookup;
 	/* We only support single profile for now */
-	ASSERT(map->num_stripes == 1);
 	device = map->stripes[0].dev;
 
 	free_extent_map(em);
@@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group)
 
 bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
 {
+	struct btrfs_fs_info *fs_info = fs_devices->fs_info;
 	struct btrfs_device *device;
 	bool ret = false;
 
-	if (!btrfs_is_zoned(fs_devices->fs_info))
+	if (!btrfs_is_zoned(fs_info))
 		return true;
 
-	/* Non-single profiles are not supported yet */
-	ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0);
-
 	/* Check if there is a device with active zones left */
-	mutex_lock(&fs_devices->device_list_mutex);
+	mutex_lock(&fs_info->chunk_mutex);
-	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
 		struct btrfs_zoned_device_info *zinfo = device->zone_info;
 
 		if (!device->bdev)
@@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
 			break;
 		}
 	}
-	mutex_unlock(&fs_devices->device_list_mutex);
+	mutex_unlock(&fs_info->chunk_mutex);
 
 	return ret;
 }

include/asm-generic/mshyperv.h

@@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void);
 u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
+void hv_setup_dma_ops(struct device *dev, bool coherent);
 void *hv_map_memory(void *addr, unsigned long size);
 void hv_unmap_memory(void *addr);
 #else /* CONFIG_HYPERV */

include/linux/bpf_verifier.h

@@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type)
 	return type & ~BPF_BASE_TYPE_MASK;
 }
 
+/* only use after check_attach_btf_id() */
 static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
 {
-	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
+	return prog->type == BPF_PROG_TYPE_EXT ?
+		prog->aux->dst_prog->type : prog->type;
 }
 
 #endif /* _LINUX_BPF_VERIFIER_H */

include/linux/virtio_config.h

@@ -23,8 +23,6 @@ struct virtio_shm_region {
  *       any of @get/@set, @get_status/@set_status, or @get_features/
  *       @finalize_features are NOT safe to be called from an atomic
  *       context.
- * @enable_cbs: enable the callbacks
- *      vdev: the virtio_device
  * @get: read the value of a configuration field
  *	vdev: the virtio_device
  *	offset: the offset of the configuration field
@@ -78,7 +76,6 @@ struct virtio_shm_region {
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
-	void (*enable_cbs)(struct virtio_device *vdev);
 	void (*get)(struct virtio_device *vdev, unsigned offset,
 		    void *buf, unsigned len);
 	void (*set)(struct virtio_device *vdev, unsigned offset,
@@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev)
 {
 	unsigned status = dev->config->get_status(dev);
 
-	if (dev->config->enable_cbs)
-                  dev->config->enable_cbs(dev);
-
 	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
 	dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
 }

include/net/mctp.h

@@ -36,8 +36,6 @@ struct mctp_hdr {
 #define MCTP_HDR_TAG_SHIFT	0
 #define MCTP_HDR_TAG_MASK	GENMASK(2, 0)
 
-#define MCTP_HEADER_MAXLEN	4
-
 #define MCTP_INITIAL_DEFAULT_NET	1
 
 static inline bool mctp_address_unicast(mctp_eid_t eid)

kernel/trace/bpf_trace.c

@@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
 }
 
 static int
-kprobe_multi_resolve_syms(const void *usyms, u32 cnt,
+kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt,
 			  unsigned long *addrs)
 {
 	unsigned long addr, size;
-	const char **syms;
+	const char __user **syms;
 	int err = -ENOMEM;
 	unsigned int i;
 	char *func;

kernel/trace/rethook.c

@@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_free(struct rethook *rh)
 {
-	rcu_assign_pointer(rh->handler, NULL);
+	WRITE_ONCE(rh->handler, NULL);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }

net/core/filter.c

@@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (!th->ack || th->rst || th->syn)
 		return -ENOENT;
 
+	if (unlikely(iph_len < sizeof(struct iphdr)))
+		return -EINVAL;
+
 	if (tcp_synq_no_recent_overflow(sk))
 		return -ENOENT;
 
 	cookie = ntohl(th->ack_seq) - 1;
 
-	switch (sk->sk_family) {
+	/* Both struct iphdr and struct ipv6hdr have the version field at the
-	case AF_INET:
+	 * same offset so we can cast to the shorter header (struct iphdr).
-		if (unlikely(iph_len < sizeof(struct iphdr)))
+	 */
+	switch (((struct iphdr *)iph)->version) {
+	case 4:
+		if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
 			return -EINVAL;
 
 		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
 		break;
 
 #if IS_BUILTIN(CONFIG_IPV6)
-	case AF_INET6:
+	case 6:
 		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
 			return -EINVAL;
 
+		if (sk->sk_family != AF_INET6)
+			return -EINVAL;
+
 		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
 		break;
 #endif /* CONFIG_IPV6 */

net/core/skbuff.c

@@ -5276,11 +5276,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (skb_cloned(to))
 		return false;
 
-	/* The page pool signature of struct page will eventually figure out
+	/* In general, avoid mixing slab allocated and page_pool allocated
-	 * which pages can be recycled or not but for now let's prohibit slab
+	 * pages within the same SKB. However when @to is not pp_recycle and
-	 * allocated and page_pool allocated SKBs from being coalesced.
+	 * @from is cloned, we can transition frag pages from page_pool to
+	 * reference counted.
+	 *
+	 * On the other hand, don't allow coalescing two pp_recycle SKBs if
+	 * @from is cloned, in case the SKB is using page_pool fragment
+	 * references (PP_FLAG_PAGE_FRAG). Since we only take full page
+	 * references for cloned SKBs at the moment that would result in
+	 * inconsistent reference counts.
 	 */
-	if (to->pp_recycle != from->pp_recycle)
+	if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from)))
 		return false;
 
 	if (len <= skb_tailroom(to)) {

net/dsa/master.c

@@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = {
 	.attrs	= dsa_slave_attrs,
 };
 
+static void dsa_master_reset_mtu(struct net_device *dev)
+{
+	int err;
+
+	err = dev_set_mtu(dev, ETH_DATA_LEN);
+	if (err)
+		netdev_dbg(dev,
+			   "Unable to reset MTU to exclude DSA overheads\n");
+}
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
+	const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
 	struct dsa_switch *ds = cpu_dp->ds;
 	struct device_link *consumer_link;
-	int ret;
+	int mtu, ret;
+
+	mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
 
 	/* The DSA master must use SET_NETDEV_DEV for this to work. */
 	consumer_link = device_link_add(ds->dev, dev->dev.parent,
@@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 			   "Failed to create a device link to DSA switch %s\n",
 			   dev_name(ds->dev));
 
+	/* The switch driver may not implement ->port_change_mtu(), case in
+	 * which dsa_slave_change_mtu() will not update the master MTU either,
+	 * so we need to do that here.
+	 */
+	ret = dev_set_mtu(dev, mtu);
+	if (ret)
+		netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
+			    ret, mtu);
+
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
 	 * sent to the tag format's receive function.
@@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev)
 	sysfs_remove_group(&dev->dev.kobj, &dsa_group);
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
+	dsa_master_reset_mtu(dev);
 	dsa_master_set_promiscuity(dev, -1);
 
 	dev->dsa_ptr = NULL;

net/ipv4/fib_semantics.c

@@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 	}
 
 	if (cfg->fc_oif || cfg->fc_gw_family) {
-		struct fib_nh *nh = fib_info_nh(fi, 0);
+		struct fib_nh *nh;
 
+		/* cannot match on nexthop object attributes */
+		if (fi->nh)
+			return 1;
+
+		nh = fib_info_nh(fi, 0);
 		if (cfg->fc_encap) {
 			if (fib_encap_match(net, cfg->fc_encap_type,
 					    cfg->fc_encap, nh, cfg, extack))

net/ipv6/ip6mr.c

@@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 	mifi_t mifi;
 	struct net *net = sock_net(sk);
 	struct mr_table *mrt;
-	bool do_wrmifwhole;
 
 	if (sk->sk_type != SOCK_RAW ||
 	    inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
@@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 #ifdef CONFIG_IPV6_PIMSM_V2
 	case MRT6_PIM:
 	{
+		bool do_wrmifwhole;
 		int v;
 
 		if (optlen != sizeof(v))

net/ipv6/route.c

@@ -4484,7 +4484,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 	struct inet6_dev *idev;
 	int type;
 
-	if (netif_is_l3_master(skb->dev) &&
+	if (netif_is_l3_master(skb->dev) ||
 	    dst->dev == net->loopback_dev)
 		idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
 	else

net/mctp/af_mctp.c

@@ -93,13 +93,13 @@ out_release:
 static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
-	const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
 	int rc, addrlen = msg->msg_namelen;
 	struct sock *sk = sock->sk;
 	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
 	struct mctp_skb_cb *cb;
 	struct mctp_route *rt;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
+	int hlen;
 
 	if (addr) {
 		const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER |
@@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (addr->smctp_network == MCTP_NET_ANY)
 		addr->smctp_network = mctp_default_net(sock_net(sk));
 
+	/* direct addressing */
+	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+		struct net_device *dev;
+
+		rc = -EINVAL;
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex);
+		/* check for correct halen */
+		if (dev && extaddr->smctp_halen == dev->addr_len) {
+			hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr);
+			rc = 0;
+		}
+		rcu_read_unlock();
+		if (rc)
+			goto err_free;
+		rt = NULL;
+	} else {
+		rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+				       addr->smctp_addr.s_addr);
+		if (!rt) {
+			rc = -EHOSTUNREACH;
+			goto err_free;
+		}
+		hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr);
+	}
+
 	skb = sock_alloc_send_skb(sk, hlen + 1 + len,
 				  msg->msg_flags & MSG_DONTWAIT, &rc);
 	if (!skb)
@@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	cb = __mctp_cb(skb);
 	cb->net = addr->smctp_network;
 
-	/* direct addressing */
+	if (!rt) {
-	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		/* fill extended address in cb */
 		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
 				 extaddr, msg->msg_name);
 
@@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 
 		cb->ifindex = extaddr->smctp_ifindex;
+		/* smctp_halen is checked above */
 		cb->halen = extaddr->smctp_halen;
 		memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
-
-		rt = NULL;
-	} else {
-		rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
-				       addr->smctp_addr.s_addr);
-		if (!rt) {
-			rc = -EHOSTUNREACH;
-			goto err_free;
-		}
 	}
 
 	rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,

net/mctp/route.c

@@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
 
 	if (cb->ifindex) {
 		/* direct route; use the hwaddr we stashed in sendmsg */
+		if (cb->halen != skb->dev->addr_len) {
+			/* sanity check, sendmsg should have already caught this */
+			kfree_skb(skb);
+			return -EMSGSIZE;
+		}
 		daddr = cb->haddr;
 	} else {
 		/* If lookup fails let the device handle daddr==NULL */
@@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
 
 	rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
 			     daddr, skb->dev->dev_addr, skb->len);
-	if (rc) {
+	if (rc < 0) {
 		kfree_skb(skb);
 		return -EHOSTUNREACH;
 	}
@@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 {
 	const unsigned int hlen = sizeof(struct mctp_hdr);
 	struct mctp_hdr *hdr, *hdr2;
-	unsigned int pos, size;
+	unsigned int pos, size, headroom;
 	struct sk_buff *skb2;
 	int rc;
 	u8 seq;
@@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
+	/* keep same headroom as the original skb */
+	headroom = skb_headroom(skb);
+
 	/* we've got the header */
 	skb_pull(skb, hlen);
 
@@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 		/* size of message payload */
 		size = min(mtu - hlen, skb->len - pos);
 
-		skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL);
+		skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL);
 		if (!skb2) {
 			rc = -ENOMEM;
 			break;
@@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
 			skb_set_owner_w(skb2, skb->sk);
 
 		/* establish packet */
-		skb_reserve(skb2, MCTP_HEADER_MAXLEN);
+		skb_reserve(skb2, headroom);
 		skb_reset_network_header(skb2);
 		skb_put(skb2, hlen + size);
 		skb2->transport_header = skb2->network_header + hlen;

net/netfilter/nf_tables_api.c

@@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
 	int err, i, k;
 
 	for (i = 0; i < set->num_exprs; i++) {
-		expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL);
+		expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT);
 		if (!expr)
 			goto err_expr;
 

net/netfilter/nft_bitwise.c

@@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track,
 	if (!track->regs[priv->sreg].selector)
 		return false;
 
-	bitwise = nft_expr_priv(expr);
+	bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
 	if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
 	    track->regs[priv->sreg].num_reg == 0 &&
 	    track->regs[priv->dreg].bitwise &&
@@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track,
 	if (!track->regs[priv->sreg].selector)
 		return false;
 
-	bitwise = nft_expr_priv(expr);
+	bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
 	if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
 	    track->regs[priv->dreg].bitwise &&
 	    track->regs[priv->dreg].bitwise->ops == expr->ops &&

net/netfilter/nft_connlimit.c

@@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
 			invert = true;
 	}
 
-	priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL);
+	priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT);
 	if (!priv->list)
 		return -ENOMEM;
 

net/netfilter/nft_counter.c

@@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
 	struct nft_counter __percpu *cpu_stats;
 	struct nft_counter *this_cpu;
 
-	cpu_stats = alloc_percpu(struct nft_counter);
+	cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT);
 	if (cpu_stats == NULL)
 		return -ENOMEM;
 

net/netfilter/nft_last.c

@@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	u64 last_jiffies;
 	int err;
 
-	last = kzalloc(sizeof(*last), GFP_KERNEL);
+	last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT);
 	if (!last)
 		return -ENOMEM;
 

net/netfilter/nft_limit.c

@@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 				 priv->rate);
 	}
 
-	priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL);
+	priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT);
 	if (!priv->limit)
 		return -ENOMEM;
 

net/netfilter/nft_quota.c

@@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[],
 			return -EOPNOTSUPP;
 	}
 
-	priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL);
+	priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT);
 	if (!priv->consumed)
 		return -ENOMEM;
 

net/openvswitch/actions.c

@@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
 	int rem = nla_len(attr);
 	bool dont_clone_flow_key;
 
-	/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+	/* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
 	clone_arg = nla_data(attr);
 	dont_clone_flow_key = nla_get_u32(clone_arg);
 	actions = nla_next(clone_arg, &rem);

net/openvswitch/flow_netlink.c

@@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size)
 	return sfa;
 }
 
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len);
+
+static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action)
+{
+	const struct nlattr *a;
+	int rem;
+
+	nla_for_each_nested(a, action, rem) {
+		switch (nla_type(a)) {
+		case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL:
+		case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER:
+			ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+			break;
+		}
+	}
+}
+
+static void ovs_nla_free_clone_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+	int rem = nla_len(action);
+
+	switch (nla_type(a)) {
+	case OVS_CLONE_ATTR_EXEC:
+		/* The real list of actions follows this attribute. */
+		a = nla_next(a, &rem);
+		ovs_nla_free_nested_actions(a, rem);
+		break;
+	}
+}
+
+static void ovs_nla_free_dec_ttl_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+
+	switch (nla_type(a)) {
+	case OVS_DEC_TTL_ATTR_ACTION:
+		ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+		break;
+	}
+}
+
+static void ovs_nla_free_sample_action(const struct nlattr *action)
+{
+	const struct nlattr *a = nla_data(action);
+	int rem = nla_len(action);
+
+	switch (nla_type(a)) {
+	case OVS_SAMPLE_ATTR_ARG:
+		/* The real list of actions follows this attribute. */
+		a = nla_next(a, &rem);
+		ovs_nla_free_nested_actions(a, rem);
+		break;
+	}
+}
+
 static void ovs_nla_free_set_action(const struct nlattr *a)
 {
 	const struct nlattr *ovs_key = nla_data(a);
@@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a)
 	}
 }
 
-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
 {
 	const struct nlattr *a;
 	int rem;
 
-	if (!sf_acts)
+	/* Whenever new actions are added, the need to update this
+	 * function should be considered.
+	 */
+	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+
+	if (!actions)
 		return;
 
-	nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+	nla_for_each_attr(a, actions, len, rem) {
 		switch (nla_type(a)) {
-		case OVS_ACTION_ATTR_SET:
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN:
-			ovs_nla_free_set_action(a);
+			ovs_nla_free_check_pkt_len_action(a);
 			break;
+
+		case OVS_ACTION_ATTR_CLONE:
+			ovs_nla_free_clone_action(a);
+			break;
+
 		case OVS_ACTION_ATTR_CT:
 			ovs_ct_free_action(a);
 			break;
+
+		case OVS_ACTION_ATTR_DEC_TTL:
+			ovs_nla_free_dec_ttl_action(a);
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			ovs_nla_free_sample_action(a);
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			ovs_nla_free_set_action(a);
+			break;
 		}
 	}
+}
 
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+	if (!sf_acts)
+		return;
+
+	ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len);
 	kfree(sf_acts);
 }
 
@@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr,
 	if (!start)
 		return -EMSGSIZE;
 
-	err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+	/* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */
+	attr = nla_next(nla_data(attr), &rem);
+	err = ovs_nla_put_actions(attr, rem, skb);
 
 	if (err)
 		nla_nest_cancel(skb, start);

net/rxrpc/net_ns.c

@@ -113,8 +113,8 @@ static __net_exit void rxrpc_exit_net(struct net *net)
 	struct rxrpc_net *rxnet = rxrpc_net(net);
 
 	rxnet->live = false;
-	del_timer_sync(&rxnet->peer_keepalive_timer);
 	cancel_work_sync(&rxnet->peer_keepalive_work);
+	del_timer_sync(&rxnet->peer_keepalive_timer);
 	rxrpc_destroy_all_calls(rxnet);
 	rxrpc_destroy_all_connections(rxnet);
 	rxrpc_destroy_all_peers(rxnet);

net/sctp/outqueue.c

@@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 				ctx->asoc->base.sk->sk_err = -error;
 				return;
 			}
+			ctx->asoc->stats.octrlchunks++;
 			break;
 
 		case SCTP_CID_ABORT:
@@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
 
 		case SCTP_CID_HEARTBEAT:
 			if (chunk->pmtu_probe) {
-				sctp_packet_singleton(ctx->transport, chunk, ctx->gfp);
+				error = sctp_packet_singleton(ctx->transport,
+							      chunk, ctx->gfp);
+				if (!error)
+					ctx->asoc->stats.octrlchunks++;
 				break;
 			}
 			fallthrough;

net/tls/tls_sw.c

@@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	if (prot->version == TLS_1_3_VERSION ||
 	    prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
 		memcpy(iv + iv_offset, tls_ctx->rx.iv,
-		       crypto_aead_ivsize(ctx->aead_recv));
+		       prot->iv_size + prot->salt_size);
 	else
 		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 

tools/bpf/bpftool/gen.c

@@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
 			s->map_cnt = %zu;			    \n\
 			s->map_skel_sz = sizeof(*s->maps);	    \n\
 			s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
-			if (!s->maps)				    \n\
+			if (!s->maps) {				    \n\
+				err = -ENOMEM;			    \n\
 				goto err;			    \n\
+			}					    \n\
 		",
 		map_cnt
 	);
@@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li
 			s->prog_cnt = %zu;			    \n\
 			s->prog_skel_sz = sizeof(*s->progs);	    \n\
 			s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
-			if (!s->progs)				    \n\
+			if (!s->progs) {			    \n\
+				err = -ENOMEM;			    \n\
 				goto err;			    \n\
+			}					    \n\
 		",
 		prog_cnt
 	);
@@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv)
 		%1$s__create_skeleton(struct %1$s *obj)			    \n\
 		{							    \n\
 			struct bpf_object_skeleton *s;			    \n\
+			int err;					    \n\
 									    \n\
 			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
-			if (!s)						    \n\
+			if (!s)	{					    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
+			}						    \n\
 									    \n\
 			s->sz = sizeof(*s);				    \n\
 			s->name = \"%1$s\";				    \n\
@@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv)
 			return 0;					    \n\
 		err:							    \n\
 			bpf_object__destroy_skeleton(s);		    \n\
-			return -ENOMEM;					    \n\
+			return err;					    \n\
 		}							    \n\
 									    \n\
 		static inline const void *%2$s__elf_bytes(size_t *sz)	    \n\
@@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv)
 									    \n\
 			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
 			if (!obj) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 			s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\
 			if (!s) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 			s->sz = sizeof(*s);				    \n\
@@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv)
 			s->var_cnt = %2$d;				    \n\
 			s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\
 			if (!s->vars) {					    \n\
-				errno = ENOMEM;				    \n\
+				err = -ENOMEM;				    \n\
 				goto err;				    \n\
 			}						    \n\
 		",
@@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv)
 			return obj;					    \n\
 		err:							    \n\
 			%1$s__destroy(obj);				    \n\
+			errno = -err;					    \n\
 			return NULL;					    \n\
 		}							    \n\
 									    \n\

tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c

@@ -2,6 +2,7 @@
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
 #include <test_progs.h>
 #include "dummy_st_ops.skel.h"
+#include "trace_dummy_st_ops.skel.h"
 
 /* Need to keep consistent with definition in include/linux/bpf.h */
 struct bpf_dummy_ops_state {
@@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
+	struct trace_dummy_st_ops *trace_skel;
 	struct dummy_st_ops *skel;
 	int fd, err;
 
@@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void)
 		return;
 
 	fd = bpf_program__fd(skel->progs.test_1);
+
+	trace_skel = trace_dummy_st_ops__open();
+	if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open"))
+		goto done;
+
+	err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1,
+					     fd, "test_1");
+	if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)"))
+		goto done;
+
+	err = trace_dummy_st_ops__load(trace_skel);
+	if (!ASSERT_OK(err, "load(trace_skel)"))
+		goto done;
+
+	err = trace_dummy_st_ops__attach(trace_skel);
+	if (!ASSERT_OK(err, "attach(trace_skel)"))
+		goto done;
+
 	err = bpf_prog_test_run_opts(fd, &attr);
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret");
 	ASSERT_EQ(attr.retval, exp_retval, "test_ret");
+	ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
 
+done:
 	dummy_st_ops__destroy(skel);
+	trace_dummy_st_ops__destroy(trace_skel);
 }
 
 static void test_dummy_multiple_args(void)

tools/testing/selftests/bpf/progs/map_ptr_kern.c

@@ -367,7 +367,7 @@ static inline int check_array_of_maps(void)
 
 	VERIFY(check_default(&array_of_maps->map, map));
 	inner_map = bpf_map_lookup_elem(array_of_maps, &key);
-	VERIFY(inner_map != 0);
+	VERIFY(inner_map != NULL);
 	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;
@@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void)
 
 	VERIFY(check_default(&hash_of_maps->map, map));
 	inner_map = bpf_map_lookup_elem(hash_of_maps, &key);
-	VERIFY(inner_map != 0);
+	VERIFY(inner_map != NULL);
 	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;

tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int val = 0;
+
+SEC("fentry/test_1")
+int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx)
+{
+	__u64 state;
+
+	/* Read the traced st_ops arg1 which is a pointer */
+	bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx);
+	/* Read state->val */
+	bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c

@@ -18,8 +18,9 @@
 #include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
 
-static int start_server(const struct sockaddr *addr, socklen_t len)
+static int start_server(const struct sockaddr *addr, socklen_t len, bool dual)
 {
+	int mode = !dual;
 	int fd;
 
 	fd = socket(addr->sa_family, SOCK_STREAM, 0);
@@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len)
 		goto out;
 	}
 
+	if (addr->sa_family == AF_INET6) {
+		if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode,
+			       sizeof(mode)) == -1) {
+			log_err("Failed to set the dual-stack mode");
+			goto close_out;
+		}
+	}
+
 	if (bind(fd, addr, len) == -1) {
 		log_err("Failed to bind server socket");
 		goto close_out;
@@ -47,24 +56,17 @@ out:
 	return fd;
 }
 
-static int connect_to_server(int server_fd)
+static int connect_to_server(const struct sockaddr *addr, socklen_t len)
 {
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
 	int fd = -1;
 
-	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+	fd = socket(addr->sa_family, SOCK_STREAM, 0);
-		log_err("Failed to get server addr");
-		goto out;
-	}
-
-	fd = socket(addr.ss_family, SOCK_STREAM, 0);
 	if (fd == -1) {
 		log_err("Failed to create client socket");
 		goto out;
 	}
 
-	if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+	if (connect(fd, (const struct sockaddr *)addr, len) == -1) {
 		log_err("Fail to connect to server");
 		goto close_out;
 	}
@@ -116,7 +118,8 @@ err:
 	return map_fd;
 }
 
-static int run_test(int server_fd, int results_fd, bool xdp)
+static int run_test(int server_fd, int results_fd, bool xdp,
+		    const struct sockaddr *addr, socklen_t len)
 {
 	int client = -1, srv_client = -1;
 	int ret = 0;
@@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp)
 		goto err;
 	}
 
-	client = connect_to_server(server_fd);
+	client = connect_to_server(addr, len);
 	if (client == -1)
 		goto err;
 
@@ -199,12 +202,30 @@ out:
 	return ret;
 }
 
+static bool get_port(int server_fd, in_port_t *port)
+{
+	struct sockaddr_in addr;
+	socklen_t len = sizeof(addr);
+
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		return false;
+	}
+
+	/* sin_port and sin6_port are located at the same offset. */
+	*port = addr.sin_port;
+	return true;
+}
+
 int main(int argc, char **argv)
 {
 	struct sockaddr_in addr4;
 	struct sockaddr_in6 addr6;
+	struct sockaddr_in addr4dual;
+	struct sockaddr_in6 addr6dual;
 	int server = -1;
 	int server_v6 = -1;
+	int server_dual = -1;
 	int results = -1;
 	int err = 0;
 	bool xdp;
@@ -224,25 +245,43 @@ int main(int argc, char **argv)
 	addr4.sin_family = AF_INET;
 	addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
 	addr4.sin_port = 0;
+	memcpy(&addr4dual, &addr4, sizeof(addr4dual));
 
 	memset(&addr6, 0, sizeof(addr6));
 	addr6.sin6_family = AF_INET6;
 	addr6.sin6_addr = in6addr_loopback;
 	addr6.sin6_port = 0;
 
-	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4));
+	memset(&addr6dual, 0, sizeof(addr6dual));
-	if (server == -1)
+	addr6dual.sin6_family = AF_INET6;
+	addr6dual.sin6_addr = in6addr_any;
+	addr6dual.sin6_port = 0;
+
+	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4),
+			      false);
+	if (server == -1 || !get_port(server, &addr4.sin_port))
 		goto err;
 
 	server_v6 = start_server((const struct sockaddr *)&addr6,
-				 sizeof(addr6));
+				 sizeof(addr6), false);
-	if (server_v6 == -1)
+	if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port))
 		goto err;
 
-	if (run_test(server, results, xdp))
+	server_dual = start_server((const struct sockaddr *)&addr6dual,
+				   sizeof(addr6dual), true);
+	if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port))
 		goto err;
 
-	if (run_test(server_v6, results, xdp))
+	if (run_test(server, results, xdp,
+		     (const struct sockaddr *)&addr4, sizeof(addr4)))
+		goto err;
+
+	if (run_test(server_v6, results, xdp,
+		     (const struct sockaddr *)&addr6, sizeof(addr6)))
+		goto err;
+
+	if (run_test(server_dual, results, xdp,
+		     (const struct sockaddr *)&addr4dual, sizeof(addr4dual)))
 		goto err;
 
 	printf("ok\n");
@@ -252,6 +291,7 @@ err:
 out:
 	close(server);
 	close(server_v6);
+	close(server_dual);
 	close(results);
 	return err;
 }

tools/testing/selftests/net/fib_nexthops.sh

@@ -1208,6 +1208,20 @@ ipv4_fcnal()
 	set +e
 	check_nexthop "dev veth1" ""
 	log_test $? 0 "Nexthops removed on admin down"
+
+	# nexthop route delete warning: route add with nhid and delete
+	# using device
+	run_cmd "$IP li set dev veth1 up"
+	run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1"
+	out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+	run_cmd "$IP route add 172.16.101.1/32 nhid 12"
+	run_cmd "$IP route delete 172.16.101.1/32 dev veth1"
+	out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+	[ $out1 -eq $out2 ]
+	rc=$?
+	log_test $rc 0 "Delete nexthop route warning"
+	run_cmd "$IP route delete 172.16.101.1/32 nhid 12"
+	run_cmd "$IP nexthop del id 12"
 }
 
 ipv4_grp_fcnal()