Merge ecc64d2dc9 ("Merge tag 'sysctl-7.00-fixes-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl") into android-mainline

Steps on the way to v7.0-rc3

Change-Id: Ie304ea1065476101b872fb01f45b426fa68e8e8f
Signed-off-by: Carlos Llamas <cmllamas@google.com>

Documentation/netlink/specs/nfsd.yaml

@@ -152,7 +152,7 @@ operations:
             - compound-ops
     -
       name: threads-set
-      doc: set the number of running threads
+      doc: set the maximum number of running threads
       attribute-set: server
       flags: [admin-perm]
       do:
@@ -165,7 +165,7 @@ operations:
             - min-threads
     -
       name: threads-get
-      doc: get the number of running threads
+      doc: get the maximum number of running threads
       attribute-set: server
       do:
         reply:

drivers/media/dvb-core/dvb_net.c

@@ -228,6 +228,9 @@ static int handle_one_ule_extension( struct dvb_net_priv *p )
 	unsigned char hlen = (p->ule_sndu_type & 0x0700) >> 8;
 	unsigned char htype = p->ule_sndu_type & 0x00FF;
 
+	if (htype >= ARRAY_SIZE(ule_mandatory_ext_handlers))
+		return -1;
+
 	/* Discriminate mandatory and optional extension headers. */
 	if (hlen == 0) {
 		/* Mandatory extension header */

drivers/pinctrl/cirrus/pinctrl-cs42l43.c

@@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 		if (child) {
 			ret = devm_add_action_or_reset(&pdev->dev,
 				cs42l43_fwnode_put, child);
-			if (ret) {
-				fwnode_handle_put(child);
+			if (ret)
 				return ret;
-			}
+
 			if (!child->dev)
 				child->dev = priv->dev;
 			fwnode = child;

drivers/pinctrl/cix/pinctrl-sky1.c

@@ -522,11 +522,10 @@ static int __maybe_unused sky1_pinctrl_resume(struct device *dev)
 	return pinctrl_force_default(spctl->pctl);
 }
 
-const struct dev_pm_ops sky1_pinctrl_pm_ops = {
+static const struct dev_pm_ops sky1_pinctrl_pm_ops = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(sky1_pinctrl_suspend,
 					sky1_pinctrl_resume)
 };
-EXPORT_SYMBOL_GPL(sky1_pinctrl_pm_ops);
 
 static int sky1_pinctrl_probe(struct platform_device *pdev)
 {

drivers/pinctrl/meson/pinctrl-amlogic-a4.c

@@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 				     unsigned int *num_maps)
 {
 	struct device *dev = pctldev->dev;
-	struct device_node *pnode;
 	unsigned long *configs = NULL;
 	unsigned int num_configs = 0;
 	struct property *prop;
@@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 		return -ENOENT;
 	}
 
-	pnode = of_get_parent(np);
+	struct device_node *pnode __free(device_node) = of_get_parent(np);
 	if (!pnode) {
 		dev_info(dev, "Missing function node\n");
 		return -EINVAL;

drivers/pinctrl/pinconf-generic.c

@@ -351,13 +351,13 @@ int pinconf_generic_parse_dt_config(struct device_node *np,
 
 	ret = parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg);
 	if (ret)
-		return ret;
+		goto out;
 	if (pctldev && pctldev->desc->num_custom_params &&
 		pctldev->desc->custom_params) {
 		ret = parse_dt_cfg(np, pctldev->desc->custom_params,
 				   pctldev->desc->num_custom_params, cfg, &ncfg);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* no configs found at all */

drivers/pinctrl/pinctrl-amdisp.c

@@ -80,7 +80,7 @@ static int amdisp_get_group_pins(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-const struct pinctrl_ops amdisp_pinctrl_ops = {
+static const struct pinctrl_ops amdisp_pinctrl_ops = {
 	.get_groups_count	= amdisp_get_groups_count,
 	.get_group_name		= amdisp_get_group_name,
 	.get_group_pins		= amdisp_get_group_pins,

drivers/pinctrl/pinctrl-cy8c95x0.c

@@ -627,7 +627,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		write_val = bitmap_get_value8(tval, offset);
@@ -655,7 +655,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		ret = cy8c95x0_regmap_read_bits(chip, reg, i, bits, &read_val);

drivers/pinctrl/pinctrl-equilibrium.c

@@ -23,7 +23,7 @@
 #define PIN_NAME_LEN	10
 #define PAD_REG_OFF	0x100
 
-static void eqbr_gpio_disable_irq(struct irq_data *d)
+static void eqbr_irq_mask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d)
 	gpiochip_disable_irq(gc, offset);
 }
 
-static void eqbr_gpio_enable_irq(struct irq_data *d)
+static void eqbr_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_ack_irq(struct irq_data *d)
+static void eqbr_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -62,10 +62,17 @@ static void eqbr_gpio_ack_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_mask_ack_irq(struct irq_data *d)
+static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_gpio_disable_irq(d);
-	eqbr_gpio_ack_irq(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
+	unsigned int offset = irqd_to_hwirq(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&gctrl->lock, flags);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNCR);
+	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
@@ -92,7 +99,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type,
 	return 0;
 }
 
-static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+static int eqbr_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -166,11 +173,11 @@ static void eqbr_irq_handler(struct irq_desc *desc)
 
 static const struct irq_chip eqbr_irq_chip = {
 	.name = "gpio_irq",
-	.irq_mask = eqbr_gpio_disable_irq,
-	.irq_unmask = eqbr_gpio_enable_irq,
-	.irq_ack = eqbr_gpio_ack_irq,
-	.irq_mask_ack = eqbr_gpio_mask_ack_irq,
-	.irq_set_type = eqbr_gpio_set_irq_type,
+	.irq_ack = eqbr_irq_ack,
+	.irq_mask = eqbr_irq_mask,
+	.irq_mask_ack = eqbr_irq_mask_ack,
+	.irq_unmask = eqbr_irq_unmask,
+	.irq_set_type = eqbr_irq_set_type,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };

drivers/pinctrl/pinctrl-rockchip.c

@@ -3640,14 +3640,10 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			 * or the gpio driver hasn't probed yet.
 			 */
 			scoped_guard(mutex, &bank->deferred_lock) {
-				if (!gpio || !gpio->direction_output) {
-					rc = rockchip_pinconf_defer_pin(bank,
-									pin - bank->pin_base,
-									param, arg);
-					if (rc)
-						return rc;
-					break;
-				}
+				if (!gpio || !gpio->direction_output)
+					return rockchip_pinconf_defer_pin(bank,
+									  pin - bank->pin_base,
+									  param, arg);
 			}
 		}
 

drivers/pinctrl/qcom/pinctrl-qcs615.c

@@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = {
 	.ntiles = ARRAY_SIZE(qcs615_tiles),
 	.wakeirq_map = qcs615_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static const struct of_device_id qcs615_tlmm_of_match[] = {

drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c

@@ -76,7 +76,7 @@ static const char * const pdm_clk_groups[] = { "gpio18" };
 static const char * const pdm_rx_groups[] = { "gpio21", "gpio23", "gpio25" };
 static const char * const pdm_sync_groups[] = { "gpio19" };
 
-const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
+static const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(0, LPI_NO_SLEW, _, _, _, _, 0x0000),
 	LPI_PINGROUP_OFFSET(1, LPI_NO_SLEW, _, _, _, _, 0x1000),
 	LPI_PINGROUP_OFFSET(2, LPI_NO_SLEW, _, _, _, _, 0x2000),
@@ -113,7 +113,7 @@ const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(31, LPI_NO_SLEW, _, _, _, _, 0xb010),
 };
 
-const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
+static const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
 	LPI_FUNCTION(comp_rx),
 	LPI_FUNCTION(dmic1_clk),
 	LPI_FUNCTION(dmic1_data),

drivers/pinctrl/sunxi/pinctrl-sunxi.c

@@ -204,6 +204,32 @@ sunxi_pinctrl_desc_find_function_by_pin(struct sunxi_pinctrl *pctl,
 	return NULL;
 }
 
+static struct sunxi_desc_function *
+sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl,
+						const u16 pin_num,
+						const u8 muxval)
+{
+	for (unsigned int i = 0; i < pctl->desc->npins; i++) {
+		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
+		struct sunxi_desc_function *func = pin->functions;
+
+		if (pin->pin.number != pin_num)
+			continue;
+
+		if (pin->variant && !(pctl->variant & pin->variant))
+			continue;
+
+		while (func->name) {
+			if (func->muxval == muxval)
+				return func;
+
+			func++;
+		}
+	}
+
+	return NULL;
+}
+
 static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
 {
 	struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
@@ -930,6 +956,30 @@ static const struct pinmux_ops sunxi_pmx_ops = {
 	.strict			= true,
 };
 
+static int sunxi_pinctrl_gpio_get_direction(struct gpio_chip *chip,
+					    unsigned int offset)
+{
+	struct sunxi_pinctrl *pctl = gpiochip_get_data(chip);
+	const struct sunxi_desc_function *func;
+	u32 pin = offset + chip->base;
+	u32 reg, shift, mask;
+	u8 muxval;
+
+	sunxi_mux_reg(pctl, offset, &reg, &shift, &mask);
+
+	muxval = (readl(pctl->membase + reg) & mask) >> shift;
+
+	func = sunxi_pinctrl_desc_find_function_by_pin_and_mux(pctl, pin, muxval);
+	if (!func)
+		return -ENODEV;
+
+	if (!strcmp(func->name, "gpio_out"))
+		return GPIO_LINE_DIRECTION_OUT;
+	if (!strcmp(func->name, "gpio_in") || !strcmp(func->name, "irq"))
+		return GPIO_LINE_DIRECTION_IN;
+	return -EINVAL;
+}
+
 static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip,
 					unsigned offset)
 {
@@ -1599,6 +1649,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 	pctl->chip->request = gpiochip_generic_request;
 	pctl->chip->free = gpiochip_generic_free;
 	pctl->chip->set_config = gpiochip_generic_config;
+	pctl->chip->get_direction = sunxi_pinctrl_gpio_get_direction;
 	pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input;
 	pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output;
 	pctl->chip->get = sunxi_pinctrl_gpio_get;

fs/btrfs/block-group.c

@@ -3340,7 +3340,6 @@ again:
 		btrfs_abort_transaction(trans, ret);
 		goto out_put;
 	}
-	WARN_ON(ret);
 
 	/* We've already setup this transaction, go ahead and exit */
 	if (block_group->cache_generation == trans->transid &&

fs/btrfs/delayed-inode.c

@@ -1657,7 +1657,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	if (unlikely(ret)) {
 		btrfs_err(trans->fs_info,
 "failed to add delayed dir index item, root: %llu, inode: %llu, index: %llu, error: %d",
-			  index, btrfs_root_id(node->root), node->inode_id, ret);
+			  btrfs_root_id(node->root), node->inode_id, index, ret);
 		btrfs_delayed_item_release_metadata(dir->root, item);
 		btrfs_release_delayed_item(item);
 	}

fs/btrfs/disk-io.c

@@ -1994,7 +1994,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	int level = btrfs_super_log_root_level(disk_super);
 
 	if (unlikely(fs_devices->rw_devices == 0)) {
-		btrfs_warn(fs_info, "log replay required on RO media");
+		btrfs_err(fs_info, "log replay required on RO media");
 		return -EIO;
 	}
 
@@ -2008,9 +2008,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	check.owner_root = BTRFS_TREE_LOG_OBJECTID;
 	log_tree_root->node = read_tree_block(fs_info, bytenr, &check);
 	if (IS_ERR(log_tree_root->node)) {
-		btrfs_warn(fs_info, "failed to read log tree");
 		ret = PTR_ERR(log_tree_root->node);
 		log_tree_root->node = NULL;
+		btrfs_err(fs_info, "failed to read log tree with error: %d", ret);
 		btrfs_put_root(log_tree_root);
 		return ret;
 	}
@@ -2023,9 +2023,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	/* returns with log_tree_root freed on success */
 	ret = btrfs_recover_log_trees(log_tree_root);
 	btrfs_put_root(log_tree_root);
-	if (ret) {
-		btrfs_handle_fs_error(fs_info, ret,
-				      "Failed to recover log tree");
+	if (unlikely(ret)) {
+		ASSERT(BTRFS_FS_ERROR(fs_info) != 0);
+		btrfs_err(fs_info, "failed to recover log trees with error: %d", ret);
 		return ret;
 	}
 
@@ -2972,7 +2972,6 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
 	task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
 	if (IS_ERR(task)) {
 		/* fs_info->update_uuid_tree_gen remains 0 in all error case */
-		btrfs_warn(fs_info, "failed to start uuid_rescan task");
 		up(&fs_info->uuid_tree_rescan_sem);
 		return PTR_ERR(task);
 	}
@@ -3188,7 +3187,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
 		btrfs_err(fs_info,
 		"cannot mount because of unknown incompat features (0x%llx)",
-		    incompat);
+		    incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP);
 		return -EINVAL;
 	}
 
@@ -3220,7 +3219,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (compat_ro_unsupp && is_rw_mount) {
 		btrfs_err(fs_info,
 	"cannot mount read-write because of unknown compat_ro features (0x%llx)",
-		       compat_ro);
+		       compat_ro_unsupp);
 		return -EINVAL;
 	}
 
@@ -3233,7 +3232,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
 		btrfs_err(fs_info,
 "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
-			  compat_ro);
+			  compat_ro_unsupp);
 		return -EINVAL;
 	}
 
@@ -3642,7 +3641,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		ret = PTR_ERR(fs_info->fs_root);
-		btrfs_warn(fs_info, "failed to read fs tree: %d", ret);
+		btrfs_err(fs_info, "failed to read fs tree: %d", ret);
 		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}
@@ -3663,8 +3662,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_info(fs_info, "checking UUID tree");
 		ret = btrfs_check_uuid_tree(fs_info);
 		if (ret) {
-			btrfs_warn(fs_info,
-				"failed to check the UUID tree: %d", ret);
+			btrfs_err(fs_info, "failed to check the UUID tree: %d", ret);
 			close_ctree(fs_info);
 			return ret;
 		}
@@ -4399,9 +4397,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 		 */
 		btrfs_flush_workqueue(fs_info->delayed_workers);
 
-		ret = btrfs_commit_super(fs_info);
-		if (ret)
-			btrfs_err(fs_info, "commit super ret %d", ret);
+		/*
+		 * If the filesystem is shutdown, then an attempt to commit the
+		 * super block (or any write) will just fail. Since we freeze
+		 * the filesystem before shutting it down, the filesystem is in
+		 * a consistent state and we don't need to commit super blocks.
+		 */
+		if (!btrfs_is_shutdown(fs_info)) {
+			ret = btrfs_commit_super(fs_info);
+			if (ret)
+				btrfs_err(fs_info, "commit super block returned %d", ret);
+		}
 	}
 
 	kthread_stop(fs_info->transaction_kthread);

fs/btrfs/extent-tree.c

@@ -2933,9 +2933,15 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 	while (!TRANS_ABORTED(trans) && cached_state) {
 		struct extent_state *next_state;
 
-		if (btrfs_test_opt(fs_info, DISCARD_SYNC))
+		if (btrfs_test_opt(fs_info, DISCARD_SYNC)) {
 			ret = btrfs_discard_extent(fs_info, start,
 						   end + 1 - start, NULL, true);
+			if (ret) {
+				btrfs_warn(fs_info,
+				"discard failed for extent [%llu, %llu]: errno=%d %s",
+					   start, end, ret, btrfs_decode_error(ret));
+			}
+		}
 
 		next_state = btrfs_next_extent_state(unpin, cached_state);
 		btrfs_clear_extent_dirty(unpin, start, end, &cached_state);

fs/btrfs/inode.c

@@ -1392,10 +1392,25 @@ static int cow_one_range(struct btrfs_inode *inode, struct folio *locked_folio,
 	return ret;
 
 free_reserved:
+	/*
+	 * If we have reserved an extent for the current range and failed to
+	 * create the respective extent map or ordered extent, it means that
+	 * when we reserved the extent we decremented the extent's size from
+	 * the data space_info's bytes_may_use counter and
+	 * incremented the space_info's bytes_reserved counter by the same
+	 * amount.
+	 *
+	 * We must make sure extent_clear_unlock_delalloc() does not try
+	 * to decrement again the data space_info's bytes_may_use counter, which
+	 * will be handled by btrfs_free_reserved_extent().
+	 *
+	 * Therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV, but only
+	 * EXTENT_CLEAR_META_RESV.
+	 */
 	extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached,
 				     EXTENT_LOCKED | EXTENT_DELALLOC |
 				     EXTENT_DELALLOC_NEW |
-				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
+				     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV,
 				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
 				     PAGE_END_WRITEBACK);
 	btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL);
@@ -4764,7 +4779,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
-			   btrfs_root_id(root));
+			   btrfs_root_id(dest));
 		ret = -EPERM;
 		goto out_up_write;
 	}

fs/btrfs/ioctl.c

@@ -4581,7 +4581,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
 	struct extent_io_tree *io_tree = &inode->io_tree;
-	struct page **pages;
+	struct page **pages = NULL;
 	struct btrfs_uring_priv *priv = NULL;
 	unsigned long nr_pages;
 	int ret;
@@ -4639,6 +4639,11 @@ out_fail:
 	btrfs_unlock_extent(io_tree, start, lockend, &cached_state);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	kfree(priv);
+	for (int i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			__free_page(pages[i]);
+	}
+	kfree(pages);
 	return ret;
 }
 

fs/btrfs/qgroup.c

@@ -370,7 +370,7 @@ static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrf
 		nr_members++;
 	}
 	mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum ||
-		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum);
+		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != rfer_cmpr_sum);
 
 	WARN(mismatch,
 	     "parent squota qgroup %hu/%llu has mismatched usage from its %d members. "

fs/btrfs/relocation.c

@@ -4723,6 +4723,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = btrfs_remove_dev_extents(trans, chunk_map);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 
@@ -4732,6 +4733,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 		if (unlikely(ret)) {
 			mutex_unlock(&trans->fs_info->chunk_mutex);
 			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
 			return ret;
 		}
 	}
@@ -4750,6 +4752,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = remove_chunk_stripes(trans, chunk_map, path);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 
@@ -5982,6 +5985,9 @@ static int remove_range_from_remap_tree(struct btrfs_trans_handle *trans,
 		struct btrfs_block_group *dest_bg;
 
 		dest_bg = btrfs_lookup_block_group(fs_info, new_addr);
+		if (unlikely(!dest_bg))
+			return -EUCLEAN;
+
 		adjust_block_group_remap_bytes(trans, dest_bg, -overlap_length);
 		btrfs_put_block_group(dest_bg);
 		ret = btrfs_add_to_free_space_tree(trans,

fs/btrfs/scrub.c

@@ -743,7 +743,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		btrfs_warn_rl(fs_info,
 	      "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU",
 			      logical, stripe->mirror_num,
-			      header->fsid, fs_info->fs_devices->fsid);
+			      header->fsid, fs_info->fs_devices->metadata_uuid);
 		return;
 	}
 	if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid,

fs/btrfs/tree-checker.c

@@ -1740,7 +1740,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
 			     objectid > BTRFS_LAST_FREE_OBJECTID)) {
 			extent_err(leaf, slot,
 				   "invalid extent data backref objectid value %llu",
-				   root);
+				   objectid);
 			return -EUCLEAN;
 		}
 		if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
@@ -1921,7 +1921,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf,
 		if (unlikely(prev_key->offset + prev_len > key->offset)) {
 			generic_err(leaf, slot,
 		"dev extent overlap, prev offset %llu len %llu current offset %llu",
-				    prev_key->objectid, prev_len, key->offset);
+				    prev_key->offset, prev_len, key->offset);
 			return -EUCLEAN;
 		}
 	}

fs/btrfs/volumes.c

@@ -6907,7 +6907,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 
 		ret = btrfs_translate_remap(fs_info, &new_logical, length);
 		if (ret)
-			return ret;
+			goto out;
 
 		if (new_logical != logical) {
 			btrfs_free_chunk_map(map);
@@ -6921,8 +6921,10 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	}
 
 	num_copies = btrfs_chunk_map_num_copies(map);
-	if (io_geom.mirror_num > num_copies)
-		return -EINVAL;
+	if (io_geom.mirror_num > num_copies) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	map_offset = logical - map->start;
 	io_geom.raid56_full_stripe_start = (u64)-1;

fs/nfsd/nfsctl.c

@@ -377,15 +377,15 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_threads - Start NFSD, or report the current number of running threads
+ * write_threads - Start NFSD, or report the configured number of threads
  *
  * Input:
  *			buf:		ignored
  *			size:		zero
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero
  *
@@ -399,8 +399,8 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	NFS service is started;
  *			passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -430,7 +430,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_pool_threads - Set or report the current number of threads per pool
+ * write_pool_threads - Set or report the configured number of threads per pool
  *
  * Input:
  *			buf:		ignored
@@ -447,7 +447,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
  *			string containing integer values representing the
- *			number of NFSD threads in each pool;
+ *			configured number of NFSD threads in each pool;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -1647,7 +1647,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 	if (attr)
 		nn->min_threads = nla_get_u32(attr);
 
-	ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope);
+	ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope);
 	if (ret > 0)
 		ret = 0;
 out_unlock:
@@ -1657,7 +1657,7 @@ out_unlock:
 }
 
 /**
- * nfsd_nl_threads_get_doit - get the number of running threads
+ * nfsd_nl_threads_get_doit - get the maximum number of running threads
  * @skb: reply buffer
  * @info: netlink metadata and command arguments
  *
@@ -1700,7 +1700,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
 			struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
 
 			err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
-					  sp->sp_nrthreads);
+					  sp->sp_nrthrmax);
 			if (err)
 				goto err_unlock;
 		}
@@ -2000,7 +2000,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
-					      get_current_cred());
+					      current_cred());
 		/* always save the latest error */
 		if (ret < 0)
 			err = ret;

fs/nfsd/nfssvc.c

@@ -239,12 +239,13 @@ static void nfsd_net_free(struct percpu_ref *ref)
 
 int nfsd_nrthreads(struct net *net)
 {
-	int rv = 0;
+	int i, rv = 0;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	mutex_lock(&nfsd_mutex);
 	if (nn->nfsd_serv)
-		rv = nn->nfsd_serv->sv_nrthreads;
+		for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i)
+			rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax;
 	mutex_unlock(&nfsd_mutex);
 	return rv;
 }
@@ -659,7 +660,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 
 	if (serv)
 		for (i = 0; i < serv->sv_nrpools && i < n; i++)
-			nthreads[i] = serv->sv_pools[i].sp_nrthreads;
+			nthreads[i] = serv->sv_pools[i].sp_nrthrmax;
 	return 0;
 }
 

include/linux/uaccess.h

@@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { }
 /* Define RW variant so the below _mode macro expansion works */
 #define masked_user_rw_access_begin(u)	masked_user_access_begin(u)
 #define user_rw_access_begin(u, s)	user_access_begin(u, s)
-#define user_rw_access_end()		user_access_end()
 
 /* Scoped user access */
-#define USER_ACCESS_GUARD(_mode)				\
-static __always_inline void __user *				\
-class_user_##_mode##_begin(void __user *ptr)			\
-{								\
-	return ptr;						\
-}								\
-								\
-static __always_inline void					\
-class_user_##_mode##_end(void __user *ptr)			\
-{								\
-	user_##_mode##_access_end();				\
-}								\
-								\
-DEFINE_CLASS(user_ ##_mode## _access, void __user *,		\
-	     class_user_##_mode##_end(_T),			\
-	     class_user_##_mode##_begin(ptr), void __user *ptr)	\
-								\
-static __always_inline class_user_##_mode##_access_t		\
-class_user_##_mode##_access_ptr(void __user *scope)		\
-{								\
-	return scope;						\
-}
 
-USER_ACCESS_GUARD(read)
-USER_ACCESS_GUARD(write)
-USER_ACCESS_GUARD(rw)
-#undef USER_ACCESS_GUARD
+/* Cleanup wrapper functions */
+static __always_inline void __scoped_user_read_access_end(const void *p)
+{
+	user_read_access_end();
+};
+static __always_inline void __scoped_user_write_access_end(const void *p)
+{
+	user_write_access_end();
+};
+static __always_inline void __scoped_user_rw_access_end(const void *p)
+{
+	user_access_end();
+};
 
 /**
  * __scoped_user_access_begin - Start a scoped user access
@@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw)
  *
  * Don't use directly. Use scoped_masked_user_$MODE_access() instead.
  */
-#define __scoped_user_access(mode, uptr, size, elbl)					\
-for (bool done = false; !done; done = true)						\
-	for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \
-	     !done; done = true)							\
-		for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true)	\
-			/* Force modified pointer usage within the scope */		\
-			for (const typeof(uptr) uptr = _tmpptr; !done; done = true)
+#define __scoped_user_access(mode, uptr, size, elbl)				\
+for (bool done = false; !done; done = true)					\
+	for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl);	\
+	     !done; done = true)						\
+		/* Force modified pointer usage within the scope */		\
+		for (const auto uptr  __cleanup(__scoped_user_##mode##_access_end) = \
+		     _tmpptr; !done; done = true)
 
 /**
  * scoped_user_read_access_size - Start a scoped user read access with given size

kernel/cgroup/cgroup.c

@@ -2611,6 +2611,7 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 
 	mgctx->tset.nr_tasks++;
 
+	css_set_skip_task_iters(cset, task);
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,

kernel/cgroup/cpuset.c

@@ -61,6 +61,75 @@ static const char * const perr_strings[] = {
 	[PERR_REMOTE]    = "Have remote partition underneath",
 };
 
+/*
+ * CPUSET Locking Convention
+ * -------------------------
+ *
+ * Below are the four global/local locks guarding cpuset structures in lock
+ * acquisition order:
+ *  - cpuset_top_mutex
+ *  - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock)
+ *  - cpuset_mutex
+ *  - callback_lock (raw spinlock)
+ *
+ * As cpuset will now indirectly flush a number of different workqueues in
+ * housekeeping_update() to update housekeeping cpumasks when the set of
+ * isolated CPUs is going to be changed, it may be vulnerable to deadlock
+ * if we hold cpus_read_lock while calling into housekeeping_update().
+ *
+ * The first cpuset_top_mutex will be held except when calling into
+ * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock
+ * and cpuset_mutex will be held instead. The main purpose of this mutex
+ * is to prevent regular cpuset control file write actions from interfering
+ * with the call to housekeeping_update(), though CPU hotplug operation can
+ * still happen in parallel. This mutex also provides protection for some
+ * internal variables.
+ *
+ * A task must hold all the remaining three locks to modify externally visible
+ * or used fields of cpusets, though some of the internally used cpuset fields
+ * and internal variables can be modified without holding callback_lock. If only
+ * reliable read access of the externally used fields are needed, a task can
+ * hold either cpuset_mutex or callback_lock which are exposed to other
+ * external subsystems.
+ *
+ * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others,
+ * ensuring that it is the only task able to also acquire callback_lock and
+ * be able to modify cpusets.  It can perform various checks on the cpuset
+ * structure first, knowing nothing will change. It can also allocate memory
+ * without holding callback_lock. While it is performing these checks, various
+ * callback routines can briefly acquire callback_lock to query cpusets.  Once
+ * it is ready to make the changes, it takes callback_lock, blocking everyone
+ * else.
+ *
+ * Calls to the kernel memory allocator cannot be made while holding
+ * callback_lock which is a spinlock, as the memory allocator may sleep or
+ * call back into cpuset code and acquire callback_lock.
+ *
+ * Now, the task_struct fields mems_allowed and mempolicy may be changed
+ * by other task, we use alloc_lock in the task_struct fields to protect
+ * them.
+ *
+ * The cpuset_common_seq_show() handlers only hold callback_lock across
+ * small pieces of code, such as when reading out possibly multi-word
+ * cpumasks and nodemasks.
+ */
+
+static DEFINE_MUTEX(cpuset_top_mutex);
+static DEFINE_MUTEX(cpuset_mutex);
+
+/*
+ * File level internal variables below follow one of the following exclusion
+ * rules.
+ *
+ * RWCS: Read/write-able by holding either cpus_write_lock (and optionally
+ *	 cpuset_mutex) or both cpus_read_lock and cpuset_mutex.
+ *
+ * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable
+ *	 by holding both cpuset_mutex and callback_lock.
+ *
+ * T:	 Read/write-able by holding the cpuset_top_mutex.
+ */
+
 /*
  * For local partitions, update to subpartitions_cpus & isolated_cpus is done
  * in update_parent_effective_cpumask(). For remote partitions, it is done in
@@ -70,19 +139,22 @@ static const char * const perr_strings[] = {
  * Exclusive CPUs distributed out to local or remote sub-partitions of
  * top_cpuset
  */
-static cpumask_var_t	subpartitions_cpus;
+static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 
 /*
- * Exclusive CPUs in isolated partitions
+ * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated)
  */
-static cpumask_var_t	isolated_cpus;
+static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * isolated_cpus updating flag (protected by cpuset_mutex)
- * Set if isolated_cpus is going to be updated in the current
- * cpuset_mutex crtical section.
+ * Set if housekeeping cpumasks are to be updated.
  */
-static bool isolated_cpus_updating;
+static bool		update_housekeeping;	/* RWCS */
+
+/*
+ * Copy of isolated_cpus to be passed to housekeeping_update()
+ */
+static cpumask_var_t	isolated_hk_cpus;	/* T */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -98,7 +170,7 @@ static bool isolated_cpus_updating;
  * Note that update_relax_domain_level() in cpuset-v1.c can still call
  * rebuild_sched_domains_locked() directly without using this flag.
  */
-static bool force_sd_rebuild;
+static bool force_sd_rebuild;			/* RWCS */
 
 /*
  * Partition root states:
@@ -218,42 +290,6 @@ struct cpuset top_cpuset = {
 	.partition_root_state = PRS_ROOT,
 };
 
-/*
- * There are two global locks guarding cpuset structures - cpuset_mutex and
- * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel
- * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
- * structures. Note that cpuset_mutex needs to be a mutex as it is used in
- * paths that rely on priority inheritance (e.g. scheduler - on RT) for
- * correctness.
- *
- * A task must hold both locks to modify cpusets.  If a task holds
- * cpuset_mutex, it blocks others, ensuring that it is the only task able to
- * also acquire callback_lock and be able to modify cpusets.  It can perform
- * various checks on the cpuset structure first, knowing nothing will change.
- * It can also allocate memory while just holding cpuset_mutex.  While it is
- * performing these checks, various callback routines can briefly acquire
- * callback_lock to query cpusets.  Once it is ready to make the changes, it
- * takes callback_lock, blocking everyone else.
- *
- * Calls to the kernel memory allocator can not be made while holding
- * callback_lock, as that would risk double tripping on callback_lock
- * from one of the callbacks into the cpuset code from within
- * __alloc_pages().
- *
- * If a task is only holding callback_lock, then it has read-only
- * access to cpusets.
- *
- * Now, the task_struct fields mems_allowed and mempolicy may be changed
- * by other task, we use alloc_lock in the task_struct fields to protect
- * them.
- *
- * The cpuset_common_seq_show() handlers only hold callback_lock across
- * small pieces of code, such as when reading out possibly multi-word
- * cpumasks and nodemasks.
- */
-
-static DEFINE_MUTEX(cpuset_mutex);
-
 /**
  * cpuset_lock - Acquire the global cpuset mutex
  *
@@ -283,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void)
  */
 void cpuset_full_lock(void)
 {
+	mutex_lock(&cpuset_top_mutex);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 }
@@ -291,12 +328,14 @@ void cpuset_full_unlock(void)
 {
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
+	mutex_unlock(&cpuset_top_mutex);
 }
 
 #ifdef CONFIG_LOCKDEP
 bool lockdep_is_cpuset_held(void)
 {
-	return lockdep_is_held(&cpuset_mutex);
+	return lockdep_is_held(&cpuset_mutex) ||
+	       lockdep_is_held(&cpuset_top_mutex);
 }
 #endif
 
@@ -961,7 +1000,7 @@ void rebuild_sched_domains_locked(void)
 	* offline CPUs, a warning is emitted and we return directly to
 	* prevent the panic.
 	*/
-	for (i = 0; i < ndoms; ++i) {
+	for (i = 0; doms && i < ndoms; i++) {
 		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask)))
 			return;
 	}
@@ -1162,12 +1201,18 @@ static void reset_partition_data(struct cpuset *cs)
 static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
 	WARN_ON_ONCE(old_prs == new_prs);
-	if (new_prs == PRS_ISOLATED)
+	lockdep_assert_held(&callback_lock);
+	lockdep_assert_held(&cpuset_mutex);
+	if (new_prs == PRS_ISOLATED) {
+		if (cpumask_subset(xcpus, isolated_cpus))
+			return;
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
-	else
+	} else {
+		if (!cpumask_intersects(xcpus, isolated_cpus))
+			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
-
-	isolated_cpus_updating = true;
+	}
+	update_housekeeping = true;
 }
 
 /*
@@ -1220,8 +1265,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent,
 		isolated_cpus_update(old_prs, parent->partition_root_state,
 				     xcpus);
 
-	cpumask_and(xcpus, xcpus, cpu_active_mask);
 	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+	cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask);
 }
 
 /*
@@ -1285,22 +1330,43 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_isolation_cpumasks - Update external isolation related CPU masks
+ * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
  *
- * The following external CPU masks will be updated if necessary:
- * - workqueue unbound cpumask
+ * Update housekeeping cpumasks and rebuild sched domains if necessary.
+ * This should be called at the end of cpuset or hotplug actions.
  */
-static void update_isolation_cpumasks(void)
+static void update_hk_sched_domains(void)
 {
-	int ret;
+	if (update_housekeeping) {
+		/* Updating HK cpumasks implies rebuild sched domains */
+		update_housekeeping = false;
+		force_sd_rebuild = true;
+		cpumask_copy(isolated_hk_cpus, isolated_cpus);
 
-	if (!isolated_cpus_updating)
-		return;
+		/*
+		 * housekeeping_update() is now called without holding
+		 * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex
+		 * is still being held for mutual exclusion.
+		 */
+		mutex_unlock(&cpuset_mutex);
+		cpus_read_unlock();
+		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
+		cpus_read_lock();
+		mutex_lock(&cpuset_mutex);
+	}
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
+}
 
-	ret = housekeeping_update(isolated_cpus);
-	WARN_ON_ONCE(ret < 0);
-
-	isolated_cpus_updating = false;
+/*
+ * Work function to invoke update_hk_sched_domains()
+ */
+static void hk_sd_workfn(struct work_struct *work)
+{
+	cpuset_full_lock();
+	update_hk_sched_domains();
+	cpuset_full_unlock();
 }
 
 /**
@@ -1451,7 +1517,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	cs->remote_partition = true;
 	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 	cs->prs_err = 0;
 
@@ -1496,7 +1561,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 	compute_excpus(cs, cs->effective_xcpus);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 
 	/*
@@ -1567,7 +1631,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	if (xcpus)
 		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	if (adding || deleting)
 		cpuset_force_rebuild();
 
@@ -1911,7 +1974,6 @@ write_error:
 		partition_xcpus_add(new_prs, parent, tmp->delmask);
 
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive_flag(cs, new_prs);
@@ -2156,7 +2218,7 @@ get_css:
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		cpuset_update_tasks_cpumask(cp, cp->effective_cpus);
+		cpuset_update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE
@@ -2879,7 +2941,6 @@ out:
 	else if (isolcpus_updated)
 		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
@@ -3169,9 +3230,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	}
 
 	free_cpuset(trialcs);
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 out_unlock:
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
@@ -3279,6 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	return retval ?: nbytes;
 }
@@ -3453,6 +3514,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 }
 
@@ -3608,6 +3670,7 @@ int __init cpuset_init(void)
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -3779,6 +3842,7 @@ unlock:
  */
 static void cpuset_handle_hotplug(void)
 {
+	static DECLARE_WORK(hk_sd_work, hk_sd_workfn);
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
@@ -3860,9 +3924,21 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-	/* rebuild sched domains if necessary */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_cpuslocked();
+
+	/*
+	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
+	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
+	 * cpumask can correctly reflect what is in isolated_cpus.
+	 *
+	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
+	 * is still pending. Before the pending bit is cleared, the work data
+	 * is copied out and work item dequeued. So it is possible to queue
+	 * the work again before the hk_sd_workfn() is invoked to process the
+	 * previously queued work. Since hk_sd_workfn() doesn't use the work
+	 * item at all, this is not a problem.
+	 */
+	if (update_housekeeping || force_sd_rebuild)
+		queue_work(system_unbound_wq, &hk_sd_work);
 
 	free_tmpmasks(ptmp);
 }

kernel/sched/ext.c

@@ -977,8 +977,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a,
 
 static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
 {
-	/* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
-	WRITE_ONCE(dsq->nr, dsq->nr + delta);
+	/*
+	 * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE()
+	 * on the read side and WRITE_ONCE() on the write side to properly
+	 * annotate the concurrent lockless access and avoid KCSAN warnings.
+	 */
+	WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta);
 }
 
 static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)
@@ -2736,7 +2740,7 @@ static bool check_rq_for_timeouts(struct rq *rq)
 		unsigned long last_runnable = p->scx.runnable_at;
 
 		if (unlikely(time_after(jiffies,
-					last_runnable + scx_watchdog_timeout))) {
+					last_runnable + READ_ONCE(scx_watchdog_timeout)))) {
 			u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);
 
 			scx_exit(sch, SCX_EXIT_ERROR_STALL, 0,
@@ -2764,7 +2768,7 @@ static void scx_watchdog_workfn(struct work_struct *work)
 		cond_resched();
 	}
 	queue_delayed_work(system_unbound_wq, to_delayed_work(work),
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 }
 
 void scx_tick(struct rq *rq)
@@ -3586,7 +3590,6 @@ static int scx_cgroup_init(struct scx_sched *sch)
 		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
-			css_put(css);
 			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
@@ -3709,7 +3712,9 @@ static void scx_kobj_release(struct kobject *kobj)
 static ssize_t scx_attr_ops_show(struct kobject *kobj,
 				 struct kobj_attribute *ka, char *buf)
 {
-	return sysfs_emit(buf, "%s\n", scx_root->ops.name);
+	struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return sysfs_emit(buf, "%s\n", sch->ops.name);
 }
 SCX_ATTR(ops);
 
@@ -3753,7 +3758,9 @@ static const struct kobj_type scx_ktype = {
 
 static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
-	return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name);
+	const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return add_uevent_var(env, "SCXOPS=%s", sch->ops.name);
 }
 
 static const struct kset_uevent_ops scx_uevent_ops = {
@@ -4424,10 +4431,19 @@ done:
 	scx_bypass(false);
 }
 
+/*
+ * Claim the exit on @sch. The caller must ensure that the helper kthread work
+ * is kicked before the current task can be preempted. Once exit_kind is
+ * claimed, scx_error() can no longer trigger, so if the current task gets
+ * preempted and the BPF scheduler fails to schedule it back, the helper work
+ * will never be kicked and the whole system can wedge.
+ */
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind)
 {
 	int none = SCX_EXIT_NONE;
 
+	lockdep_assert_preemption_disabled();
+
 	if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind))
 		return false;
 
@@ -4450,6 +4466,7 @@ static void scx_disable(enum scx_exit_kind kind)
 	rcu_read_lock();
 	sch = rcu_dereference(scx_root);
 	if (sch) {
+		guard(preempt)();
 		scx_claim_exit(sch, kind);
 		kthread_queue_work(sch->helper, &sch->disable_work);
 	}
@@ -4772,6 +4789,8 @@ static bool scx_vexit(struct scx_sched *sch,
 {
 	struct scx_exit_info *ei = sch->exit_info;
 
+	guard(preempt)();
+
 	if (!scx_claim_exit(sch, kind))
 		return false;
 
@@ -4956,20 +4975,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	return 0;
 }
 
-static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+/*
+ * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
+ * starvation. During the READY -> ENABLED task switching loop, the calling
+ * thread's sched_class gets switched from fair to ext. As fair has higher
+ * priority than ext, the calling thread can be indefinitely starved under
+ * fair-class saturation, leading to a system hang.
+ */
+struct scx_enable_cmd {
+	struct kthread_work	work;
+	struct sched_ext_ops	*ops;
+	int			ret;
+};
+
+static void scx_enable_workfn(struct kthread_work *work)
 {
+	struct scx_enable_cmd *cmd =
+		container_of(work, struct scx_enable_cmd, work);
+	struct sched_ext_ops *ops = cmd->ops;
 	struct scx_sched *sch;
 	struct scx_task_iter sti;
 	struct task_struct *p;
 	unsigned long timeout;
 	int i, cpu, ret;
 
-	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
-			   cpu_possible_mask)) {
-		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
-		return -EINVAL;
-	}
-
 	mutex_lock(&scx_enable_mutex);
 
 	if (scx_enable_state() != SCX_DISABLED) {
@@ -5061,7 +5090,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	WRITE_ONCE(scx_watchdog_timeout, timeout);
 	WRITE_ONCE(scx_watchdog_timestamp, jiffies);
 	queue_delayed_work(system_unbound_wq, &scx_watchdog_work,
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 
 	/*
 	 * Once __scx_enabled is set, %current can be switched to SCX anytime.
@@ -5186,13 +5215,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	atomic_long_inc(&scx_enable_seq);
 
-	return 0;
+	cmd->ret = 0;
+	return;
 
 err_free_ksyncs:
 	free_kick_syncs();
 err_unlock:
 	mutex_unlock(&scx_enable_mutex);
-	return ret;
+	cmd->ret = ret;
+	return;
 
 err_disable_unlock_all:
 	scx_cgroup_unlock();
@@ -5211,7 +5242,41 @@ err_disable:
 	 */
 	scx_error(sch, "scx_enable() failed (%d)", ret);
 	kthread_flush_work(&sch->disable_work);
-	return 0;
+	cmd->ret = 0;
+}
+
+static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+{
+	static struct kthread_worker *helper;
+	static DEFINE_MUTEX(helper_mutex);
+	struct scx_enable_cmd cmd;
+
+	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
+			   cpu_possible_mask)) {
+		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
+		return -EINVAL;
+	}
+
+	if (!READ_ONCE(helper)) {
+		mutex_lock(&helper_mutex);
+		if (!helper) {
+			helper = kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(helper)) {
+				helper = NULL;
+				mutex_unlock(&helper_mutex);
+				return -ENOMEM;
+			}
+			sched_set_fifo(helper->task);
+		}
+		mutex_unlock(&helper_mutex);
+	}
+
+	kthread_init_work(&cmd.work, scx_enable_workfn);
+	cmd.ops = ops;
+
+	kthread_queue_work(READ_ONCE(helper), &cmd.work);
+	kthread_flush_work(&cmd.work);
+	return cmd.ret;
 }
 
 

kernel/sched/ext_idle.c

@@ -663,9 +663,8 @@ void scx_idle_init_masks(void)
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL));
 
-	/* Allocate per-node idle cpumasks */
-	scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks,
-					   num_possible_nodes());
+	/* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */
+	scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks, nr_node_ids);
 	BUG_ON(!scx_idle_node_masks);
 
 	for_each_node(i) {

kernel/sched/ext_internal.h

@@ -74,7 +74,7 @@ enum scx_exit_flags {
 	 * info communication. The following flag indicates whether ops.init()
 	 * finished successfully.
 	 */
-	SCX_EFLAG_INITIALIZED,
+	SCX_EFLAG_INITIALIZED   = 1LLU << 0,
 };
 
 /*

kernel/sched/isolation.c

@@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask)
 	struct cpumask *trial, *old = NULL;
 	int err;
 
-	lockdep_assert_cpus_held();
-
 	trial = kmalloc(cpumask_size(), GFP_KERNEL);
 	if (!trial)
 		return -ENOMEM;
@@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask)
 	}
 
 	if (!housekeeping.flags)
-		static_branch_enable_cpuslocked(&housekeeping_overridden);
+		static_branch_enable(&housekeeping_overridden);
 
 	if (housekeeping.flags & HK_FLAG_DOMAIN)
 		old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN);

kernel/time/jiffies.c

@@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies);
 int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ)
-		return -EINVAL;
 	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
 				  do_proc_int_conv_userhz_jiffies);
 }

kernel/time/timer_migration.c

@@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
 	int cpu;
 
-	lockdep_assert_cpus_held();
-
 	if (!works)
 		return -ENOMEM;
 	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
@@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	 * First set previously isolated CPUs as available (unisolate).
 	 * This cpumask contains only CPUs that switched to available now.
 	 */
+	guard(cpus_read_lock)();
 	cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask);
 	cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask);
 
@@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void)
 	cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 	/* Protect against RCU torture hotplug testing */
-	guard(cpus_read_lock)();
 	return tmigr_isolated_exclude_cpumask(cpumask);
 }
 late_initcall(tmigr_init_isolation);

tools/sched_ext/Kconfig

@@ -0,0 +1,61 @@
+# sched-ext mandatory options
+#
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_SCHED_CLASS_EXT=y
+
+# Required by some rust schedulers (e.g. scx_p2dq)
+#
+CONFIG_KALLSYMS_ALL=y
+
+# Required on arm64
+#
+# CONFIG_DEBUG_INFO_REDUCED is not set
+
+# LAVD tracks futex to give an additional time slice for futex holder
+# (i.e., avoiding lock holder preemption) for better system-wide progress.
+# LAVD first tries to use ftrace to trace futex function calls.
+# If that is not available, it tries to use a tracepoint.
+CONFIG_FUNCTION_TRACER=y
+
+# Enable scheduling debugging
+#
+CONFIG_SCHED_DEBUG=y
+
+# Enable extra scheduling features (for a better code coverage while testing
+# the schedulers)
+#
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_SCHED_CORE=y
+CONFIG_SCHED_MC=y
+
+# Enable fully preemptible kernel for a better test coverage of the schedulers
+#
+# CONFIG_PREEMPT_NONE is not set
+# CONFIG_PREEMPT_VOLUNTARY is not set
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+
+# Additional debugging information (useful to catch potential locking issues)
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_PROVE_LOCKING=y
+
+# Bpftrace headers (for additional debug info)
+CONFIG_BPF_EVENTS=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_KPROBES=y
+CONFIG_KPROBE_EVENTS=y
+CONFIG_UPROBES=y
+CONFIG_UPROBE_EVENTS=y
+CONFIG_DEBUG_FS=y
+
+# Enable access to kernel configuration and headers at runtime
+CONFIG_IKHEADERS=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_IKCONFIG=y

tools/sched_ext/Makefile

@@ -122,6 +122,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     -I../../include							\
 	     $(call get_sys_includes,$(CLANG))					\
 	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building

tools/sched_ext/README.md

@@ -58,14 +58,8 @@ CONFIG_SCHED_CLASS_EXT=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_DEBUG_INFO_BTF=y
-```
-
-It's also recommended that you also include the following Kconfig options:
-
-```
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
-CONFIG_PAHOLE_HAS_BTF_TAG=y
 ```
 
 There is a `Kconfig` file in this directory whose contents you can append to

tools/sched_ext/include/scx/compat.h

@@ -125,6 +125,7 @@ static inline long scx_hotplug_seq(void)
 {
 	int fd;
 	char buf[32];
+	char *endptr;
 	ssize_t len;
 	long val;
 
@@ -137,8 +138,10 @@ static inline long scx_hotplug_seq(void)
 	buf[len] = 0;
 	close(fd);
 
-	val = strtoul(buf, NULL, 10);
-	SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val);
+	errno = 0;
+	val = strtoul(buf, &endptr, 10);
+	SCX_BUG_ON(errno == ERANGE || endptr == buf ||
+		   (*endptr != '\n' && *endptr != '\0'), "invalid num hotplug events: %ld", val);
 
 	return val;
 }

tools/sched_ext/scx_central.c

@@ -66,7 +66,7 @@ restart:
 	assert(skel->rodata->nr_cpu_ids > 0);
 	assert(skel->rodata->nr_cpu_ids <= INT32_MAX);
 
-	while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:c:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;

tools/sched_ext/scx_sdt.c

@@ -54,7 +54,7 @@ restart:
 	optind = 1;
 	skel = SCX_OPS_OPEN(sdt_ops, scx_sdt);
 
-	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+	while ((opt = getopt(argc, argv, "vh")) != -1) {
 		switch (opt) {
 		case 'v':
 			verbose = true;

tools/testing/selftests/cgroup/test_cpuset_prs.sh

@@ -196,7 +196,6 @@ test_add_proc()
 #  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
 #  C<l> = add cpu-list to cpuset.cpus
 #  X<l> = add cpu-list to cpuset.cpus.exclusive
-#  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
 #  CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
 #  O<c>=<v> = Write <v> to CPU online file of <c>
@@ -209,44 +208,46 @@ test_add_proc()
 # sched-debug matching which includes offline CPUs and single-CPU partitions
 # while the second one is for matching cpuset.cpus.isolated.
 #
-SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
+SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1"
 TEST_MATRIX=(
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
-	"   C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .      .     0 A2:0-1"
 	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
-	"  C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
-	"  C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
+	"   C0-1     .      .    C2-3    P1   C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3    P1    C1:P1    .      .     0 "
+	"   C0-1     .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3     .     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .     P1     0 "
 	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
-	"  C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
 	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
 	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
-	"C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
-	"C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
+	"  C0-3:P1 C2-3:P1  .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
+	"  C2-3:P1  C2:P1   .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# CPU offlining cases:
-	"   C0-1     .      .    C2-3    S+    C4-5     .     O2=0   0 A1:0-1|B1:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
-	"C2-3:P1:S+  C3:P1  .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .     O2=0   0 A1:0-1|B1:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
+	"  C2-3:P1  C3:P1   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P2   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-2"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0   .      .     0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0  O3=1    .     0 A1:1-2|A2:3 A1:P1|A2:P2  3"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -264,88 +265,87 @@ TEST_MATRIX=(
 	#
 	# Remote partition and cpuset.cpus.exclusive tests
 	#
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
-	" C0-3:S+ C1-3:S+ C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
+	"   C0-3    C1-3  C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+	"  C4:X0-3  X1-3  X2-3     .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+	"  C4:X0-3  X1-3  X2-3     .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
 
 	# Nested remote/local partition tests
-	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+	"   C0-3    C1-3  C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P0|B1:P1"
-	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
+	"   C0-3    C1-3   C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
 								       A1:P0|A2:P2|A3:P1 2-4|2-3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
 								       A1:P0|A2:P2|A3:P1 2"
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      X5      .      .    0 A1:0-4|A2:1-4|A3:2-4 \
 								       A1:P0|A2:P-2|A3:P-1 ."
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
 								       A1:P0|A2:P2|A3:P-1 2-4"
 
 	# Remote partition offline tests
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
 
 	# An invalidated remote partition cannot self-recover from hotplug
-	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+	"   C0-3    C1-3   C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
 
 	# cpus.exclusive.effective clearing test
-	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
+	"   C0-3    C1-3   C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
 
 	# Invalid to valid remote partition transition test
-	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
-	" C0-3:S+ C1-3:X3:P2
-			    .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+	"   C0-3    C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+	"   C0-3 C1-3:X3:P2 .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
 
 	# Invalid to valid local partition direct transition tests
-	" C1-3:S+:P2 X4:P2  .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
-	" C1-3:S+:P2 X4:P2  .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
-	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
-	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+	" C1-3:P2  X4:P2    .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+	" C1-3:P2  X4:P2    .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+	" C0-3:P2    .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
+	" C0-3:P2    .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
 
 	# Local partition invalidation tests
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .      .      .      .     0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .     X4      .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .    C4:X     .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
 	# Local partition CPU change tests
-	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
-	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+	" C0-5:P2  C4-5:P1  .      .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+	" C0-5:P2  C4-5:P1  .      .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
 
 	# cpus_allowed/exclusive_cpus update tests
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .    X:C4     .      P2     .     0 A1:4|A2:4|XA2:|XA3:|A3:4 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .     X1      .      P2     .     0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .      .     X3      P2     .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .      .     X3      .      .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .     X4      .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
 								       A1:P0|A3:P-2"
 
@@ -356,37 +356,37 @@ TEST_MATRIX=(
 	#
 	# Adding CPUs to partition root that are not in parent's
 	# cpuset.cpus is allowed, but those extra CPUs are ignored.
-	"C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
+	"  C2-3:P1   C3:P1  .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
 
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
-	"C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
-	" C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+	"   C3:P1     C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
 	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# Changing a partition root to member makes child partitions invalid
-	"C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
 
 	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
 	# as they overlap.
-	"C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1   .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
 
 	# Deletion of CPUs distributed to child cgroup is allowed.
-	"C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
+	"  C0-1:P1  C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
 
 	# To become a valid partition root, cpuset.cpus must overlap parent's
 	# cpuset.cpus.
-	"  C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
+	"  C0-1:P1   .      .    C2-3     .   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
 
 	# Enabling partition with child cpusets is allowed
-	"  C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
+	"   C0-1    C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
 
 	# A partition root with non-partition root parent is invalid| but it
 	# can be made valid if its parent becomes a partition root too.
-	"  C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
-	"  C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
+	"   C0-1    C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
+	"   C0-1   C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
 
 	# A non-exclusive cpuset.cpus change will not invalidate its siblings partition.
 	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2|B1:3 A1:P1|B1:P0"
@@ -398,23 +398,23 @@ TEST_MATRIX=(
 
 	# Child partition root that try to take all CPUs from parent partition
 	# with tasks will remain invalid.
-	" C1-4:P1:S+ P1     .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
-	" C1-4:P1:S+ P1     .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
-	" C1-4:P1:S+ P1     .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
+	"  C1-4:P1  P1      .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
 
 	# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
 	# affect cpuset.cpus.exclusive.effective.
-	" C1-4:X3:S+ C1:X3  .      .       .     C      .      .     0 A2:1-4|XA2:3"
+	"  C1-4:X3 C1:X3    .      .       .     C      .      .     0 A2:1-4|XA2:3"
 
 	# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
 	# but creating a local partition out of it is not allowed. Similarly and change
 	# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
 	# invalidate it.
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
 								       A1:P0|A2:P2:B1:P1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
 
 	# When multiple partitions with conflicting cpuset.cpus are created, the
@@ -426,14 +426,14 @@ TEST_MATRIX=(
 	" C1-3:X1-3  .      .    C4-5      .     .      .     C1-2   0 A1:1-3|B1:1-2"
 
 	# cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
-	" C1-3:S+   C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
+	"   C1-3    C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
 
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	# Failure cases:
 
 	# A task cannot be added to a partition with no cpu
-	"C2-3:P1:S+  C3:P1  .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1 C3:P1    .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
 
 	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
 	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3|B1:4-5"
@@ -465,31 +465,31 @@ REMOTE_TEST_MATRIX=(
 	#  old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
 	#  new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------- ------- ------- ------- ----- ------ --------
-	" X1-3:S+ X4-6:S+ X1-2     X3     X4-5     X6 \
+	"   X1-3   X4-6  X1-2      X3     X4-5     X6 \
 	      .      .     P2      P2      P2      P2    c11:1-2|c12:3|c21:4-5|c22:6 \
 							 c11:P2|c12:P2|c21:P2|c22:P2 1-6"
-	" CX1-4:S+   .   X1-2:P2   C3      .       .  \
+	"  CX1-4     .  X1-2:P2    C3      .       .  \
 	      .      .     .      C3-4     .       .     p1:3-4|c11:1-2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P0 1-2"
-	" CX1-4:S+   .   X1-2:P2   .       .       .  \
+	"  CX1-4     .  X1-2:P2    .       .       .  \
 	    X2-4     .     .       .       .       .     p1:1,3-4|c11:2 \
 							 p1:P0|c11:P2 2"
-	" CX1-5:S+   .   X1-2:P2 X3-5:P1   .       .  \
+	"  CX1-5     .  X1-2:P2  X3-5:P1   .       .  \
 	    X2-4     .     .       .       .       .     p1:1,5|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X2      .       .       .     p1:1|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
 	# p1 as member, will get its effective CPUs from its parent rtest
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X1     CX2-4    .       .     p1:5-7|c11:1|c12:2-4 \
 							 p1:P0|c11:P2|c12:P1 1"
-	" CX1-4:S+ X5-6:P1:S+ .    .       .       .  \
-	      .      .   X1-2:P2  X4-5:P1  .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+	"  CX1-4  X5-6:P1  .       .       .       .  \
+	      .      .  X1-2:P2  X4-5:P1   .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
 							 p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
 							 1-2,4-6|1-2,5-6"
 	# c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition
-	" C1-5:P1:S+ .  C1-4:P1   C2-3     .       .  \
+	"  C1-5:P1   .  C1-4:P1   C2-3     .       .  \
 	      .      .     .       P1      .       .     p1:5|c11:1-4|c12:5 \
 							 p1:P1|c11:P1|c12:P-1"
 )
@@ -530,7 +530,6 @@ set_ctrl_state()
 	CGRP=$1
 	STATE=$2
 	SHOWERR=${3}
-	CTRL=${CTRL:=$CONTROLLER}
 	HASERR=0
 	REDIRECT="2> $TMPMSG"
 	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
@@ -540,15 +539,16 @@ set_ctrl_state()
 	for CMD in $(echo $STATE | sed -e "s/:/ /g")
 	do
 		TFILE=$CGRP/cgroup.procs
-		SFILE=$CGRP/cgroup.subtree_control
 		PFILE=$CGRP/cpuset.cpus.partition
 		CFILE=$CGRP/cpuset.cpus
 		XFILE=$CGRP/cpuset.cpus.exclusive
-		case $CMD in
-		    S*) PREFIX=${CMD#?}
-			COMM="echo ${PREFIX}${CTRL} > $SFILE"
+
+		# Enable cpuset controller if not enabled yet
+		[[ -f $CFILE ]] || {
+			COMM="echo +cpuset > $CGRP/../cgroup.subtree_control"
 			eval $COMM $REDIRECT
-			;;
+		}
+		case $CMD in
 		    X*)
 			CPUS=${CMD#?}
 			COMM="echo $CPUS > $XFILE"
@@ -764,7 +764,7 @@ check_cgroup_states()
 # only CPUs in isolated partitions as well as those that are isolated at
 # boot time.
 #
-# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
 # <isolcpus1> - expected sched/domains value
 # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
 #
@@ -773,6 +773,7 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
+	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -810,6 +811,11 @@ check_isolcpus()
 	ISOLCPUS=
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
+	#
+	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
+	#
+	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
+
 	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#
@@ -947,7 +953,6 @@ check_test_results()
 run_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
 	RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
 	I=0
@@ -1003,7 +1008,6 @@ run_state_test()
 run_remote_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	[[ -d rtest ]] || mkdir rtest
 	cd rtest
 	echo +cpuset > cgroup.subtree_control

tools/testing/selftests/sched_ext/Makefile

@@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     $(CLANG_SYS_INCLUDES) 						\
 	     -Wall -Wno-compare-distinct-pointer-types				\
 	     -Wno-incompatible-function-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building

tools/testing/selftests/sched_ext/init_enable_count.c

@@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global)
 			char buf;
 
 			close(pipe_fds[1]);
-			read(pipe_fds[0], &buf, 1);
+			if (read(pipe_fds[0], &buf, 1) < 0)
+				exit(1);
 			close(pipe_fds[0]);
 			exit(0);
 		}

tools/testing/selftests/sched_ext/peek_dsq.bpf.c

@@ -58,14 +58,14 @@ static void record_peek_result(long pid)
 {
 	u32 slot_key;
 	long *slot_pid_ptr;
-	int ix;
+	u32 ix;
 
 	if (pid <= 0)
 		return;
 
 	/* Find an empty slot or one with the same PID */
 	bpf_for(ix, 0, 10) {
-		slot_key = (pid + ix) % MAX_SAMPLES;
+		slot_key = ((u64)pid + ix) % MAX_SAMPLES;
 		slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key);
 		if (!slot_pid_ptr)
 			continue;

tools/testing/selftests/sched_ext/rt_stall.c

@@ -15,7 +15,6 @@
 #include <signal.h>
 #include <bpf/bpf.h>
 #include <scx/common.h>
-#include <unistd.h>
 #include "rt_stall.bpf.skel.h"
 #include "scx_test.h"
 #include "../kselftest.h"

tools/testing/selftests/sched_ext/runner.c

@@ -166,6 +166,9 @@ int main(int argc, char **argv)
 		enum scx_test_status status;
 		struct scx_test *test = &__scx_tests[i];
 
+		if (exit_req)
+			break;
+
 		if (list) {
 			printf("%s\n", test->name);
 			if (i == (__scx_num_tests - 1))