[Deepin-Kernel-SIG] [linux 6.6-y] [Upstream] Update kernel base to 6.6.84-part2

Documentation/timers/no_hz.rst

@@ -129,11 +129,8 @@ adaptive-tick CPUs:  At least one non-adaptive-tick CPU must remain
 online to handle timekeeping tasks in order to ensure that system
 calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
 (This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
-user processes to observe slight drifts in clock rate.)  Therefore, the
-boot CPU is prohibited from entering adaptive-ticks mode.  Specifying a
-"nohz_full=" mask that includes the boot CPU will result in a boot-time
-error message, and the boot CPU will be removed from the mask.  Note that
-this means that your system must have at least two CPUs in order for
+user processes to observe slight drifts in clock rate.) Note that this
+means that your system must have at least two CPUs in order for
 CONFIG_NO_HZ_FULL=y to do anything for you.
 
 Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded.

arch/x86/kernel/cpu/mshyperv.c

@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
-#include <linux/i8253.h>
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
@@ -575,16 +574,6 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
-	/*
-	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
-	 * counter register during PIT shutdown restarts the PIT. So it
-	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
-	 * to false tells pit_shutdown() not to zero the counter so that
-	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
-	 * and setting this value has no effect.
-	 */
-	i8253_clear_counter_on_shutdown = false;
-
 #if IS_ENABLED(CONFIG_HYPERV)
 	if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) ||
 	    ms_hyperv.paravisor_present)

drivers/block/zram/zram_drv.c

@@ -2247,6 +2247,8 @@ static int zram_add(void)
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
 
+	comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor);
+
 	/* Actual capacity set using sysfs (/sys/block/zram<id>/disksize */
 	set_capacity(zram->disk, 0);
 	/* zram devices sort of resembles non-rotational disks */
@@ -2281,8 +2283,6 @@ static int zram_add(void)
 	if (ret)
 		goto out_cleanup_disk;
 
-	comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor);
-
 	zram_debugfs_register(zram);
 	pr_info("Added device: %s\n", zram->disk->disk_name);
 	return device_id;

drivers/clocksource/i8253.c

@@ -20,13 +20,6 @@
 DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-/*
- * Handle PIT quirk in pit_shutdown() where zeroing the counter register
- * restarts the PIT, negating the shutdown. On platforms with the quirk,
- * platform specific code can set this to false.
- */
-bool i8253_clear_counter_on_shutdown __ro_after_init = true;
-
 #ifdef CONFIG_CLKSRC_I8253
 /*
  * Since the PIT overflows every tick, its not very useful
@@ -112,12 +105,33 @@ void clockevent_i8253_disable(void)
 {
 	raw_spin_lock(&i8253_lock);
 
+	/*
+	 * Writing the MODE register should stop the counter, according to
+	 * the datasheet. This appears to work on real hardware (well, on
+	 * modern Intel and AMD boxes; I didn't dig the Pegasos out of the
+	 * shed).
+	 *
+	 * However, some virtual implementations differ, and the MODE change
+	 * doesn't have any effect until either the counter is written (KVM
+	 * in-kernel PIT) or the next interrupt (QEMU). And in those cases,
+	 * it may not stop the *count*, only the interrupts. Although in
+	 * the virt case, that probably doesn't matter, as the value of the
+	 * counter will only be calculated on demand if the guest reads it;
+	 * it's the interrupts which cause steal time.
+	 *
+	 * Hyper-V apparently has a bug where even in mode 0, the IRQ keeps
+	 * firing repeatedly if the counter is running. But it *does* do the
+	 * right thing when the MODE register is written.
+	 *
+	 * So: write the MODE and then load the counter, which ensures that
+	 * the IRQ is stopped on those buggy virt implementations. And then
+	 * write the MODE again, which is the right way to stop it.
+	 */
 	outb_p(0x30, PIT_MODE);
+	outb_p(0, PIT_CH0);
+	outb_p(0, PIT_CH0);
 
-	if (i8253_clear_counter_on_shutdown) {
-		outb_p(0, PIT_CH0);
-		outb_p(0, PIT_CH0);
-	}
+	outb_p(0x30, PIT_MODE);
 
 	raw_spin_unlock(&i8253_lock);
 }

drivers/gpu/drm/hyperv/hyperv_drm_drv.c

@@ -157,6 +157,7 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
 	return 0;
 
 err_free_mmio:
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 err_vmbus_close:
 	vmbus_close(hdev->channel);
@@ -175,6 +176,7 @@ static void hyperv_vmbus_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 }
 

drivers/hv/vmbus_drv.c

@@ -2242,12 +2242,25 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size)
 	struct resource *iter;
 
 	mutex_lock(&hyperv_mmio_lock);
+
+	/*
+	 * If all bytes of the MMIO range to be released are within the
+	 * special case fb_mmio shadow region, skip releasing the shadow
+	 * region since no corresponding __request_region() was done
+	 * in vmbus_allocate_mmio().
+	 */
+	if (fb_mmio && start >= fb_mmio->start &&
+	    (start + size - 1 <= fb_mmio->end))
+		goto skip_shadow_release;
+
 	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
 		if ((iter->start >= start + size) || (iter->end <= start))
 			continue;
 
 		__release_region(iter, start, size);
 	}
+
+skip_shadow_release:
 	release_mem_region(start, size);
 	mutex_unlock(&hyperv_mmio_lock);
 

drivers/net/bonding/bond_options.c

@@ -1226,10 +1226,28 @@ static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *sla
 	       slave->dev->flags & IFF_MULTICAST;
 }
 
+/**
+ * slave_set_ns_maddrs - add/del all NS mac addresses for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @add: add or remove all the NS mac addresses
+ *
+ * This function tries to add or delete all the NS mac addresses on the slave
+ *
+ * Note, the IPv6 NS target address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * arp_validate changes
+ *   * enslaving, releasing new slaves
+ */
 static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add)
 {
 	struct in6_addr *targets = bond->params.ns_targets;
 	char slot_maddr[MAX_ADDR_LEN];
+	struct in6_addr mcaddr;
 	int i;
 
 	if (!slave_can_set_ns_maddr(bond, slave))
@@ -1239,7 +1257,8 @@ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool
 		if (ipv6_addr_any(&targets[i]))
 			break;
 
-		if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) {
+		addrconf_addr_solict_mult(&targets[i], &mcaddr);
+		if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) {
 			if (add)
 				dev_mc_add(slave->dev, slot_maddr);
 			else
@@ -1262,23 +1281,43 @@ void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
 	slave_set_ns_maddrs(bond, slave, false);
 }
 
+/**
+ * slave_set_ns_maddr - set new NS mac address for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @target: the new IPv6 target
+ * @slot: the old IPv6 target in the slot
+ *
+ * This function tries to replace the old mac address to new one on the slave.
+ *
+ * Note, the target/slot IPv6 address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * An IPv6 NS target is added or removed.
+ */
 static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave,
 			       struct in6_addr *target, struct in6_addr *slot)
 {
-	char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN];
+	char mac_addr[MAX_ADDR_LEN];
+	struct in6_addr mcast_addr;
 
 	if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
 		return;
 
-	/* remove the previous maddr from slave */
+	/* remove the previous mac addr from slave */
+	addrconf_addr_solict_mult(slot, &mcast_addr);
 	if (!ipv6_addr_any(slot) &&
-	    !ndisc_mc_map(slot, slot_maddr, slave->dev, 0))
-		dev_mc_del(slave->dev, slot_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_del(slave->dev, mac_addr);
 
-	/* add new maddr on slave if target is set */
+	/* add new mac addr on slave if target is set */
+	addrconf_addr_solict_mult(target, &mcast_addr);
 	if (!ipv6_addr_any(target) &&
-	    !ndisc_mc_map(target, target_maddr, slave->dev, 0))
-		dev_mc_add(slave->dev, target_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_add(slave->dev, mac_addr);
 }
 
 static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,

drivers/net/dsa/mv88e6xxx/chip.c

@@ -2125,13 +2125,11 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
-					const unsigned char *addr, u16 vid,
-					u8 state)
+static int mv88e6xxx_port_db_get(struct mv88e6xxx_chip *chip,
+				 const unsigned char *addr, u16 vid,
+				 u16 *fid, struct mv88e6xxx_atu_entry *entry)
 {
-	struct mv88e6xxx_atu_entry entry;
 	struct mv88e6xxx_vtu_entry vlan;
-	u16 fid;
 	int err;
 
 	/* Ports have two private address databases: one for when the port is
@@ -2142,7 +2140,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	 * VLAN ID into the port's database used for VLAN-unaware bridging.
 	 */
 	if (vid == 0) {
-		fid = MV88E6XXX_FID_BRIDGED;
+		*fid = MV88E6XXX_FID_BRIDGED;
 	} else {
 		err = mv88e6xxx_vtu_get(chip, vid, &vlan);
 		if (err)
@@ -2152,14 +2150,39 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 		if (!vlan.valid)
 			return -EOPNOTSUPP;
 
-		fid = vlan.fid;
+		*fid = vlan.fid;
 	}
 
-	entry.state = 0;
-	ether_addr_copy(entry.mac, addr);
-	eth_addr_dec(entry.mac);
+	entry->state = 0;
+	ether_addr_copy(entry->mac, addr);
+	eth_addr_dec(entry->mac);
+
+	return mv88e6xxx_g1_atu_getnext(chip, *fid, entry);
+}
+
+static bool mv88e6xxx_port_db_find(struct mv88e6xxx_chip *chip,
+				   const unsigned char *addr, u16 vid)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
 
-	err = mv88e6xxx_g1_atu_getnext(chip, fid, &entry);
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
+	if (err)
+		return false;
+
+	return entry.state && ether_addr_equal(entry.mac, addr);
+}
+
+static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
+					const unsigned char *addr, u16 vid,
+					u8 state)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
+
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
 	if (err)
 		return err;
 
@@ -2757,6 +2780,13 @@ static int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, addr, vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -6454,6 +6484,13 @@ static int mv88e6xxx_port_mdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_MC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, mdb->addr, mdb->vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;

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

@@ -1958,7 +1958,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
+						 rxr->page_pool, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);

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

@@ -462,20 +462,13 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp,
-		   struct rx_cmp_ext *rxcmp1)
+		   struct page_pool *pool, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!skb)
 		return NULL;
-	skb_checksum_none_assert(skb);
-	if (RX_CMP_L4_CS_OK(rxcmp1)) {
-		if (bp->dev->features & NETIF_F_RXCSUM) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
-		}
-	}
+
 	xdp_update_skb_shared_info(skb, num_frags,
 				   sinfo->xdp_frags_size,
 				   BNXT_RX_PAGE_SIZE * sinfo->nr_frags,

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

@@ -33,6 +33,5 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
 				   u8 num_frags, struct page_pool *pool,
-				   struct xdp_buff *xdp,
-				   struct rx_cmp_ext *rxcmp1);
+				   struct xdp_buff *xdp);
 #endif

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

@@ -510,7 +510,7 @@ void ice_init_arfs(struct ice_vsi *vsi)
 	struct hlist_head *arfs_fltr_list;
 	unsigned int i;
 
-	if (!vsi || vsi->type != ICE_VSI_PF)
+	if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi))
 		return;
 
 	arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list),

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

@@ -46,6 +46,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;