Merge branch 'perf-tools' into perf-tools-next

To get some fixes in the perf test and JSON metrics into the development
branch.

Signed-off-by: Namhyung Kim <[e-mail]>

Documentation/filesystems/overlayfs.rst

···
 that files have been removed.  This is done using whiteouts and opaque
 directories (non-directories are always opaque).
 
-A whiteout is created as a character device with 0/0 device number.
+A whiteout is created as a character device with 0/0 device number or
+as a zero-size regular file with the xattr "trusted.overlay.whiteout".
+
 When a whiteout is found in the upper level of a merged directory, any
 matching name in the lower level is ignored, and the whiteout itself
 is also hidden.
···
 A directory is made opaque by setting the xattr "trusted.overlay.opaque"
 to "y".  Where the upper filesystem contains an opaque directory, any
 directory in the lower filesystem with the same name is ignored.
+
+An opaque directory should not conntain any whiteouts, because they do not
+serve any purpose.  A merge directory containing regular files with the xattr
+"trusted.overlay.whiteout", should be additionally marked by setting the xattr
+"trusted.overlay.opaque" to "x" on the merge directory itself.
+This is needed to avoid the overhead of checking the "trusted.overlay.whiteout"
+on all entries during readdir in the common case.
 
 readdir
 -------
···
 mount, so to support storing an effective whiteout file in an overlayfs mount an
 alternative form of whiteout is supported. This form is a regular, zero-size
 file with the "overlay.whiteout" xattr set, inside a directory with the
-"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs,
-but can be used by userspace tools (like containers) that generate lower layers.
+"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_).
+These alternative whiteouts are never created by overlayfs, but can be used by
+userspace tools (like containers) that generate lower layers.
 These alternative whiteouts can be escaped using the standard xattr escape
 mechanism in order to properly nest to any depth.
 

MAINTAINERS

···
 
 CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
 M:	David Howells <[e-mail]>
-L:	[e-mail] (moderated for non-subscribers)
+L:	[e-mail]
 S:	Supported
 F:	Documentation/filesystems/caching/cachefiles.rst
 F:	fs/cachefiles/
···
 S:	Maintained
 F:	rust/kernel/net/phy.rs
 
-EXEC & BINFMT API
+EXEC & BINFMT API, ELF
 R:	Eric Biederman <[e-mail]>
 R:	Kees Cook <[e-mail]>
 L:	[e-mail]
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
+F:	Documentation/userspace-api/ELF.rst
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h
···
 
 FILESYSTEMS [NETFS LIBRARY]
 M:	David Howells <[e-mail]>
-L:	[e-mail] (moderated for non-subscribers)
+R:	Jeff Layton <[e-mail]>
+L:	[e-mail]
 L:	[e-mail]
 S:	Supported
 F:	Documentation/filesystems/caching/

Makefile

···
 # perform bounds checking.
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
+#Currently, disable -Wstringop-overflow for GCC 11, globally.
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 

arch/riscv/net/bpf_jit_comp64.c

···
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+	bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT;
 	void *orig_call = func_addr;
 	bool save_ret;
 	u32 insn;
···
 
 	stack_size = round_up(stack_size, 16);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* For the trampoline called from function entry,
 		 * the frame of traced function and the frame of
 		 * trampoline need to be considered.
···
 
 	emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
 
-	if (func_addr) {
+	if (!is_struct_ops) {
 		/* trampoline called from function entry */
 		emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx);
 		emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx);

drivers/block/rbd.c

···
 static void rbd_lock_del_request(struct rbd_img_request *img_req)
 {
 	struct rbd_device *rbd_dev = img_req->rbd_dev;
-	bool need_wakeup;
+	bool need_wakeup = false;
 
 	lockdep_assert_held(&rbd_dev->lock_rwsem);
 	spin_lock(&rbd_dev->lock_lists_lock);
-	rbd_assert(!list_empty(&img_req->lock_item));
-	list_del_init(&img_req->lock_item);
-	need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
-		       list_empty(&rbd_dev->running_list));
+	if (!list_empty(&img_req->lock_item)) {
+		list_del_init(&img_req->lock_item);
+		need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
+			       list_empty(&rbd_dev->running_list));
+	}
 	spin_unlock(&rbd_dev->lock_lists_lock);
 	if (need_wakeup)
 		complete(&rbd_dev->releasing_wait);
···
 		return;
 	}
 
-	list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) {
+	while (!list_empty(&rbd_dev->acquiring_list)) {
+		img_req = list_first_entry(&rbd_dev->acquiring_list,
+					   struct rbd_img_request, lock_item);
 		mutex_lock(&img_req->state_mutex);
 		rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK);
+		if (!result)
+			list_move_tail(&img_req->lock_item,
+				       &rbd_dev->running_list);
+		else
+			list_del_init(&img_req->lock_item);
 		rbd_img_schedule(img_req, result);
 		mutex_unlock(&img_req->state_mutex);
 	}
-
-	list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list);
 }
 
 static bool locker_equal(const struct ceph_locker *lhs,
···
 
 	if (need_put) {
 		destroy_workqueue(rbd_dev->task_wq);
-		ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+		ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 	}
 
 	rbd_dev_free(rbd_dev);
···
 		return NULL;
 
 	/* get an id and fill in device name */
-	rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0,
-					 minor_to_rbd_dev_id(1 << MINORBITS),
-					 GFP_KERNEL);
+	rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida,
+					minor_to_rbd_dev_id(1 << MINORBITS) - 1,
+					GFP_KERNEL);
 	if (rbd_dev->dev_id < 0)
 		goto fail_rbd_dev;
 
···
 	return rbd_dev;
 
 fail_dev_id:
-	ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id);
+	ida_free(&rbd_dev_id_ida, rbd_dev->dev_id);
 fail_rbd_dev:
 	rbd_dev_free(rbd_dev);
 	return NULL;

drivers/dpll/dpll_core.c

···
 	WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
 #define ASSERT_DPLL_NOT_REGISTERED(d)	\
 	WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED))
-#define ASSERT_PIN_REGISTERED(p)	\
-	WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED))
 
 struct dpll_device_registration {
 	struct list_head list;
···
 }
 EXPORT_SYMBOL_GPL(dpll_device_unregister);
 
+static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
+{
+	kfree(prop->package_label);
+	kfree(prop->panel_label);
+	kfree(prop->board_label);
+	kfree(prop->freq_supported);
+}
+
+static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
+			     struct dpll_pin_properties *dst)
+{
+	memcpy(dst, src, sizeof(*dst));
+	if (src->freq_supported && src->freq_supported_num) {
+		size_t freq_size = src->freq_supported_num *
+				   sizeof(*src->freq_supported);
+		dst->freq_supported = kmemdup(src->freq_supported,
+					      freq_size, GFP_KERNEL);
+		if (!src->freq_supported)
+			return -ENOMEM;
+	}
+	if (src->board_label) {
+		dst->board_label = kstrdup(src->board_label, GFP_KERNEL);
+		if (!dst->board_label)
+			goto err_board_label;
+	}
+	if (src->panel_label) {
+		dst->panel_label = kstrdup(src->panel_label, GFP_KERNEL);
+		if (!dst->panel_label)
+			goto err_panel_label;
+	}
+	if (src->package_label) {
+		dst->package_label = kstrdup(src->package_label, GFP_KERNEL);
+		if (!dst->package_label)
+			goto err_package_label;
+	}
+
+	return 0;
+
+err_package_label:
+	kfree(dst->panel_label);
+err_panel_label:
+	kfree(dst->board_label);
+err_board_label:
+	kfree(dst->freq_supported);
+	return -ENOMEM;
+}
+
 static struct dpll_pin *
 dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	       const struct dpll_pin_properties *prop)
···
 	if (WARN_ON(prop->type < DPLL_PIN_TYPE_MUX ||
 		    prop->type > DPLL_PIN_TYPE_MAX)) {
 		ret = -EINVAL;
-		goto err;
+		goto err_pin_prop;
 	}
-	pin->prop = prop;
+	ret = dpll_pin_prop_dup(prop, &pin->prop);
+	if (ret)
+		goto err_pin_prop;
 	refcount_set(&pin->refcount, 1);
 	xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
 	if (ret)
-		goto err;
+		goto err_xa_alloc;
 	return pin;
-err:
+err_xa_alloc:
 	xa_destroy(&pin->dpll_refs);
 	xa_destroy(&pin->parent_refs);
+	dpll_pin_prop_free(&pin->prop);
+err_pin_prop:
 	kfree(pin);
 	return ERR_PTR(ret);
 }
···
 		xa_destroy(&pin->dpll_refs);
 		xa_destroy(&pin->parent_refs);
 		xa_erase(&dpll_pin_xa, pin->id);
+		dpll_pin_prop_free(&pin->prop);
 		kfree(pin);
 	}
 	mutex_unlock(&dpll_lock);
···
 	if (WARN_ON(!ops) ||
 	    WARN_ON(!ops->state_on_dpll_get) ||
 	    WARN_ON(!ops->direction_get))
-		return -EINVAL;
-	if (ASSERT_DPLL_REGISTERED(dpll))
 		return -EINVAL;
 
 	mutex_lock(&dpll_lock);
···
 	unsigned long i, stop;
 	int ret;
 
-	if (WARN_ON(parent->prop->type != DPLL_PIN_TYPE_MUX))
+	if (WARN_ON(parent->prop.type != DPLL_PIN_TYPE_MUX))
 		return -EINVAL;
 
 	if (WARN_ON(!ops) ||
 	    WARN_ON(!ops->state_on_pin_get) ||
 	    WARN_ON(!ops->direction_get))
-		return -EINVAL;
-	if (ASSERT_PIN_REGISTERED(parent))
 		return -EINVAL;
 
 	mutex_lock(&dpll_lock);

drivers/dpll/dpll_core.h

···
  * @module:		module of creator
  * @dpll_refs:		hold referencees to dplls pin was registered with
  * @parent_refs:	hold references to parent pins pin was registered with
- * @prop:		pointer to pin properties given by registerer
+ * @prop:		pin properties copied from the registerer
  * @rclk_dev_name:	holds name of device when pin can recover clock from it
  * @refcount:		refcount
  **/
···
 	struct module *module;
 	struct xarray dpll_refs;
 	struct xarray parent_refs;
-	const struct dpll_pin_properties *prop;
+	struct dpll_pin_properties prop;
 	refcount_t refcount;
 };
 

drivers/dpll/dpll_netlink.c

···
 	if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY, sizeof(freq), &freq,
 			  DPLL_A_PIN_PAD))
 		return -EMSGSIZE;
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++) {
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++) {
 		nest = nla_nest_start(msg, DPLL_A_PIN_FREQUENCY_SUPPORTED);
 		if (!nest)
 			return -EMSGSIZE;
-		freq = pin->prop->freq_supported[fs].min;
+		freq = pin->prop.freq_supported[fs].min;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
 			return -EMSGSIZE;
 		}
-		freq = pin->prop->freq_supported[fs].max;
+		freq = pin->prop.freq_supported[fs].max;
 		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, sizeof(freq),
 				  &freq, DPLL_A_PIN_PAD)) {
 			nla_nest_cancel(msg, nest);
···
 {
 	int fs;
 
-	for (fs = 0; fs < pin->prop->freq_supported_num; fs++)
-		if (freq >= pin->prop->freq_supported[fs].min &&
-		    freq <= pin->prop->freq_supported[fs].max)
+	for (fs = 0; fs < pin->prop.freq_supported_num; fs++)
+		if (freq >= pin->prop.freq_supported[fs].min &&
+		    freq <= pin->prop.freq_supported[fs].max)
 			return true;
 	return false;
 }
···
 dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 		     struct netlink_ext_ack *extack)
 {
-	const struct dpll_pin_properties *prop = pin->prop;
+	const struct dpll_pin_properties *prop = &pin->prop;
 	struct dpll_pin_ref *ref;
 	int ret;
 
···
 	return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll);
 }
 
+static bool dpll_pin_available(struct dpll_pin *pin)
+{
+	struct dpll_pin_ref *par_ref;
+	unsigned long i;
+
+	if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
+		return false;
+	xa_for_each(&pin->parent_refs, i, par_ref)
+		if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
+				DPLL_REGISTERED))
+			return true;
+	xa_for_each(&pin->dpll_refs, i, par_ref)
+		if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
+				DPLL_REGISTERED))
+			return true;
+	return false;
+}
+
 /**
  * dpll_device_change_ntf - notify that the dpll device has been changed
  * @dpll: registered dpll pointer
···
 	int ret = -ENOMEM;
 	void *hdr;
 
-	if (WARN_ON(!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)))
+	if (!dpll_pin_available(pin))
 		return -ENODEV;
 
 	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
···
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
···
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "state changing is not allowed");
 		return -EOPNOTSUPP;
 	}
···
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "prio changing is not allowed");
 		return -EOPNOTSUPP;
 	}
···
 	int ret;
 
 	if (!(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE &
-	      pin->prop->capabilities)) {
+	      pin->prop.capabilities)) {
 		NL_SET_ERR_MSG(extack, "direction changing is not allowed");
 		return -EOPNOTSUPP;
 	}
···
 	int ret;
 
 	phase_adj = nla_get_s32(phase_adj_attr);
-	if (phase_adj > pin->prop->phase_range.max ||
-	    phase_adj < pin->prop->phase_range.min) {
+	if (phase_adj > pin->prop.phase_range.max ||
+	    phase_adj < pin->prop.phase_range.min) {
 		NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr,
 				    "phase adjust value not supported");
 		return -EINVAL;
···
 	unsigned long i;
 
 	xa_for_each_marked(&dpll_pin_xa, i, pin, DPLL_REGISTERED) {
-		prop = pin->prop;
+		prop = &pin->prop;
 		cid_match = clock_id ? pin->clock_id == clock_id : true;
 		mod_match = mod_name_attr && module_name(pin->module) ?
 			!nla_strcmp(mod_name_attr,
···
 	}
 	pin = dpll_pin_find_from_nlattr(info);
 	if (!IS_ERR(pin)) {
+		if (!dpll_pin_available(pin)) {
+			nlmsg_free(msg);
+			return -ENODEV;
+		}
 		ret = dpll_msg_add_pin_handle(msg, pin);
 		if (ret) {
 			nlmsg_free(msg);
···
 
 	xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
 				 ctx->idx) {
+		if (!dpll_pin_available(pin))
+			continue;
 		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq,
 				  &dpll_nl_family, NLM_F_MULTI,
···
 	}
 	info->user_ptr[0] = xa_load(&dpll_pin_xa,
 				    nla_get_u32(info->attrs[DPLL_A_PIN_ID]));
-	if (!info->user_ptr[0]) {
+	if (!info->user_ptr[0] ||
+	    !dpll_pin_available(info->user_ptr[0])) {
 		NL_SET_ERR_MSG(info->extack, "pin not found");
 		ret = -ENODEV;
 		goto unlock_dev;

drivers/gpu/drm/ttm/ttm_device.c

···
 		    bool use_dma_alloc, bool use_dma32)
 {
 	struct ttm_global *glob = &ttm_glob;
-	int ret;
+	int ret, nid;
 
 	if (WARN_ON(vma_manager == NULL))
 		return -EINVAL;
···
 
 	ttm_sys_man_init(bdev);
 
-	ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32);
+	if (dev)
+		nid = dev_to_node(dev);
+	else
+		nid = NUMA_NO_NODE;
+
+	ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32);
 
 	bdev->vma_manager = vma_manager;
 	spin_lock_init(&bdev->lru_lock);

drivers/net/ethernet/8390/8390.c

···
 module_init(ns8390_module_init);
 module_exit(ns8390_module_exit);
 #endif /* MODULE */
+MODULE_DESCRIPTION("National Semiconductor 8390 core driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/8390/8390p.c

···
 
 module_init(NS8390p_init_module);
 module_exit(NS8390p_cleanup_module);
+MODULE_DESCRIPTION("National Semiconductor 8390 core for ISA driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/8390/apne.c

···
 	return 1;
 }
 
+MODULE_DESCRIPTION("National Semiconductor 8390 Amiga PCMCIA ethernet driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/8390/hydra.c

···
 module_init(hydra_init_module);
 module_exit(hydra_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro-II Hydra 8390 ethernet driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/8390/stnic.c

···
 
 module_init(stnic_probe);
 module_exit(stnic_cleanup);
+MODULE_DESCRIPTION("National Semiconductor DP83902AV ethernet driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/8390/zorro8390.c

···
 module_init(zorro8390_init_module);
 module_exit(zorro8390_cleanup_module);
 
+MODULE_DESCRIPTION("Zorro NS8390-based ethernet driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/broadcom/bcm4908_enet.c

···
 };
 module_platform_driver(bcm4908_enet_driver);
 
+MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match);

drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c

···
 EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/broadcom/bgmac-bcma.c

···
 module_exit(bgmac_exit)
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/broadcom/bgmac-platform.c

···
 };
 
 module_platform_driver(bgmac_enet_driver);
+MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/broadcom/bgmac.c

···
 EXPORT_SYMBOL_GPL(bgmac_enet_resume);
 
 MODULE_AUTHOR("Rafał Miłecki");
+MODULE_DESCRIPTION("Broadcom iProc GBit driver");
 MODULE_LICENSE("GPL");

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

···
 {
 	bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS);
 	int i, j, rc, ulp_base_vec, ulp_msix;
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
···
 
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		if (!rx_rings)
+			return 0;
+		return bnxt_calc_nr_ring_pages(rx_rings - 1,
+					       BNXT_RSS_TABLE_ENTRIES_P5);
+	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return 2;
 	return 1;
···
 			if (cp < (rx + tx)) {
 				rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false);
 				if (rc)
-					return rc;
+					goto get_rings_exit;
 				if (bp->flags & BNXT_FLAG_AGG_RINGS)
 					rx <<= 1;
 				hw_resc->resv_rx_rings = rx;
···
 		hw_resc->resv_cp_rings = cp;
 		hw_resc->resv_stat_ctxs = stats;
 	}
+get_rings_exit:
 	hwrm_req_drop(bp, req);
-	return 0;
+	return rc;
 }
 
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
···
 
 		req->num_rx_rings = cpu_to_le16(rx_rings);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+			u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 			req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
 			req->num_msix = cpu_to_le16(cp_rings);
-			req->num_rsscos_ctxs =
-				cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+			req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 		} else {
 			req->num_cmpl_rings = cpu_to_le16(cp_rings);
 			req->num_hw_ring_grps = cpu_to_le16(ring_grps);
···
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	req->num_rx_rings = cpu_to_le16(rx_rings);
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
+		u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps);
+
 		req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps);
-		req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64));
+		req->num_rsscos_ctxs = cpu_to_le16(rss_ctx);
 	} else {
 		req->num_cmpl_rings = cpu_to_le16(cp_rings);
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
···
 
 int bnxt_num_tx_to_cp(struct bnxt *bp, int tx)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	if (!tcs)
 		tcs = 1;
···
 
 static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
+	int tcs = bp->num_tc;
 
 	return (tx_cp - bp->tx_nr_rings_xdp) * tcs +
 	       bp->tx_nr_rings_xdp;
···
 	struct net_device *dev = bp->dev;
 	int tcs, i;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	if (tcs) {
 		int i, off, count;
 
···
 {
 	const int len = sizeof(bp->irq_tbl[0].name);
 
-	if (netdev_get_num_tc(bp->dev))
+	if (bp->num_tc) {
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
+	}
 
 	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
 		 0);
···
 
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
-	int tcs = netdev_get_num_tc(bp->dev);
 	bool irq_cleared = false;
+	int tcs = bp->num_tc;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
···
 		    bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
 		netdev_reset_tc(bp->dev);
+		bp->num_tc = 0;
 		if (bp->tx_nr_rings_xdp)
 			bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
 		else
···
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
 		goto half_open_err;
 	}
+	bnxt_init_napi(bp);
 	set_bit(BNXT_STATE_HALF_OPEN, &bp->state);
 	rc = bnxt_init_nic(bp, true);
 	if (rc) {
 		clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
+		bnxt_del_napi(bp);
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
 		goto half_open_err;
 	}
···
 void bnxt_half_close_nic(struct bnxt *bp)
 {
 	bnxt_hwrm_resource_free(bp, false, true);
+	bnxt_del_napi(bp);
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
 	clear_bit(BNXT_STATE_HALF_OPEN, &bp->state);
···
 
 	bp->fw_cap = 0;
 	rc = bnxt_hwrm_ver_get(bp);
+	/* FW may be unresponsive after FLR. FLR must complete within 100 msec
+	 * so wait before continuing with recovery.
+	 */
+	if (rc)
+		msleep(100);
 	bnxt_try_map_fw_health_reg(bp);
 	if (rc) {
 		rc = bnxt_try_recover_fw(bp);
···
 		return -EINVAL;
 	}
 
-	if (netdev_get_num_tc(dev) == tc)
+	if (bp->num_tc == tc)
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
···
 	if (tc) {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc;
 		netdev_set_num_tc(dev, tc);
+		bp->num_tc = tc;
 	} else {
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 		netdev_reset_tc(dev);
+		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);

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

···
 	u8			tc_to_qidx[BNXT_MAX_QUEUE];
 	u8			q_ids[BNXT_MAX_QUEUE];
 	u8			max_q;
+	u8			num_tc;
 
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ

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

···
 		}
 	}
 	if (bp->ieee_ets) {
-		int tc = netdev_get_num_tc(bp->dev);
+		int tc = bp->num_tc;
 
 		if (!tc)
 			tc = 1;

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

···
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 	tx_grps = max(tcs, 1);
 	if (bp->tx_nr_rings_xdp)
 		tx_grps++;
···
 	if (channel->combined_count)
 		sh = true;
 
-	tcs = netdev_get_num_tc(dev);
+	tcs = bp->num_tc;
 
 	req_tx_rings = sh ? channel->combined_count : channel->tx_count;
 	req_rx_rings = sh ? channel->combined_count : channel->rx_count;
···
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5);
+		return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
+		       BNXT_RSS_TABLE_ENTRIES_P5;
 	return HW_HASH_INDEX_SIZE;
 }
 

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

···
 	if (prog)
 		tx_xdp = bp->rx_nr_rings;
 
-	tc = netdev_get_num_tc(dev);
+	tc = bp->num_tc;
 	if (!tc)
 		tc = 1;
 	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,

drivers/net/ethernet/cavium/liquidio/lio_core.c

···
 #include "octeon_network.h"
 
 MODULE_AUTHOR("Cavium Networks, <[e-mail]>");
+MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Core");
 MODULE_LICENSE("GPL");
 
 /* OOM task polling interval */

drivers/net/ethernet/cirrus/ep93xx_eth.c

···
 
 module_platform_driver(ep93xx_eth_driver);
 
+MODULE_DESCRIPTION("Cirrus EP93xx Ethernet driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:ep93xx-eth");

drivers/net/ethernet/engleder/tsnep_main.c

···
 
 			xdp_prepare_buff(&xdp, page_address(entry->page),
 					 XDP_PACKET_HEADROOM + TSNEP_RX_INLINE_METADATA_SIZE,
-					 length, false);
+					 length - ETH_FCS_LEN, false);
 
 			consume = tsnep_xdp_run_prog(rx, prog, &xdp,
 						     &xdp_status, tx_nq, tx);
···
 		prefetch(entry->xdp->data);
 		length = __le32_to_cpu(entry->desc_wb->properties) &
 			 TSNEP_DESC_LENGTH_MASK;
-		xsk_buff_set_size(entry->xdp, length);
+		xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN);
 		xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool);
 
 		/* RX metadata with timestamps is in front of actual data,
···
 
 			allocated--;
 		}
+	}
+
+	/* set need wakeup flag immediately if ring is not filled completely,
+	 * first polling would be too late as need wakeup signalisation would
+	 * be delayed for an indefinite time
+	 */
+	if (xsk_uses_need_wakeup(rx->xsk_pool)) {
+		int desc_available = tsnep_rx_desc_available(rx);
+
+		if (desc_available)
+			xsk_set_rx_need_wakeup(rx->xsk_pool);
+		else
+			xsk_clear_rx_need_wakeup(rx->xsk_pool);
 	}
 }
 

drivers/net/ethernet/ezchip/nps_enet.c

···
 module_platform_driver(nps_enet_driver);
 
 MODULE_AUTHOR("EZchip Semiconductor");
+MODULE_DESCRIPTION("EZchip NPS Ethernet driver");
 MODULE_LICENSE("GPL v2");

drivers/net/ethernet/freescale/enetc/enetc.c

···
 }
 EXPORT_SYMBOL_GPL(enetc_pci_remove);
 
+MODULE_DESCRIPTION("NXP ENETC Ethernet driver");
 MODULE_LICENSE("Dual BSD/GPL");

drivers/net/ethernet/freescale/fec_main.c

···
 
 		/* if any of the above changed restart the FEC */
 		if (status_change) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_restart(ndev);
···
 		}
 	} else {
 		if (fep->link) {
+			netif_stop_queue(ndev);
 			napi_disable(&fep->napi);
 			netif_tx_lock_bh(ndev);
 			fec_stop(ndev);
···
 
 module_platform_driver(fec_driver);
 
+MODULE_DESCRIPTION("NXP Fast Ethernet Controller (FEC) driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/freescale/fsl_pq_mdio.c

···
 
 module_platform_driver(fsl_pq_mdio_driver);
 
+MODULE_DESCRIPTION("Freescale PQ MDIO helpers");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/intel/i40e/i40e_main.c

···
 	struct i40e_hmc_obj_rxq rx_ctx;
 	int err = 0;
 	bool ok;
-	int ret;
 
 	bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
 
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
-	if (ring->vsi->type == I40E_VSI_MAIN)
-		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	ring->rx_buf_len = vsi->rx_buf_len;
+
+	/* XDP RX-queue info only needed for RX rings exposed to XDP */
+	if (ring->vsi->type != I40E_VSI_MAIN)
+		goto skip;
+
+	if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
+	}
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
-		ring->rx_buf_len =
-		  xsk_pool_get_rx_frame_size(ring->xsk_pool);
-		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
+		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
-		if (ret)
-			return ret;
+		if (err)
+			return err;
 		dev_info(&vsi->back->pdev->dev,
 			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
-		ring->rx_buf_len = vsi->rx_buf_len;
-		if (ring->vsi->type == I40E_VSI_MAIN) {
-			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (ret)
-				return ret;
-		}
+		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED,
+						 NULL);
+		if (err)
+			return err;
 	}
 
+skip:
 	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,

drivers/net/ethernet/intel/i40e/i40e_txrx.c

···
 int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int err;
 
 	u64_stats_init(&rx_ring->syncp);
 
···
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_process = 0;
 	rx_ring->next_to_use = 0;
-
-	/* XDP RX-queue info only needed for RX rings exposed to XDP */
-	if (rx_ring->vsi->type == I40E_VSI_MAIN) {
-		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				       rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
-		if (err < 0)
-			return err;
-	}
 
 	rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;
 
···
 static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res,
 				  struct xdp_buff *xdp)
 {
-	u32 next = rx_ring->next_to_clean;
+	u32 nr_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 next = rx_ring->next_to_clean, i = 0;
 	struct i40e_rx_buffer *rx_buffer;
 
 	xdp->flags = 0;
···
 		if (!rx_buffer->page)
 			continue;
 
-		if (xdp_res == I40E_XDP_CONSUMED)
-			rx_buffer->pagecnt_bias++;
-		else
+		if (xdp_res != I40E_XDP_CONSUMED)
 			i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz);
+		else if (i++ <= nr_frags)
+			rx_buffer->pagecnt_bias++;
 
 		/* EOP buffer will be put in i40e_clean_rx_irq() */
 		if (next == rx_ring->next_to_process)
···
  * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function allocates an skb.  It then populates it with the page
  * data from the current receive descriptor, taking care to set up the
  * skb correctly.
  */
 static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
-					  struct xdp_buff *xdp,
-					  u32 nr_frags)
+					  struct xdp_buff *xdp)
 {
 	unsigned int size = xdp->data_end - xdp->data;
 	struct i40e_rx_buffer *rx_buffer;
+	struct skb_shared_info *sinfo;
 	unsigned int headlen;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
 	/* prefetch first cache line of first page */
 	net_prefetch(xdp->data);
···
 	memcpy(__skb_put(skb, headlen), xdp->data,
 	       ALIGN(headlen, sizeof(long)));
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 	/* update all of the pointers */
 	size -= headlen;
···
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo, *skinfo = skb_shinfo(skb);
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
 
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
 		       sizeof(skb_frag_t) * nr_frags);
 
···
  * i40e_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
- * @nr_frags: number of buffers for the packet
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
 static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
-				      struct xdp_buff *xdp,
-				      u32 nr_frags)
+				      struct xdp_buff *xdp)
 {
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo;
 	struct sk_buff *skb;
+	u32 nr_frags;
 
 	/* Prefetch first cache line of first page. If xdp->data_meta
 	 * is unused, this points exactly as xdp->data, otherwise we
···
 	 * data, and then actual data.
 	 */
 	net_prefetch(xdp->data_meta);
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 
 	/* build an skb around the page buffer */
 	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
···
 		skb_metadata_set(skb, metasize);
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *sinfo;
-
-		sinfo = xdp_get_shared_info_from_buff(xdp);
 		xdp_update_skb_shared_info(skb, nr_frags,
 					   sinfo->xdp_frags_size,
 					   nr_frags * xdp->frame_sz,
···
 			total_rx_bytes += size;
 		} else {
 			if (ring_uses_build_skb(rx_ring))
-				skb = i40e_build_skb(rx_ring, xdp, nfrags);
+				skb = i40e_build_skb(rx_ring, xdp);
 			else
-				skb = i40e_construct_skb(rx_ring, xdp, nfrags);
+				skb = i40e_construct_skb(rx_ring, xdp);
 
 			/* drop if we failed to retrieve a buffer */
 			if (!skb) {

drivers/net/ethernet/intel/i40e/i40e_xsk.c

···
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
···
 		xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog);
 		i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets,
 					  &rx_bytes, xdp_res, &failure);
-		first->flags = 0;
 		next_to_clean = next_to_process;
 		if (failure)
 			break;

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

···
 	ring->rx_buf_len = ring->vsi->rx_buf_len;
 
 	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			__xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					   ring->q_index,
-					   ring->q_vector->napi.napi_id,
-					   ring->vsi->rx_buf_len);
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
+		}
 
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_XSK_BUFF_POOL,
 							 NULL);
···
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				__xdp_rxq_info_reg(&ring->xdp_rxq,
-						   ring->netdev,
-						   ring->q_index,
-						   ring->q_vector->napi.napi_id,
-						   ring->vsi->rx_buf_len);
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
+				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+							 ring->q_index,
+							 ring->q_vector->napi.napi_id,
+							 ring->rx_buf_len);
+				if (err)
+					return err;
+			}
 
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 							 MEM_TYPE_PAGE_SHARED,

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

···
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
-	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				     rx_ring->q_index, rx_ring->q_vector->napi.napi_id))
-			goto err;
 	return 0;
 
 err:
···
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	rx_buf->act = ret;
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	ice_set_rx_bufs_act(xdp, rx_ring, ret);
 }
 
 /**
···
 	}
 
 	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		if (unlikely(xdp_buff_has_frags(xdp)))
-			ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
 		return -ENOMEM;
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
+	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
+	 * can pop off frags but driver has to handle it on its own
+	 */
+	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
···
 
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
···
 						    ICE_XDP_CONSUMED);
 			xdp->data = NULL;
 			rx_ring->first_desc = ntc;
+			rx_ring->nr_frags = 0;
 			break;
 		}
 		xdp->data = NULL;
 		rx_ring->first_desc = ntc;
+		rx_ring->nr_frags = 0;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,

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

···
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
+	u32 nr_frags;
 	dma_addr_t dma;			/* physical address of ring */
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */

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

···
  * act: action to store onto Rx buffers related to XDP buffer parts
  *
  * Set action that should be taken before putting Rx buffer from first frag
- * to one before last. Last one is handled by caller of this function as it
- * is the EOP frag that is currently being processed. This function is
- * supposed to be called only when XDP buffer contains frags.
+ * to the last.
  */
 static inline void
 ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
 		    const unsigned int act)
 {
-	const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-	u32 first = rx_ring->first_desc;
-	u32 nr_frags = sinfo->nr_frags;
+	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
 	struct ice_rx_buf *buf;
 
 	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[first];
+		buf = &rx_ring->rx_buf[idx];
 		buf->act = act;
 
-		if (++first == cnt)
-			first = 0;
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	/* adjust pagecnt_bias on frags freed by XDP prog */
+	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
+		u32 delta = rx_ring->nr_frags - sinfo_frags;
+
+		while (delta) {
+			if (idx == 0)
+				idx = cnt - 1;
+			else
+				idx--;
+			buf = &rx_ring->rx_buf[idx];
+			buf->pagecnt_bias--;
+			delta--;
+		}
 	}
 }
 

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

···
 	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
-				   virt_to_page(xdp->data_hard_start), 0, size);
+				   virt_to_page(xdp->data_hard_start),
+				   XDP_PACKET_HEADROOM, size);
 	sinfo->xdp_frags_size += size;
 	xsk_buff_add_frag(xdp);
 
···
 
 		if (!first) {
 			first = xdp;
-			xdp_buff_clear_frags_flag(first);
 		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
 			break;
 		}

drivers/net/ethernet/intel/idpf/idpf_lib.c

···
 	/* setup watchdog timeout value to be 5 second */
 	netdev->watchdog_timeo = 5 * HZ;
 
+	netdev->dev_port = idx;
+
 	/* configure default MTU size */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = vport->max_mtu;

drivers/net/ethernet/litex/litex_liteeth.c

···
 module_platform_driver(liteeth_driver);
 
 MODULE_AUTHOR("Joel Stanley <[e-mail]>");
+MODULE_DESCRIPTION("LiteX Liteeth Ethernet driver");
 MODULE_LICENSE("GPL");

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

···
 	mvpp2_write(priv, MVPP22_BM_POOL_BASE_ADDR_HIGH_REG, val);
 }
 
+/* Cleanup pool before actual initialization in the OS */
+static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id)
+{
+	unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu());
+	u32 val;
+	int i;
+
+	/* Drain the BM from all possible residues left by firmware */
+	for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++)
+		mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id));
+
+	put_cpu();
+
+	/* Stop the BM pool */
+	val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id));
+	val |= MVPP2_BM_STOP_MASK;
+	mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val);
+}
+
 static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv)
 {
 	enum dma_data_direction dma_dir = DMA_FROM_DEVICE;
 	int i, err, poolnum = MVPP2_BM_POOLS_NUM;
 	struct mvpp2_port *port;
+
+	if (priv->percpu_pools)
+		poolnum = mvpp2_get_nrxqs(priv) * 2;
+
+	/* Clean up the pool state in case it contains stale state */
+	for (i = 0; i < poolnum; i++)
+		mvpp2_bm_pool_cleanup(priv, i);
 
 	if (priv->percpu_pools) {
 		for (i = 0; i < priv->port_count; i++) {
···
 			}
 		}
 
-		poolnum = mvpp2_get_nrxqs(priv) * 2;
 		for (i = 0; i < poolnum; i++) {
 			/* the pool in use */
 			int pn = i / (poolnum / 2);

drivers/net/ethernet/marvell/octeontx2/af/mbox.c

···
 EXPORT_SYMBOL(otx2_mbox_id2name);
 
 MODULE_AUTHOR("Marvell.");
+MODULE_DESCRIPTION("Marvell RVU NIC Mbox helpers");
 MODULE_LICENSE("GPL v2");

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

···
 {
 	const char *namep = mlx5_command_str(opcode);
 	struct mlx5_cmd_stats *stats;
+	unsigned long flags;
 
 	if (!err || !(strcmp(namep, "unknown command opcode")))
 		return;
···
 	stats = xa_load(&dev->cmd.stats, opcode);
 	if (!stats)
 		return;
-	spin_lock_irq(&stats->lock);
+	spin_lock_irqsave(&stats->lock, flags);
 	stats->failed++;
 	if (err < 0)
 		stats->last_failed_errno = -err;
···
 		stats->last_failed_mbox_status = status;
 		stats->last_failed_syndrome = syndrome;
 	}
-	spin_unlock_irq(&stats->lock);
+	spin_unlock_irqrestore(&stats->lock, flags);
 }
 
 /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */

drivers/net/ethernet/mellanox/mlx5/core/en.h

···
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);

drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c

···
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}

drivers/net/ethernet/mellanox/mlx5/core/en/params.c

···
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	bool allow_swp;
 
-	allow_swp =
-		mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev);
+	allow_swp = mlx5_geneve_tx_allowed(mdev) ||
+		    (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO);
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

···
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
-	md_buff[*md_buff_sz++] = metadata_id;
+	md_buff[(*md_buff_sz)++] = metadata_id;
 	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
 	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c

···
 	/* iv len */
 	aes_gcm->icv_len = x->aead->alg_icv_len;
 
+	attrs->dir = x->xso.dir;
+
 	/* esn */
 	if (x->props.flags & XFRM_STATE_ESN) {
 		attrs->replay_esn.trigger = true;
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		if (attrs->dir == XFRM_DEV_OFFLOAD_OUT)
+			goto skip_replay_window;
+
 		switch (x->replay_esn->replay_window) {
 		case 32:
 			attrs->replay_esn.replay_window =
···
 		}
 	}
 
-	attrs->dir = x->xso.dir;
+skip_replay_window:
 	/* spi */
 	attrs->spi = be32_to_cpu(x->id.spi);
 
···
 			return -EINVAL;
 		}
 
-		if (x->replay_esn && x->replay_esn->replay_window != 32 &&
+		if (x->replay_esn && x->xso.dir == XFRM_DEV_OFFLOAD_IN &&
+		    x->replay_esn->replay_window != 32 &&
 		    x->replay_esn->replay_window != 64 &&
 		    x->replay_esn->replay_window != 128 &&
 		    x->replay_esn->replay_window != 256) {

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

···
 
 	ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS,
 			sizeof(*ft->g), GFP_KERNEL);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if  (!in || !ft->g) {
-		kfree(ft->g);
-		kvfree(in);
+	if (!ft->g)
 		return -ENOMEM;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free_g;
 	}
 
 	mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria);
···
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	switch (type) {
···
 		break;
 	default:
 		err = -EINVAL;
-		goto out;
+		goto err_free_in;
 	}
 
 	MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
···
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	memset(in, 0, inlen);
···
 	MLX5_SET_CFG(in, end_flow_index, ix - 1);
 	ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in);
 	if (IS_ERR(ft->g[ft->num_groups]))
-		goto err;
+		goto err_clean_group;
 	ft->num_groups++;
 
 	kvfree(in);
 	return 0;
 
-err:
+err_clean_group:
 	err = PTR_ERR(ft->g[ft->num_groups]);
 	ft->g[ft->num_groups] = NULL;
-out:
+err_free_in:
 	kvfree(in);
-
+err_free_g:
+	kfree(ft->g);
+	ft->g = NULL;
 	return err;
 }
 

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

···
 {
 	int tc, i;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++)
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++)
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
 			mlx5e_destroy_tis(mdev, tisn[i][tc]);
 }
···
 	int tc, i;
 	int err;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) {
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
 			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 			void *tisc;
···
 	return err;
 }
 
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 	int err;
···
 		goto err_destroy_mkey;
 	}
 
-	err = mlx5e_create_tises(mdev, res->tisn);
-	if (err) {
-		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-		goto err_destroy_bfreg;
+	if (create_tises) {
+		err = mlx5e_create_tises(mdev, res->tisn);
+		if (err) {
+			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+			goto err_destroy_bfreg;
+		}
+		res->tisn_valid = true;
 	}
+
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
···
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
-	mlx5e_destroy_tises(mdev, res->tisn);
+	if (res->tisn_valid)
+		mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);

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

···
 	if (netif_device_present(netdev))
 		return 0;
 
-	err = mlx5e_create_mdev_resources(mdev);
+	err = mlx5e_create_mdev_resources(mdev, true);
 	if (err)
 		return err;
 

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

···
 
 	err = mlx5e_rss_params_indir_init(&indir, mdev,
 					  mlx5e_rqt_size(mdev, hp->num_channels),
-					  mlx5e_rqt_size(mdev, priv->max_nch));
+					  mlx5e_rqt_size(mdev, hp->num_channels));
 	if (err)
 		return err;
 
···
 	list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) {
 		if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev))
 			continue;
+
+		list_del(&peer_flow->peer_flows);
 		if (refcount_dec_and_test(&peer_flow->refcnt)) {
 			mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow);
-			list_del(&peer_flow->peer_flows);
 			kfree(peer_flow);
 		}
 	}

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c

···
 		i++;
 	}
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 	dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, outer_headers.dmac_47_16);
 	ether_addr_copy(dmac_v, entry->key.addr);
···
 	if (!rule_spec)
 		return ERR_PTR(-ENOMEM);
 
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
 
 	flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
···
 		dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		dest.vport.vhca_id = port->esw_owner_vhca_id;
 	}
+	rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN;
 	handle = mlx5_add_flow_rules(port->mcast.ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);

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

···
 		 fte->flow_context.flow_tag);
 	MLX5_SET(flow_context, in_flow_context, flow_source,
 		 fte->flow_context.flow_source);
+	MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en,
+		 !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN));
 
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);

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

···
 		}
 
 		/* This should only be called once per mdev */
-		err = mlx5e_create_mdev_resources(mdev);
+		err = mlx5e_create_mdev_resources(mdev, false);
 		if (err)
 			goto destroy_ht;
 	}

drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c

···
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	MLX5_SET(cqc,   cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE);
+	MLX5_SET(cqc,   cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 	MLX5_SET(cqc,   cqc, c_eqn_or_apu_element, eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
 	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c

···
 		switch (action_type) {
 		case DR_ACTION_TYP_DROP:
 			attr.final_icm_addr = nic_dmn->drop_icm_addr;
+			attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
 			break;
 		case DR_ACTION_TYP_FT:
 			dest_action = action;
···
 							action->sampler->tx_icm_addr;
 			break;
 		case DR_ACTION_TYP_VPORT:
-			attr.hit_gvmi = action->vport->caps->vhca_gvmi;
-			dest_action = action;
-			attr.final_icm_addr = rx_rule ?
-				action->vport->caps->icm_address_rx :
-				action->vport->caps->icm_address_tx;
+			if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) {
+				/* can't go to uplink on RX rule - dropping instead */
+				attr.final_icm_addr = nic_dmn->drop_icm_addr;
+				attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48;
+			} else {
+				attr.hit_gvmi = action->vport->caps->vhca_gvmi;
+				dest_action = action;
+				attr.final_icm_addr = rx_rule ?
+						      action->vport->caps->icm_address_rx :
+						      action->vport->caps->icm_address_tx;
+			}
 			break;
 		case DR_ACTION_TYP_POP_VLAN:
 			if (!rx_rule && !(dmn->ste_ctx->actions_caps &

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

···
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid);
 
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
+
+	*sd_group = MLX5_GET(query_nic_vport_context_out, out,
+			     nic_vport_context.sd_group);
+out:
+	kvfree(out);
+	return err;
+}
+
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;

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

···
 		dev_err(priv->device, "unable to bring out of ahb reset: %pe\n",
 			ERR_PTR(ret));
 
+	/* Wait a bit for the reset to take effect */
+	udelay(10);
+
 	/* Init MAC and get the capabilities */
 	ret = stmmac_hw_init(priv);
 	if (ret)

drivers/net/fjes/fjes_hw.c

···
 
 	mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid);
 	hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.req_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.req_buf)) {
+		result = -ENOMEM;
+		goto free_ep_info;
+	}
 
 	hw->hw_info.req_buf_size = mem_size;
 
 	mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid);
 	hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL);
-	if (!(hw->hw_info.res_buf))
-		return -ENOMEM;
+	if (!(hw->hw_info.res_buf)) {
+		result = -ENOMEM;
+		goto free_req_buf;
+	}
 
 	hw->hw_info.res_buf_size = mem_size;
 
 	result = fjes_hw_alloc_shared_status_region(hw);
 	if (result)
-		return result;
+		goto free_res_buf;
 
 	hw->hw_info.buffer_share_bit = 0;
 	hw->hw_info.buffer_unshare_reserve_bit = 0;
···
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->tx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			result = fjes_hw_alloc_epbuf(&buf_pair->rx);
 			if (result)
-				return result;
+				goto free_epbuf;
 
 			spin_lock_irqsave(&hw->rx_status_lock, flags);
 			fjes_hw_setup_epbuf(&buf_pair->tx, mac,
···
 	fjes_hw_init_command_registers(hw, &param);
 
 	return 0;
+
+free_epbuf:
+	for (epidx = 0; epidx < hw->max_epid ; epidx++) {
+		if (epidx == hw->my_epid)
+			continue;
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx);
+		fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx);
+	}
+	fjes_hw_free_shared_status_region(hw);
+free_res_buf:
+	kfree(hw->hw_info.res_buf);
+	hw->hw_info.res_buf = NULL;
+free_req_buf:
+	kfree(hw->hw_info.req_buf);
+	hw->hw_info.req_buf = NULL;
+free_ep_info:
+	kfree(hw->ep_shm_info);
+	hw->ep_shm_info = NULL;
+	return result;
 }
 
 static void fjes_hw_cleanup(struct fjes_hw *hw)

drivers/net/hyperv/netvsc_drv.c

···
 
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
-MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
+MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
 unsigned int netvsc_ring_bytes __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
···
 		pr_info("Increased ring_size to %u (min allowed)\n",
 			ring_size);
 	}
-	netvsc_ring_bytes = ring_size * PAGE_SIZE;
+	netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);
 
 	register_netdevice_notifier(&netvsc_netdev_notifier);
 

drivers/net/macsec.c

···
 		return ERR_PTR(-EINVAL);
 	}
 
-	ret = skb_ensure_writable_head_tail(skb, dev);
-	if (unlikely(ret < 0)) {
-		macsec_txsa_put(tx_sa);
-		kfree_skb(skb);
-		return ERR_PTR(ret);
+	if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM ||
+		     skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) {
+		struct sk_buff *nskb = skb_copy_expand(skb,
+						       MACSEC_NEEDED_HEADROOM,
+						       MACSEC_NEEDED_TAILROOM,
+						       GFP_ATOMIC);
+		if (likely(nskb)) {
+			consume_skb(skb);
+			skb = nskb;
+		} else {
+			macsec_txsa_put(tx_sa);
+			kfree_skb(skb);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (!skb) {
+			macsec_txsa_put(tx_sa);
+			return ERR_PTR(-ENOMEM);
+		}
 	}
 
 	unprotected_len = skb->len;

drivers/net/phy/micrel.c

···
  */
 #define LAN8814_1PPM_FORMAT			17179
 
+#define PTP_RX_VERSION				0x0248
+#define PTP_TX_VERSION				0x0288
+#define PTP_MAX_VERSION(x)			(((x) & GENMASK(7, 0)) << 8)
+#define PTP_MIN_VERSION(x)			((x) & GENMASK(7, 0))
+
 #define PTP_RX_MOD				0x024F
 #define PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_ BIT(3)
 #define PTP_RX_TIMESTAMP_EN			0x024D
···
 	lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_L2_ADDR_EN, 0);
 	lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0);
 	lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0);
+
+	/* Disable checking for minorVersionPTP field */
+	lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
+	lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION,
+			      PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));
 
 	skb_queue_head_init(&ptp_priv->tx_queue);
 	skb_queue_head_init(&ptp_priv->rx_queue);

drivers/net/tun.c

···
 	switch (act) {
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(tun->dev, xdp, xdp_prog);
-		if (err)
+		if (err) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_TX:
 		err = tun_xdp_tx(tun->dev, xdp);
-		if (err < 0)
+		if (err < 0) {
+			dev_core_stats_rx_dropped_inc(tun->dev);
 			return err;
+		}
+		dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data);
 		break;
 	case XDP_PASS:
 		break;

drivers/net/wireless/ath/ath11k/core.h

···
 	struct ieee80211_chanctx_conf chanctx;
 	struct ath11k_arp_ns_offload arp_ns_offload;
 	struct ath11k_rekey_data rekey_data;
-
-#ifdef CONFIG_ATH11K_DEBUGFS
-	struct dentry *debugfs_twt;
-#endif /* CONFIG_ATH11K_DEBUGFS */
 };
 
 struct ath11k_vif_iter {

drivers/net/wireless/ath/ath11k/debugfs.c

···
 	.open = simple_open
 };
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif)
 {
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_base *ab = arvif->ar->ab;
+	struct dentry *debugfs_twt;
 
 	if (arvif->vif->type != NL80211_IFTYPE_AP &&
 	    !(arvif->vif->type == NL80211_IFTYPE_STATION &&
 	      test_bit(WMI_TLV_SERVICE_STA_TWT, ab->wmi_ab.svc_map)))
 		return;
 
-	arvif->debugfs_twt = debugfs_create_dir("twt",
-						arvif->vif->debugfs_dir);
-	debugfs_create_file("add_dialog", 0200, arvif->debugfs_twt,
+	debugfs_twt = debugfs_create_dir("twt",
+					 arvif->vif->debugfs_dir);
+	debugfs_create_file("add_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_add_dialog);
 
-	debugfs_create_file("del_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("del_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_del_dialog);
 
-	debugfs_create_file("pause_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("pause_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_pause_dialog);
 
-	debugfs_create_file("resume_dialog", 0200, arvif->debugfs_twt,
+	debugfs_create_file("resume_dialog", 0200, debugfs_twt,
 			    arvif, &ath11k_fops_twt_resume_dialog);
 }
 
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
-	if (!arvif->debugfs_twt)
-		return;
-
-	debugfs_remove_recursive(arvif->debugfs_twt);
-	arvif->debugfs_twt = NULL;
-}

drivers/net/wireless/ath/ath11k/debugfs.h

···
 	return ar->debug.rx_filter;
 }
 
-void ath11k_debugfs_add_interface(struct ath11k_vif *arvif);
-void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif);
+void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif);
 void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				     enum wmi_direct_buffer_module id,
 				     enum ath11k_dbg_dbr_event event,
···
 					      u32 pdev_id, u32 vdev_id, u32 stats_id)
 {
 	return 0;
-}
-
-static inline void ath11k_debugfs_add_interface(struct ath11k_vif *arvif)
-{
-}
-
-static inline void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif)
-{
 }
 
 static inline void

drivers/net/wireless/ath/ath11k/mac.c

···
 		goto err;
 	}
 
-	/* In the case of hardware recovery, debugfs files are
-	 * not deleted since ieee80211_ops.remove_interface() is
-	 * not invoked. In such cases, try to delete the files.
-	 * These will be re-created later.
-	 */
-	ath11k_debugfs_remove_interface(arvif);
-
 	memset(arvif, 0, sizeof(*arvif));
 
 	arvif->ar = ar;
···
 
 	ath11k_dp_vdev_tx_attach(ar, arvif);
 
-	ath11k_debugfs_add_interface(arvif);
-
 	if (vif->type != NL80211_IFTYPE_MONITOR &&
 	    test_bit(ATH11K_FLAG_MONITOR_CONF_ENABLED, &ar->monitor_flags)) {
 		ret = ath11k_mac_monitor_vdev_create(ar);
···
 
 	/* Recalc txpower for remaining vdev */
 	ath11k_mac_txpower_recalc(ar);
-
-	ath11k_debugfs_remove_interface(arvif);
 
 	/* TODO: recal traffic pause state based on the available vdevs */
 
···
 #endif
 
 #ifdef CONFIG_ATH11K_DEBUGFS
+	.vif_add_debugfs		= ath11k_debugfs_op_vif_add,
 	.sta_add_debugfs		= ath11k_debugfs_sta_op_add,
 #endif
 

drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c

···
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 #include <linux/firmware.h>
 #include "iwl-drv.h"
···
 		node_trig = (void *)node_tlv->data;
 	}
 
-	memcpy(node_trig->data + offset, trig->data, trig_data_len);
+	memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len);
 	node_tlv->length = cpu_to_le32(size);
 
 	if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) {

drivers/net/wireless/intersil/p54/fwio.c

···
 			   "FW rev %s - Softmac protocol %x.%x\n",
 			   fw_version, priv->fw_var >> 8, priv->fw_var & 0xff);
 		snprintf(dev->wiphy->fw_version, sizeof(dev->wiphy->fw_version),
-				"%s - %x.%x", fw_version,
+				"%.19s - %x.%x", fw_version,
 				priv->fw_var >> 8, priv->fw_var & 0xff);
 	}
 

drivers/net/xen-netback/netback.c

···
 	}
 
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
-	     shinfo->nr_frags++, gop++, nr_slots--) {
+	     nr_slots--) {
+		if (unlikely(!txp->size)) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&queue->response_lock, flags);
+			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
+			push_tx_responses(queue);
+			spin_unlock_irqrestore(&queue->response_lock, flags);
+			++txp;
+			continue;
+		}
+
 		index = pending_index(queue->pending_cons++);
 		pending_idx = queue->pending_ring[index];
 		xenvif_tx_create_map_op(queue, pending_idx, txp,
 				        txp == first ? extra_count : 0, gop);
 		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
+		++shinfo->nr_frags;
+		++gop;
 
 		if (txp == first)
 			txp = txfrags;
···
 		shinfo = skb_shinfo(nskb);
 		frags = shinfo->frags;
 
-		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
-		     shinfo->nr_frags++, txp++, gop++) {
+		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
+			if (unlikely(!txp->size)) {
+				unsigned long flags;
+
+				spin_lock_irqsave(&queue->response_lock, flags);
+				make_tx_response(queue, txp, 0,
+						 XEN_NETIF_RSP_OKAY);
+				push_tx_responses(queue);
+				spin_unlock_irqrestore(&queue->response_lock,
+						       flags);
+				continue;
+			}
+
 			index = pending_index(queue->pending_cons++);
 			pending_idx = queue->pending_ring[index];
 			xenvif_tx_create_map_op(queue, pending_idx, txp, 0,
 						gop);
 			frag_set_pending_idx(&frags[shinfo->nr_frags],
 					     pending_idx);
+			++shinfo->nr_frags;
+			++gop;
 		}
 
-		skb_shinfo(skb)->frag_list = nskb;
-	} else if (nskb) {
+		if (shinfo->nr_frags) {
+			skb_shinfo(skb)->frag_list = nskb;
+			nskb = NULL;
+		}
+	}
+
+	if (nskb) {
 		/* A frag_list skb was allocated but it is no longer needed
-		 * because enough slots were converted to copy ops above.
+		 * because enough slots were converted to copy ops above or some
+		 * were empty.
 		 */
 		kfree_skb(nskb);
 	}

drivers/video/fbdev/core/fbcon.c

···
 
 	if (logo_lines > vc->vc_bottom) {
 		logo_shown = FBCON_LOGO_CANSHOW;
-		printk(KERN_INFO
-		       "fbcon_init: disable boot-logo (boot-logo bigger than screen).\n");
+		pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n");
 	} else {
 		logo_shown = FBCON_LOGO_DRAW;
 		vc->vc_top = logo_lines;

drivers/video/fbdev/savage/savagefb_driver.c

···
 
 	DBG("savagefb_check_var");
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	var->transp.offset = 0;
 	var->transp.length = 0;
 	switch (var->bits_per_pixel) {

drivers/video/fbdev/sis/sis_main.c

···
 
 	vtotal = var->upper_margin + var->lower_margin + var->vsync_len;
 
+	if (!var->pixclock)
+		return -EINVAL;
 	pixclock = var->pixclock;
 
 	if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) {

drivers/video/fbdev/stifb.c

···
 	    }
 	    break;
 	}
-	stifb_blank(0, (struct fb_info *)fb);	/* 0=enable screen */
+	stifb_blank(0, fb->info);	/* 0=enable screen */
 
 	SETUP_FB(fb);
 }

drivers/video/fbdev/vt8500lcdfb.c

···
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "no IRQ defined\n");
 		ret = -ENODEV;
 		goto failed_free_palette;
 	}

fs/afs/dir.c

···
 		if (xas_retry(&xas, folio))
 			continue;
 		BUG_ON(xa_is_value(folio));
-		ASSERTCMP(folio_file_mapping(folio), ==, mapping);
+		ASSERTCMP(folio->mapping, ==, mapping);
 
 		folio_put(folio);
 	}
···
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio));
 		for (offset = 0; offset < size; offset += sizeof(*block)) {
 			block = kmap_local_folio(folio, offset);
-			pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block);
+			pr_warn("[%02lx] %32phN\n", folio->index + offset, block);
 			kunmap_local(block);
 		}
 	}
···
 		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(folio_file_mapping(folio) != mapping);
+		BUG_ON(folio->mapping != mapping);
 
 		if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) {
 			afs_dir_dump(dvnode, req);
···
 			continue;
 		}
 
+		/* Don't expose silly rename entries to userspace. */
+		if (nlen > 6 &&
+		    dire->u.name[0] == '.' &&
+		    ctx->actor != afs_lookup_filldir &&
+		    ctx->actor != afs_lookup_one_filldir &&
+		    memcmp(dire->u.name, ".__afs", 6) == 0)
+			continue;
+
 		/* found the next entry */
 		if (!dir_emit(ctx, dire->u.name, nlen,
 			      ntohl(dire->u.vnode),
···
 			break;
 		}
 
+		if (vp->scb.status.abort_code)
+			trace_afs_bulkstat_error(op, &vp->fid, i, vp->scb.status.abort_code);
 		if (!vp->scb.have_status && !vp->scb.have_error)
 			continue;
 
···
 		afs_begin_vnode_operation(op);
 		afs_wait_for_operation(op);
 	}
-	inode = ERR_PTR(afs_op_error(op));
 
 out_op:
 	if (!afs_op_error(op)) {
-		inode = &op->file[1].vnode->netfs.inode;
-		op->file[1].vnode = NULL;
+		if (op->file[1].scb.status.abort_code) {
+			afs_op_accumulate_error(op, -ECONNABORTED,
+						op->file[1].scb.status.abort_code);
+		} else {
+			inode = &op->file[1].vnode->netfs.inode;
+			op->file[1].vnode = NULL;
+		}
 	}
 
 	if (op->file[0].scb.have_status)
···
 {
 	struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio));
 
-	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio));
+	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index);
 
 	folio_detach_private(folio);
 

fs/afs/dynroot.c

···
 	.lookup		= afs_dynroot_lookup,
 };
 
-/*
- * Dirs in the dynamic root don't need revalidation.
- */
-static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	return 1;
-}
-
 const struct dentry_operations afs_dynroot_dentry_operations = {
-	.d_revalidate	= afs_dynroot_d_revalidate,
 	.d_delete	= always_delete_dentry,
 	.d_release	= afs_d_release,
 	.d_automount	= afs_d_automount,

fs/afs/proc.c

···
 
 	if (!preflist) {
 		seq_puts(m, "NO PREFS\n");
-		return 0;
+		goto out;
 	}
 
 	seq_printf(m, "PROT SUBNET                                      PRIOR (v=%u n=%u/%u/%u)\n",
···
 		}
 	}
 
-	rcu_read_lock();
+out:
+	rcu_read_unlock();
 	return 0;
 }
 

fs/btrfs/compression.c

···
 }
 
 static int compression_decompress(int type, struct list_head *ws,
-               const u8 *data_in, struct page *dest_page,
-               unsigned long start_byte, size_t srclen, size_t destlen)
+		const u8 *data_in, struct page *dest_page,
+		unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
 	switch (type) {
 	case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_LZO:  return lzo_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
-						start_byte, srclen, destlen);
+						dest_pgoff, srclen, destlen);
 	case BTRFS_COMPRESS_NONE:
 	default:
 		/*
···
  * start_byte tells us the offset into the compressed data we're interested in
  */
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
-		     unsigned long start_byte, size_t srclen, size_t destlen)
+		     unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
 	struct list_head *workspace;
+	const u32 sectorsize = fs_info->sectorsize;
 	int ret;
+
+	/*
+	 * The full destination page range should not exceed the page size.
+	 * And the @destlen should not exceed sectorsize, as this is only called for
+	 * inline file extents, which should not exceed sectorsize.
+	 */
+	ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize);
 
 	workspace = get_workspace(type, 0);
 	ret = compression_decompress(type, workspace, data_in, dest_page,
-				     start_byte, srclen, destlen);
+				     dest_pgoff, srclen, destlen);
 	put_workspace(type, workspace);
 
 	return ret;

fs/btrfs/compression.h

···
 		unsigned long *total_in, unsigned long *total_out);
 int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *zlib_alloc_workspace(unsigned int level);
 void zlib_free_workspace(struct list_head *ws);
···
 		unsigned long *total_in, unsigned long *total_out);
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 struct list_head *lzo_alloc_workspace(unsigned int level);
 void lzo_free_workspace(struct list_head *ws);

fs/btrfs/extent-tree.c

···
 	u64 bytes_left, end;
 	u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT);
 
-	if (WARN_ON(start != aligned_start)) {
+	/* Adjust the range to be aligned to 512B sectors if necessary. */
+	if (start != aligned_start) {
 		len -= aligned_start - start;
 		len = round_down(len, 1 << SECTOR_SHIFT);
 		start = aligned_start;
···
 	return 0;
 }
 
+static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info,
+				    struct find_free_extent_ctl *ffe_ctl)
+{
+	if (ffe_ctl->for_treelog) {
+		spin_lock(&fs_info->treelog_bg_lock);
+		if (fs_info->treelog_bg)
+			ffe_ctl->hint_byte = fs_info->treelog_bg;
+		spin_unlock(&fs_info->treelog_bg_lock);
+	} else if (ffe_ctl->for_data_reloc) {
+		spin_lock(&fs_info->relocation_bg_lock);
+		if (fs_info->data_reloc_bg)
+			ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+		spin_unlock(&fs_info->relocation_bg_lock);
+	} else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) {
+		struct btrfs_block_group *block_group;
+
+		spin_lock(&fs_info->zone_active_bgs_lock);
+		list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
+			/*
+			 * No lock is OK here because avail is monotinically
+			 * decreasing, and this is just a hint.
+			 */
+			u64 avail = block_group->zone_capacity - block_group->alloc_offset;
+
+			if (block_group_bits(block_group, ffe_ctl->flags) &&
+			    avail >= ffe_ctl->num_bytes) {
+				ffe_ctl->hint_byte = block_group->start;
+				break;
+			}
+		}
+		spin_unlock(&fs_info->zone_active_bgs_lock);
+	}
+
+	return 0;
+}
+
 static int prepare_allocation(struct btrfs_fs_info *fs_info,
 			      struct find_free_extent_ctl *ffe_ctl,
 			      struct btrfs_space_info *space_info,
···
 		return prepare_allocation_clustered(fs_info, ffe_ctl,
 						    space_info, ins);
 	case BTRFS_EXTENT_ALLOC_ZONED:
-		if (ffe_ctl->for_treelog) {
-			spin_lock(&fs_info->treelog_bg_lock);
-			if (fs_info->treelog_bg)
-				ffe_ctl->hint_byte = fs_info->treelog_bg;
-			spin_unlock(&fs_info->treelog_bg_lock);
-		}
-		if (ffe_ctl->for_data_reloc) {
-			spin_lock(&fs_info->relocation_bg_lock);
-			if (fs_info->data_reloc_bg)
-				ffe_ctl->hint_byte = fs_info->data_reloc_bg;
-			spin_unlock(&fs_info->relocation_bg_lock);
-		}
-		return 0;
+		return prepare_allocation_zoned(fs_info, ffe_ctl);
 	default:
 		BUG();
 	}

fs/btrfs/inode.c

···
 	u64 root_flags;
 	int ret;
 
+	down_write(&fs_info->subvol_sem);
+
 	/*
 	 * Don't allow to delete a subvolume with send in progress. This is
 	 * inside the inode lock so the error handling that has to drop the bit
···
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu during send",
 			   dest->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	if (atomic_read(&dest->nr_swapfiles)) {
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
 			   root->root_key.objectid);
-		return -EPERM;
+		ret = -EPERM;
+		goto out_up_write;
 	}
 	root_flags = btrfs_root_flags(&dest->root_item);
 	btrfs_set_root_flags(&dest->root_item,
 			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
 	spin_unlock(&dest->root_item_lock);
 
-	down_write(&fs_info->subvol_sem);
-
 	ret = may_destroy_subvol(dest);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
···
 	 */
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
 	if (ret)
-		goto out_up_write;
+		goto out_undead;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
···
 	inode->i_flags |= S_DEAD;
 out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv);
-out_up_write:
-	up_write(&fs_info->subvol_sem);
+out_undead:
 	if (ret) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
 		btrfs_set_root_flags(&dest->root_item,
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
-	} else {
+	}
+out_up_write:
+	up_write(&fs_info->subvol_sem);
+	if (!ret) {
 		d_invalidate(dentry);
 		btrfs_prune_dentries(dest);
 		ASSERT(dest->send_in_progress == 0);

fs/btrfs/ioctl.c

···
 		return -EOPNOTSUPP;
 	}
 
+	if (btrfs_root_refs(&root->root_item) == 0)
+		return -ENOENT;
+
 	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
 		return -EINVAL;
 
···
 		if (argp) {
 			if (copy_from_user(&range, argp, sizeof(range))) {
 				ret = -EFAULT;
+				goto out;
+			}
+			if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) {
+				ret = -EOPNOTSUPP;
 				goto out;
 			}
 			/* compression requires us to start the IO */

fs/btrfs/lzo.c

···
 }
 
 int lzo_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	size_t in_len;
 	size_t out_len;
 	size_t max_segment_len = WORKSPACE_BUF_LENGTH;
 	int ret = 0;
-	char *kaddr;
-	unsigned long bytes;
 
 	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
 		return -EUCLEAN;
···
 	}
 	data_in += LZO_LEN;
 
-	out_len = PAGE_SIZE;
+	out_len = sectorsize;
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		pr_warn("BTRFS: decompress failed!\n");
···
 		goto out;
 	}
 
-	if (out_len < start_byte) {
+	ASSERT(out_len <= sectorsize);
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len);
+	/* Early end, considered as an error. */
+	if (unlikely(out_len < destlen)) {
 		ret = -EIO;
-		goto out;
+		memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len);
 	}
-
-	/*
-	 * the caller is already checking against PAGE_SIZE, but lets
-	 * move this check closer to the memcpy/memset
-	 */
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes = min_t(unsigned long, destlen, out_len - start_byte);
-
-	kaddr = kmap_local_page(dest_page);
-	memcpy(kaddr, workspace->buf + start_byte, bytes);
-
-	/*
-	 * btrfs_getblock is doing a zero on the tail of the page too,
-	 * but this will cover anything missing from the decompressed
-	 * data.
-	 */
-	if (bytes < destlen)
-		memset(kaddr+bytes, 0, destlen-bytes);
-	kunmap_local(kaddr);
 out:
 	return ret;
 }

fs/btrfs/ref-verify.c

···
 out_unlock:
 	spin_unlock(&fs_info->ref_verify_lock);
 out:
-	if (ret)
+	if (ret) {
+		btrfs_free_ref_cache(fs_info);
 		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
+	}
 	return ret;
 }
 
···
 		}
 	}
 	if (ret) {
-		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 		btrfs_free_ref_cache(fs_info);
+		btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY);
 	}
 	btrfs_free_path(path);
 	return ret;

fs/btrfs/scrub.c

···
 static void scrub_read_endio(struct btrfs_bio *bbio)
 {
 	struct scrub_stripe *stripe = bbio->private;
+	struct bio_vec *bvec;
+	int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
+	int num_sectors;
+	u32 bio_size = 0;
+	int i;
+
+	ASSERT(sector_nr < stripe->nr_sectors);
+	bio_for_each_bvec_all(bvec, &bbio->bio, i)
+		bio_size += bvec->bv_len;
+	num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits;
 
 	if (bbio->bio.bi_status) {
-		bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
-		bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
+		bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors);
+		bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors);
 	} else {
-		bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
+		bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors);
 	}
 	bio_put(&bbio->bio);
 	if (atomic_dec_and_test(&stripe->pending_io)) {
···
 {
 	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 	struct btrfs_bio *bbio = NULL;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	u64 stripe_len = BTRFS_STRIPE_LEN;
 	int mirror = stripe->mirror_num;
 	int i;
···
 	for_each_set_bit(i, &stripe->extent_sector_bitmap, stripe->nr_sectors) {
 		struct page *page = scrub_stripe_get_page(stripe, i);
 		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i);
+
+		/* We're beyond the chunk boundary, no need to read anymore. */
+		if (i >= nr_sectors)
+			break;
 
 		/* The current sector cannot be merged, submit the bio. */
 		if (bbio &&
···
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_bio *bbio;
+	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+				      stripe->bg->length - stripe->logical) >>
+				  fs_info->sectorsize_bits;
 	int mirror = stripe->mirror_num;
 
 	ASSERT(stripe->bg);
···
 	bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
 			       scrub_read_endio, stripe);
 
-	/* Read the whole stripe. */
 	bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
-	for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) {
+	/* Read the whole range inside the chunk boundary. */
+	for (unsigned int cur = 0; cur < nr_sectors; cur++) {
+		struct page *page = scrub_stripe_get_page(stripe, cur);
+		unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur);
 		int ret;
 
-		ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0);
+		ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
 		/* We should have allocated enough bio vectors. */
-		ASSERT(ret == PAGE_SIZE);
+		ASSERT(ret == fs_info->sectorsize);
 	}
 	atomic_inc(&stripe->pending_io);
 

fs/btrfs/send.c

···
 		goto out;
 	}
 
-	sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots),
-				     arg->clone_sources_count + 1,
+	sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1,
+				     sizeof(*sctx->clone_roots),
 				     GFP_KERNEL);
 	if (!sctx->clone_roots) {
 		ret = -ENOMEM;

fs/btrfs/subpage.c

···
 
 	spin_lock_irqsave(&subpage->lock, flags);
 	bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
-	folio_start_writeback(folio);
+	if (!folio_test_writeback(folio))
+		folio_start_writeback(folio);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 

fs/btrfs/super.c

···
 
 	btrfs_info_to_ctx(fs_info, &old_ctx);
 
+	/*
+	 * This is our "bind mount" trick, we don't want to allow the user to do
+	 * anything other than mount a different ro/rw and a different subvol,
+	 * all of the mount options should be maintained.
+	 */
+	if (mount_reconfigure)
+		ctx->mount_opt = old_ctx.mount_opt;
+
 	sync_filesystem(sb);
 	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 

fs/btrfs/tree-checker.c

···
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
-				   ptr, inline_type, end);
+				   ptr, btrfs_extent_inline_ref_size(inline_type), end);
 			return -EUCLEAN;
 		}
 

fs/btrfs/volumes.c

···
 	map = btrfs_find_chunk_map(fs_info, logical, length);
 
 	if (unlikely(!map)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
···
 	}
 
 	if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
-		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
 			   logical, logical + length, map->start,

fs/btrfs/zlib.c

···
 }
 
 int zlib_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
 	int wbits = MAX_WBITS;
-	unsigned long bytes_left;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
-
-	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
-	bytes_left = destlen;
+	unsigned long to_copy;
 
 	workspace->strm.next_in = data_in;
 	workspace->strm.avail_in = srclen;
···
 		return -EIO;
 	}
 
-	while (bytes_left > 0) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
+	/*
+	 * Everything (in/out buf) should be at most one sector, there should
+	 * be no need to switch any input/output buffer.
+	 */
+	ret = zlib_inflate(&workspace->strm, Z_FINISH);
+	to_copy = min(workspace->strm.total_out, destlen);
+	if (ret != Z_STREAM_END)
+		goto out;
 
-		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
-		if (ret != Z_OK && ret != Z_STREAM_END)
-			break;
+	memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy);
 
-		buf_start = total_out;
-		total_out = workspace->strm.total_out;
-
-		if (total_out == buf_start) {
-			ret = -EIO;
-			break;
-		}
-
-		if (total_out <= start_byte)
-			goto next;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
-		bytes = min(bytes, bytes_left);
-
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->buf + buf_offset, bytes);
-
-		pg_offset += bytes;
-		bytes_left -= bytes;
-next:
-		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = workspace->buf_size;
-	}
-
-	if (ret != Z_STREAM_END && bytes_left != 0)
+out:
+	if (unlikely(to_copy != destlen)) {
+		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+					to_copy, destlen);
 		ret = -EIO;
-	else
+	} else {
 		ret = 0;
+	}
 
 	zlib_inflateEnd(&workspace->strm);
 
-	/*
-	 * this should only happen if zlib returned fewer bytes than we
-	 * expected.  btrfs_get_block is responsible for zeroing from the
-	 * end of the inline extent (destlen) to the end of the page
-	 */
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
-	}
+	if (unlikely(to_copy < destlen))
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	return ret;
 }
 

fs/btrfs/zoned.c

···
 
 	map = block_group->physical_map;
 
+	spin_lock(&fs_info->zone_active_bgs_lock);
 	spin_lock(&block_group->lock);
 	if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) {
 		ret = true;
···
 		goto out_unlock;
 	}
 
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_zoned_device_info *zinfo;
 		int reserved = 0;
···
 		 */
 		if (atomic_read(&zinfo->active_zones_left) <= reserved) {
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 
 		if (!btrfs_dev_set_active_zone(device, physical)) {
 			/* Cannot activate the zone */
 			ret = false;
-			spin_unlock(&fs_info->zone_active_bgs_lock);
 			goto out_unlock;
 		}
 		if (!is_data)
 			zinfo->reserved_active_zones--;
 	}
-	spin_unlock(&fs_info->zone_active_bgs_lock);
 
 	/* Successfully activated all the zones */
 	set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags);
···
 
 	/* For the active block group list */
 	btrfs_get_block_group(block_group);
-
-	spin_lock(&fs_info->zone_active_bgs_lock);
 	list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
 	spin_unlock(&fs_info->zone_active_bgs_lock);
 
···
 
 out_unlock:
 	spin_unlock(&block_group->lock);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
 	return ret;
 }
 

fs/cachefiles/ondemand.c

···
 	struct fscache_volume *volume = object->volume->vcookie;
 	size_t volume_key_size, cookie_key_size, data_len;
 
+	if (!object->ondemand)
+		return 0;
+
 	/*
 	 * CacheFiles will firstly check the cache file under the root cache
 	 * directory. If the coherency check failed, it will fallback to

fs/exec.c

···
 	struct filename *tmp = getname(library);
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
-		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
+		.open_flag = O_LARGEFILE | O_RDONLY,
 		.acc_mode = MAY_READ | MAY_EXEC,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
···
 
 #endif /* CONFIG_MMU */
 
+/*
+ * On success, caller must call do_close_execat() on the returned
+ * struct file to close it.
+ */
 static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
 	struct file *file;
···
 	return ERR_PTR(err);
 }
 
+/**
+ * open_exec - Open a path name for execution
+ *
+ * @name: path name to open with the intent of executing it.
+ *
+ * Returns ERR_PTR on failure or allocated struct file on success.
+ *
+ * As this is a wrapper for the internal do_open_execat(), callers
+ * must call allow_write_access() before fput() on release. Also see
+ * do_close_execat().
+ */
 struct file *open_exec(const char *name)
 {
 	struct filename *filename = getname_kernel(name);
···
 
 out_unlock:
 	up_write(&me->signal->exec_update_lock);
+	if (!bprm->cred)
+		mutex_unlock(&me->signal->cred_guard_mutex);
+
 out:
 	return retval;
 }
···
 	return -ENOMEM;
 }
 
+/* Matches do_open_execat() */
+static void do_close_execat(struct file *file)
+{
+	if (!file)
+		return;
+	allow_write_access(file);
+	fput(file);
+}
+
 static void free_bprm(struct linux_binprm *bprm)
 {
 	if (bprm->mm) {
···
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
-	if (bprm->file) {
-		allow_write_access(bprm->file);
-		fput(bprm->file);
-	}
+	do_close_execat(bprm->file);
 	if (bprm->executable)
 		fput(bprm->executable);
 	/* If a binfmt changed the interp, free it. */
···
 
 	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
 	if (!bprm) {
-		allow_write_access(file);
-		fput(file);
+		do_close_execat(file);
 		return ERR_PTR(-ENOMEM);
 	}
 
···
 	}
 	rcu_read_unlock();
 
+	/* "users" and "in_exec" locked for copy_fs() */
 	if (p->fs->users > n_fs)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	else
···
 	return 0;
 }
 
-/*
- * sys_execve() executes a new program.
- */
 static int bprm_execve(struct linux_binprm *bprm)
 {
 	int retval;

fs/netfs/buffered_read.c

···
 		}
 
 		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
-			if (folio_index(folio) == rreq->no_unlock_folio &&
+			if (folio->index == rreq->no_unlock_folio &&
 			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
 				_debug("no unlock");
 			else
···
  */
 int netfs_read_folio(struct file *file, struct folio *folio)
 {
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	struct folio *sink = NULL;
 	int ret;
 
-	_enter("%lx", folio_index(folio));
+	_enter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
 				   folio_file_pos(folio), folio_size(folio),
···
 		ret = PTR_ERR(rreq);
 		goto error;
 	}
-	rreq->no_unlock_folio	= folio_index(folio);
+	rreq->no_unlock_folio	= folio->index;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
 	ret = netfs_begin_cache_read(rreq, ctx);
···
 			     size_t offset, size_t len)
 {
 	struct netfs_io_request *rreq;
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	unsigned long long start = folio_pos(folio);
 	size_t flen = folio_size(folio);
···
 		goto error;
 	}
 
-	rreq->no_unlock_folio = folio_index(folio);
+	rreq->no_unlock_folio = folio->index;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 	ret = netfs_begin_cache_read(rreq, ctx);
 	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)

fs/netfs/buffered_write.c

···
 		if (unlikely(fault_in_iov_iter_readable(iter, part) == part))
 			break;
 
-		ret = -ENOMEM;
 		folio = netfs_grab_folio_for_write(mapping, pos, part);
-		if (!folio)
+		if (IS_ERR(folio)) {
+			ret = PTR_ERR(folio);
 			break;
+		}
 
 		flen = folio_size(folio);
 		offset = pos & (flen - 1);
···
 			break;
 		default:
 			WARN(true, "Unexpected modify type %u ix=%lx\n",
-			     howto, folio_index(folio));
+			     howto, folio->index);
 			ret = -EIO;
 			goto error_folio_unlock;
 		}
···
 	xas_for_each(&xas, folio, last) {
 		WARN(!folio_test_writeback(folio),
 		     "bad %zx @%llx page %lx %lx\n",
-		     wreq->len, wreq->start, folio_index(folio), last);
+		     wreq->len, wreq->start, folio->index, last);
 
 		if ((finfo = netfs_folio_info(folio))) {
 			/* Streaming writes cannot be redirtied whilst under
···
 				continue;
 			if (xa_is_value(folio))
 				break;
-			if (folio_index(folio) != index) {
+			if (folio->index != index) {
 				xas_reset(xas);
 				break;
 			}
···
 	long count = wbc->nr_to_write;
 	int ret;
 
-	_enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching);
+	_enter(",%lx,%llx-%llx,%u", folio->index, start, end, caching);
 
 	wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
 				   NETFS_WRITEBACK);
···
 
 	start = folio_pos(folio); /* May regress with THPs */
 
-	_debug("wback %lx", folio_index(folio));
+	_debug("wback %lx", folio->index);
 
 	/* At this point we hold neither the i_pages lock nor the page lock:
 	 * the page may be truncated or invalidated (changing page->mapping to

fs/netfs/fscache_cache.c

···
 void fscache_put_cache(struct fscache_cache *cache,
 		       enum fscache_cache_trace where)
 {
-	unsigned int debug_id = cache->debug_id;
+	unsigned int debug_id;
 	bool zero;
 	int ref;
 
 	if (IS_ERR_OR_NULL(cache))
 		return;
 
+	debug_id = cache->debug_id;
 	zero = __refcount_dec_and_test(&cache->ref, &ref);
 	trace_fscache_cache(debug_id, ref - 1, where);
 

fs/netfs/io.c

···
 			/* We might have multiple writes from the same huge
 			 * folio, but we mustn't unlock a folio more than once.
 			 */
-			if (have_unlocked && folio_index(folio) <= unlocked)
+			if (have_unlocked && folio->index <= unlocked)
 				continue;
 			unlocked = folio_next_index(folio) - 1;
 			trace_netfs_folio(folio, netfs_folio_trace_end_copy);

fs/netfs/misc.c

···
 	struct netfs_folio *finfo = NULL;
 	size_t flen = folio_size(folio);
 
-	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
+	_enter("{%lx},%zx,%zx", folio->index, offset, length);
 
 	folio_wait_fscache(folio);
 

fs/nfsd/nfs4state.c

···
 {
 	struct file_lock *fl;
 	int status = false;
-	struct nfsd_file *nf = find_any_file(fp);
+	struct nfsd_file *nf;
 	struct inode *inode;
 	struct file_lock_context *flctx;
 
+	spin_lock(&fp->fi_lock);
+	nf = find_any_file_locked(fp);
 	if (!nf) {
 		/* Any valid lock stateid should have some sort of access */
 		WARN_ON_ONCE(1);
-		return status;
+		goto out;
 	}
 
 	inode = file_inode(nf->nf_file);
···
 		}
 		spin_unlock(&flctx->flc_lock);
 	}
-	nfsd_file_put(nf);
+out:
+	spin_unlock(&fp->fi_lock);
 	return status;
 }
 
···
  * @cstate: NFSv4 COMPOUND state
  * @u: RELEASE_LOCKOWNER arguments
  *
- * The lockowner's so_count is bumped when a lock record is added
- * or when copying a conflicting lock. The latter case is brief,
- * but can lead to fleeting false positives when looking for
- * locks-in-use.
+ * Check if theree are any locks still held and if not - free the lockowner
+ * and any lock state that is owned.
  *
  * Return values:
  *   %nfs_ok: lockowner released or not found
···
 		spin_unlock(&clp->cl_lock);
 		return nfs_ok;
 	}
-	if (atomic_read(&lo->lo_owner.so_count) != 2) {
-		spin_unlock(&clp->cl_lock);
-		nfs4_put_stateowner(&lo->lo_owner);
-		return nfserr_locks_held;
+
+	list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) {
+		if (check_for_locks(stp->st_stid.sc_file, lo)) {
+			spin_unlock(&clp->cl_lock);
+			nfs4_put_stateowner(&lo->lo_owner);
+			return nfserr_locks_held;
+		}
 	}
 	unhash_lockowner_locked(lo);
 	while (!list_empty(&lo->lo_owner.so_stateids)) {

fs/overlayfs/namei.c

···
 
 struct ovl_lookup_data {
 	struct super_block *sb;
-	struct vfsmount *mnt;
+	const struct ovl_layer *layer;
 	struct qstr name;
 	bool is_dir;
 	bool opaque;
+	bool xwhiteouts;
 	bool stop;
 	bool last;
 	char *redirect;
···
 	return real;
 }
 
-static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path)
-{
-	return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE);
-}
-
 static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d,
 						   const char *name,
 						   struct dentry *base, int len,
 						   bool drop_negative)
 {
-	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len);
+	struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name,
+						 base, len);
 
 	if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
 		if (drop_negative && ret->d_lockref.count == 1) {
···
 			     size_t prelen, const char *post,
 			     struct dentry **ret, bool drop_negative)
 {
+	struct ovl_fs *ofs = OVL_FS(d->sb);
 	struct dentry *this;
 	struct path path;
 	int err;
 	bool last_element = !post[0];
+	bool is_upper = d->layer->idx == 0;
+	char val;
 
 	this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative);
 	if (IS_ERR(this)) {
···
 	}
 
 	path.dentry = this;
-	path.mnt = d->mnt;
-	if (ovl_path_is_whiteout(OVL_FS(d->sb), &path)) {
+	path.mnt = d->layer->mnt;
+	if (ovl_path_is_whiteout(ofs, &path)) {
 		d->stop = d->opaque = true;
 		goto put_and_out;
 	}
···
 			d->stop = true;
 			goto put_and_out;
 		}
-		err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL);
+		err = ovl_check_metacopy_xattr(ofs, &path, NULL);
 		if (err < 0)
 			goto out_err;
 
···
 		if (d->last)
 			goto out;
 
-		if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) {
+		/* overlay.opaque=x means xwhiteouts directory */
+		val = ovl_get_opaquedir_val(ofs, &path);
+		if (last_element && !is_upper && val == 'x') {
+			d->xwhiteouts = true;
+			ovl_layer_set_xwhiteouts(ofs, d->layer);
+		} else if (val == 'y') {
 			d->stop = true;
 			if (last_element)
 				d->opaque = true;
···
  * Returns next layer in stack starting from top.
  * Returns -1 if this is the last layer.
  */
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer)
 {
 	struct ovl_entry *oe = OVL_E(dentry);
 	struct ovl_path *lowerstack = ovl_lowerstack(oe);
···
 	BUG_ON(idx < 0);
 	if (idx == 0) {
 		ovl_path_upper(dentry, path);
-		if (path->dentry)
+		if (path->dentry) {
+			*layer = &OVL_FS(dentry->d_sb)->layers[0];
 			return ovl_numlower(oe) ? 1 : -1;
+		}
 		idx++;
 	}
 	BUG_ON(idx > ovl_numlower(oe));
 	path->dentry = lowerstack[idx - 1].dentry;
-	path->mnt = lowerstack[idx - 1].layer->mnt;
+	*layer = lowerstack[idx - 1].layer;
+	path->mnt = (*layer)->mnt;
 
 	return (idx < ovl_numlower(oe)) ? idx + 1 : -1;
 }
···
 	old_cred = ovl_override_creds(dentry->d_sb);
 	upperdir = ovl_dentry_upper(dentry->d_parent);
 	if (upperdir) {
-		d.mnt = ovl_upper_mnt(ofs);
+		d.layer = &ofs->layers[0];
 		err = ovl_lookup_layer(upperdir, &d, &upperdentry, true);
 		if (err)
 			goto out;
···
 		else if (d.is_dir || !ofs->numdatalayer)
 			d.last = lower.layer->idx == ovl_numlower(roe);
 
-		d.mnt = lower.layer->mnt;
+		d.layer = lower.layer;
 		err = ovl_lookup_layer(lower.dentry, &d, &this, false);
 		if (err)
 			goto out_put;
···
 
 	if (upperopaque)
 		ovl_dentry_set_opaque(dentry);
+	if (d.xwhiteouts)
+		ovl_dentry_set_xwhiteouts(dentry);
 
 	if (upperdentry)
 		ovl_dentry_set_upper_alias(dentry);

fs/overlayfs/overlayfs.h

···
 	OVL_XATTR_METACOPY,
 	OVL_XATTR_PROTATTR,
 	OVL_XATTR_XWHITEOUT,
-	OVL_XATTR_XWHITEOUTS,
 };
 
 enum ovl_inode_flag {
···
 	OVL_E_UPPER_ALIAS,
 	OVL_E_OPAQUE,
 	OVL_E_CONNECTED,
+	/* Lower stack may contain xwhiteout entries */
+	OVL_E_XWHITEOUTS,
 };
 
 enum {
···
 bool ovl_dentry_is_opaque(struct dentry *dentry);
 bool ovl_dentry_is_whiteout(struct dentry *dentry);
 void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry);
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry);
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer);
 bool ovl_dentry_has_upper_alias(struct dentry *dentry);
 void ovl_dentry_set_upper_alias(struct dentry *dentry);
 bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags);
···
 int ovl_copy_up_start(struct dentry *dentry, int flags);
 void ovl_copy_up_end(struct dentry *dentry);
 bool ovl_already_copied_up(struct dentry *dentry, int flags);
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			      enum ovl_xattr ox);
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox);
 bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path);
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path);
 bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath);
 
···
 		.mnt = ovl_upper_mnt(ofs),
 	};
 
-	return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE);
+	return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y';
+}
+
+static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs,
+					 const struct path *path)
+{
+	return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE);
 }
 
 static inline bool ovl_redirect_follow(struct ovl_fs *ofs)
···
 struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh);
 struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 				struct dentry *origin, bool verify);
-int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer);
 int ovl_verify_lowerdata(struct dentry *dentry);
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags);

fs/overlayfs/ovl_entry.h

···
 	int idx;
 	/* One fsid per unique underlying sb (upper fsid == 0) */
 	int fsid;
+	/* xwhiteouts were found on this layer */
+	bool has_xwhiteouts;
 };
 
 struct ovl_path {
···
 	unsigned int numfs;
 	/* Number of data-only lower layers */
 	unsigned int numdatalayer;
-	const struct ovl_layer *layers;
+	struct ovl_layer *layers;
 	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;

fs/overlayfs/readdir.c

···
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	rdd->in_xwhiteouts_dir = rdd->dentry &&
-		ovl_path_check_xwhiteouts_xattr(OVL_FS(rdd->dentry->d_sb), realpath);
 	rdd->first_maybe_whiteout = NULL;
 	rdd->ctx.pos = 0;
 	do {
···
 		.is_lowest = false,
 	};
 	int idx, next;
+	const struct ovl_layer *layer;
 
 	for (idx = 0; idx != -1; idx = next) {
-		next = ovl_path_next(idx, dentry, &realpath);
+		next = ovl_path_next(idx, dentry, &realpath, &layer);
 		rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
+		rdd.in_xwhiteouts_dir = layer->has_xwhiteouts &&
+					ovl_dentry_has_xwhiteouts(dentry);
 
 		if (next != -1) {
 			err = ovl_dir_read(&realpath, &rdd);

fs/overlayfs/super.c

···
 				   struct ovl_entry *oe)
 {
 	struct dentry *root;
+	struct ovl_fs *ofs = OVL_FS(sb);
 	struct ovl_path *lowerpath = ovl_lowerstack(oe);
 	unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
 	int fsid = lowerpath->layer->fsid;
···
 		ovl_dentry_set_upper_alias(root);
 		if (ovl_is_impuredir(sb, upperdentry))
 			ovl_set_flag(OVL_IMPURE, d_inode(root));
+	}
+
+	/* Look for xwhiteouts marker except in the lowermost layer */
+	for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) {
+		struct path path = {
+			.mnt = lowerpath->layer->mnt,
+			.dentry = lowerpath->dentry,
+		};
+
+		/* overlay.opaque=x means xwhiteouts directory */
+		if (ovl_get_opaquedir_val(ofs, &path) == 'x') {
+			ovl_layer_set_xwhiteouts(ofs, lowerpath->layer);
+			ovl_dentry_set_xwhiteouts(root);
+		}
 	}
 
 	/* Root is always merge -> can have whiteouts */

fs/overlayfs/util.c

···
 	ovl_dentry_set_flag(OVL_E_OPAQUE, dentry);
 }
 
+bool ovl_dentry_has_xwhiteouts(struct dentry *dentry)
+{
+	return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry)
+{
+	ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry);
+}
+
+/*
+ * ovl_layer_set_xwhiteouts() is called before adding the overlay dir
+ * dentry to dcache, while readdir of that same directory happens after
+ * the overlay dir dentry is in dcache, so if some cpu observes that
+ * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts
+ * for the layers where xwhiteouts marker was found in that merge dir.
+ */
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer)
+{
+	if (layer->has_xwhiteouts)
+		return;
+
+	/* Write once to read-mostly layer properties */
+	ofs->layers[layer->idx].has_xwhiteouts = true;
+}
+
 /*
  * For hard links and decoded file handles, it's possible for ovl_dentry_upper()
  * to return positive, while there's no actual upper alias for the inode.
···
 	return res >= 0;
 }
 
-bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path)
-{
-	struct dentry *dentry = path->dentry;
-	int res;
-
-	/* xattr.whiteouts must be a directory */
-	if (!d_is_dir(dentry))
-		return false;
-
-	res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUTS, NULL, 0);
-	return res >= 0;
-}
-
 /*
  * Load persistent uuid from xattr into s_uuid if found, or store a new
  * random generated value in s_uuid and in xattr.
···
 	return false;
 }
 
-bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path,
-			       enum ovl_xattr ox)
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox)
 {
 	int res;
 	char val;
 
 	if (!d_is_dir(path->dentry))
-		return false;
+		return 0;
 
 	res = ovl_path_getxattr(ofs, path, ox, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
-
-	return false;
+	return res == 1 ? val : 0;
 }
 
 #define OVL_XATTR_OPAQUE_POSTFIX	"opaque"
···
 #define OVL_XATTR_METACOPY_POSTFIX	"metacopy"
 #define OVL_XATTR_PROTATTR_POSTFIX	"protattr"
 #define OVL_XATTR_XWHITEOUT_POSTFIX	"whiteout"
-#define OVL_XATTR_XWHITEOUTS_POSTFIX	"whiteouts"
 
 #define OVL_XATTR_TAB_ENTRY(x) \
 	[x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \
···
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR),
 	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT),
-	OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUTS),
 };
 
 int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,

fs/smb/client/file.c

···
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
···
 			continue;
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
···
 	xas_for_each(&xas, folio, end) {
 		if (!folio_test_writeback(folio)) {
 			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio_index(folio), end);
+				  len, start, folio->index, end);
 			continue;
 		}
 
···
 				continue;
 			if (xa_is_value(folio))
 				break;
-			if (folio_index(folio) != index)
+			if (folio->index != index)
 				break;
 			if (!folio_try_get_rcu(folio)) {
 				xas_reset(&xas);
···
 					goto skip_write;
 			}
 
-			if (folio_mapping(folio) != mapping ||
+			if (folio->mapping != mapping ||
 			    !folio_test_dirty(folio)) {
 				start += folio_size(folio);
 				folio_unlock(folio);

fs/tracefs/event_inode.c

···
 
 /* Choose something "unique" ;-) */
 #define EVENTFS_FILE_INODE_INO		0x12c4e37
-#define EVENTFS_DIR_INODE_INO		0x134b2f5
+
+/* Just try to make something consistent and unique */
+static int eventfs_dir_ino(struct eventfs_inode *ei)
+{
+	if (!ei->ino)
+		ei->ino = get_next_ino();
+
+	return ei->ino;
+}
 
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
···
 	inode->i_fop = &eventfs_file_operations;
 
 	/* All directories will have the same inode number */
-	inode->i_ino = EVENTFS_DIR_INODE_INO;
+	inode->i_ino = eventfs_dir_ino(ei);
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
···
 
 		name = ei_child->name;
 
-		ino = EVENTFS_DIR_INODE_INO;
+		ino = eventfs_dir_ino(ei_child);
 
 		if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR))
 			goto out_dec;

fs/tracefs/internal.h

···
 	struct eventfs_attr		*entry_attrs;
 	struct eventfs_attr		attr;
 	void				*data;
+	unsigned int			is_freed:1;
+	unsigned int			is_events:1;
+	unsigned int			nr_entries:30;
+	unsigned int			ino;
 	/*
 	 * Union - used for deletion
 	 * @llist:	for calling dput() if needed after RCU
···
 		struct llist_node	llist;
 		struct rcu_head		rcu;
 	};
-	unsigned int			is_freed:1;
-	unsigned int			is_events:1;
-	unsigned int			nr_entries:30;
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)

include/linux/mlx5/driver.h

···
 		struct mlx5_sq_bfreg       bfreg;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
+		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;

include/linux/mlx5/fs.h

···
 
 enum {
 	FLOW_CONTEXT_HAS_TAG = BIT(0),
+	FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1),
 };
 
 struct mlx5_flow_context {

include/linux/mlx5/mlx5_ifc.h

···
 	u8         action[0x10];
 
 	u8         extended_destination[0x1];
-	u8         reserved_at_81[0x1];
+	u8         uplink_hairpin_en[0x1];
 	u8         flow_source[0x2];
 	u8         encrypt_decrypt_type[0x4];
 	u8         destination_list_size[0x18];
···
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xd0];
+	u8	   reserved_at_60[0xa0];
 
+	u8	   reserved_at_100[0x1];
+	u8         sd_group[0x3];
+	u8	   reserved_at_104[0x1c];
+
+	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
···
 	u8         reserved_at_20[0x20];
 
 	u8         local_port[0x8];
-	u8         reserved_at_28[0x15];
-	u8         sd_group[0x3];
+	u8         reserved_at_28[0x18];
 
 	u8         reserved_at_60[0x20];
 };

include/linux/mlx5/vport.h

···
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);

include/linux/sched.h

···
 	unsigned			sched_rt_mutex:1;
 #endif
 
-	/* Bit to tell LSMs we're in execve(): */
+	/* Bit to tell TOMOYO we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;
 #ifndef TIF_RESTORE_SIGMASK

include/linux/skmsg.h

···
 	return !!psock->saved_data_ready;
 }
 
-static inline bool sk_is_udp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_DGRAM &&
-	       sk->sk_protocol == IPPROTO_UDP;
-}
-
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER	(1UL << 1)

include/net/inet_connection_sock.h

···
 	return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops;
 }
 
+static inline void inet_init_csk_locks(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	spin_lock_init(&icsk->icsk_accept_queue.rskq_lock);
+	spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock);
+}
+
 #endif /* _INET_CONNECTION_SOCK_H */

include/net/inet_sock.h

···
 #define inet_assign_bit(nr, sk, val)		\
 	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
 
-static inline bool sk_is_inet(struct sock *sk)
-{
-	return sk->sk_family == AF_INET || sk->sk_family == AF_INET6;
-}
-
 /**
  * sk_to_full_sk - Access to a full socket
  * @sk: pointer to a socket

include/net/llc_pdu.h

···
  */
 static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
+	memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN);
 }
 
 /**
···
  */
 static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da)
 {
-	if (skb->protocol == htons(ETH_P_802_2))
-		memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
+	memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN);
 }
 
 /**

include/net/netfilter/nf_tables.h

···
  *	@nla: netlink attributes
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
+ *	@flags: modifiers to new request
  *	@family: protocol family
  *	@level: depth of the chains
  *	@report: notify via unicast netlink message
···
  *
  *	@key: element key
  *	@key_end: closing element key
+ *	@data: element data
  *	@priv: element private data and extensions
  */
 struct nft_set_elem {
···
  *	@dtype: data type
  *	@dlen: data length
  *	@objtype: object type
- *	@flags: flags
  *	@size: number of set elements
  *	@policy: set policy
  *	@gc_int: garbage collector interval
+ *	@timeout: element timeout
  *	@field_len: length of each field in concatenation, bytes
  *	@field_count: number of concatenated fields in element
  *	@expr: set must support for expressions
···
 /**
  *	enum nft_set_class - performance class
  *
- *	@NFT_LOOKUP_O_1: constant, O(1)
- *	@NFT_LOOKUP_O_LOG_N: logarithmic, O(log N)
- *	@NFT_LOOKUP_O_N: linear, O(N)
+ *	@NFT_SET_CLASS_O_1: constant, O(1)
+ *	@NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N)
+ *	@NFT_SET_CLASS_O_N: linear, O(N)
  */
 enum nft_set_class {
 	NFT_SET_CLASS_O_1,
···
  *	@remove: remove element from set
  *	@walk: iterate over all set elements
  *	@get: get set elements
+ *	@commit: commit set elements
+ *	@abort: abort set elements
  *	@privsize: function to return size of set private data
+ *	@estimate: estimate the required memory size and the lookup complexity class
  *	@init: initialize private data of new set instance
  *	@destroy: destroy private data of set instance
+ *	@gc_init: initialize garbage collection
  *	@elemsize: element private size
  *
  *	Operations lookup, update and delete have simpler interfaces, are faster
···
  *	@policy: set parameterization (see enum nft_set_policies)
  *	@udlen: user data length
  *	@udata: user data
- *	@expr: stateful expression
+ *	@pending_update: list of pending update set element
  * 	@ops: set ops
  * 	@flags: set flags
  *	@dead: set will be freed, never cleared
  *	@genmask: generation mask
  * 	@klen: key length
  * 	@dlen: data length
+ *	@num_exprs: numbers of exprs
+ *	@exprs: stateful expression
+ *	@catchall_list: list of catch-all set element
  * 	@data: private set data
  */
 struct nft_set {
···
  *
  *	@len: length of extension area
  *	@offset: offsets of individual extension types
+ *	@ext_len: length of the expected extension(used to sanity check)
  */
 struct nft_set_ext_tmpl {
 	u16	len;
···
  *	@select_ops: function to select nft_expr_ops
  *	@release_ops: release nft_expr_ops
  *	@ops: default ops, used when no select_ops functions is present
+ *	@inner_ops: inner ops, used for inner packet operation
  *	@list: used internally
  *	@name: Identifier
  *	@owner: module reference
···
  *	struct nft_expr_ops - nf_tables expression operations
  *
  *	@eval: Expression evaluation function
+ *	@clone: Expression clone function
  *	@size: full expression size, including private data size
  *	@init: initialization function
  *	@activate: activate expression in the next generation
  *	@deactivate: deactivate expression in next generation
  *	@destroy: destruction function, called after synchronize_rcu
+ *	@destroy_clone: destruction clone function
  *	@dump: function to dump parameters
- *	@type: expression type
  *	@validate: validate expression, called during loop detection
+ *	@reduce: reduce expression
+ *	@gc: garbage collection expression
+ *	@offload: hardware offload expression
+ *	@offload_action: function to report true/false to allocate one slot or not in the flow
+ *			 offload array
+ *	@offload_stats: function to synchronize hardware stats via updating the counter expression
+ *	@type: expression type
  *	@data: extra data to attach to this expression operation
  */
 struct nft_expr_ops {
···
 /**
  *	struct nft_chain - nf_tables chain
  *
+ *	@blob_gen_0: rule blob pointer to the current generation
+ *	@blob_gen_1: rule blob pointer to the future generation
  *	@rules: list of rules in the chain
  *	@list: used internally
  *	@rhlhead: used internally
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@flags: bitmask of enum nft_chain_flags
+ *	@flags: bitmask of enum NFTA_CHAIN_FLAGS
+ *	@bound: bind or not
+ *	@genmask: generation mask
  *	@name: name of the chain
+ *	@udlen: user data length
+ *	@udata: user data in the chain
+ *	@blob_next: rule blob pointer to the next in the chain
  */
 struct nft_chain {
 	struct nft_rule_blob		__rcu *blob_gen_0;
···
  *	@hook_list: list of netfilter hooks (for NFPROTO_NETDEV family)
  *	@type: chain type
  *	@policy: default policy
+ *	@flags: indicate the base chain disabled or not
  *	@stats: per-cpu chain stats
  *	@chain: the chain
  *	@flow_block: flow block (for hardware offload)
···
  *	struct nft_object - nf_tables stateful object
  *
  *	@list: table stateful object list node
- *	@key:  keys that identify this object
  *	@rhlhead: nft_objname_ht node
+ *	@key: keys that identify this object
  *	@genmask: generation mask
  *	@use: number of references to this stateful object
  *	@handle: unique object handle
+ *	@udlen: length of user data
+ *	@udata: user data
  *	@ops: object operations
  *	@data: object data, layout depends on type
  */
···
  *	@destroy: release existing stateful object
  *	@dump: netlink dump stateful object
  *	@update: update stateful object
+ *	@type: pointer to object type
  */
 struct nft_object_ops {
 	void				(*eval)(struct nft_object *obj,
···
  *	@genmask: generation mask
  *	@use: number of references to this flow table
  * 	@handle: unique object handle
- *	@dev_name: array of device names
+ *	@hook_list: hook list for hooks per net_device in flowtables
  *	@data: rhashtable and garbage collector
- * 	@ops: array of hooks
  */
 struct nft_flowtable {
 	struct list_head		list;

include/net/sch_generic.h

···
 						struct nlattr **tca,
 						struct netlink_ext_ack *extack);
 	void			(*tmplt_destroy)(void *tmplt_priv);
+	void			(*tmplt_reoffload)(struct tcf_chain *chain,
+						   bool add,
+						   flow_setup_cb_t *cb,
+						   void *cb_priv);
 	struct tcf_exts *	(*get_exts)(const struct tcf_proto *tp,
 					    u32 handle);
 

include/net/sock.h

···
 			   &skb_shinfo(skb)->tskey);
 }
 
+static inline bool sk_is_inet(const struct sock *sk)
+{
+	int family = READ_ONCE(sk->sk_family);
+
+	return family == AF_INET || family == AF_INET6;
+}
+
 static inline bool sk_is_tcp(const struct sock *sk)
 {
-	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_STREAM &&
+	       sk->sk_protocol == IPPROTO_TCP;
+}
+
+static inline bool sk_is_udp(const struct sock *sk)
+{
+	return sk_is_inet(sk) &&
+	       sk->sk_type == SOCK_DGRAM &&
+	       sk->sk_protocol == IPPROTO_UDP;
 }
 
 static inline bool sk_is_stream_unix(const struct sock *sk)

include/net/xdp_sock_drv.h

···
 	return ret;
 }
 
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+	struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+
+	list_del(&xskb->xskb_list_node);
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
+{
+	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+	struct xdp_buff_xsk *frag;
+
+	frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+			       xskb_list_node);
+	return &frag->xdp;
+}
+
 static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
 {
 	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
 	xdp->data_meta = xdp->data;
 	xdp->data_end = xdp->data + size;
+	xdp->flags = 0;
 }
 
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
···
 }
 
 static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+	return NULL;
+}
+
+static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
 {
 	return NULL;
 }

include/trace/events/afs.h

···
 		      __print_symbolic(__entry->where, afs_file_errors))
 	    );
 
+TRACE_EVENT(afs_bulkstat_error,
+	    TP_PROTO(struct afs_operation *op, struct afs_fid *fid, unsigned int index, s32 abort),
+
+	    TP_ARGS(op, fid, index, abort),
+
+	    TP_STRUCT__entry(
+		    __field_struct(struct afs_fid,	fid)
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		index)
+		    __field(s32,			abort)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->fid = *fid;
+		    __entry->index = index;
+		    __entry->abort = abort;
+			   ),
+
+	    TP_printk("OP=%08x[%02x] %llx:%llx:%x a=%d",
+		      __entry->op, __entry->index,
+		      __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique,
+		      __entry->abort)
+	    );
+
 TRACE_EVENT(afs_cm_no_server,
 	    TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
 

include/uapi/linux/btrfs.h

···
  */
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
+#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP	(BTRFS_DEFRAG_RANGE_COMPRESS |		\
+					 BTRFS_DEFRAG_RANGE_START_IO)
+
 struct btrfs_ioctl_defrag_range_args {
 	/* start of the defrag operation */
 	__u64 start;

init/Kconfig

···
 	bool
 	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
 
+# Currently, disable -Wstringop-overflow for GCC 11, globally.
+config GCC11_NO_STRINGOP_OVERFLOW
+	def_bool y
+
+config CC_NO_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW
+
+config CC_STRINGOP_OVERFLOW
+	bool
+	default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW
+
 #
 # For architectures that know their GCC __int128 support is sound
 #

kernel/fork.c

···
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
 		spin_lock(&fs->lock);
+		/* "users" and "in_exec" locked for check_unsafe_exec() */
 		if (fs->in_exec) {
 			spin_unlock(&fs->lock);
 			return -EAGAIN;

kernel/rcu/tree.c

···
 	return needmore;
 }
 
+static void swake_up_one_online_ipi(void *arg)
+{
+	struct swait_queue_head *wqh = arg;
+
+	swake_up_one(wqh);
+}
+
+static void swake_up_one_online(struct swait_queue_head *wqh)
+{
+	int cpu = get_cpu();
+
+	/*
+	 * If called from rcutree_report_cpu_starting(), wake up
+	 * is dangerous that late in the CPU-down hotplug process. The
+	 * scheduler might queue an ignored hrtimer. Defer the wake up
+	 * to an online CPU instead.
+	 */
+	if (unlikely(cpu_is_offline(cpu))) {
+		int target;
+
+		target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU),
+					 cpu_online_mask);
+
+		smp_call_function_single(target, swake_up_one_online_ipi,
+					 wqh, 0);
+		put_cpu();
+	} else {
+		put_cpu();
+		swake_up_one(wqh);
+	}
+}
+
 /*
  * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
  * interrupt or softirq handler, in which case we just might immediately
···
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
-	swake_up_one(&rcu_state.gp_wq);
+	swake_up_one_online(&rcu_state.gp_wq);
 }
 
 /*

kernel/rcu/tree_exp.h

···
 	return ret;
 }
 
-
 /*
  * Report the exit from RCU read-side critical section for the last task
  * that queued itself during or before the current expedited preemptible-RCU
···
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up_one(&rcu_state.expedited_wq);
+				swake_up_one_online(&rcu_state.expedited_wq);
 			}
 			break;
 		}

kernel/trace/tracing_map.c

···
 				}
 
 				memcpy(elt->key, key, map->key_size);
-				entry->val = elt;
+				/*
+				 * Ensure the initialization is visible and
+				 * publish the elt.
+				 */
+				smp_wmb();
+				WRITE_ONCE(entry->val, elt);
 				atomic64_inc(&map->hits);
 
 				return entry->val;

net/8021q/vlan_netlink.c

···
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			vlan_dev_set_ingress_priority(dev, m->to, m->from);
 		}
 	}
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
+			if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING)
+				continue;
 			m = nla_data(attr);
 			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
 			if (err)

net/core/dev.c

···
 
 static void __net_exit default_device_exit_net(struct net *net)
 {
+	struct netdev_name_node *name_node, *tmp;
 	struct net_device *dev, *aux;
 	/*
 	 * Push all migratable network devices back to the
···
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
 		if (netdev_name_in_use(&init_net, fb_name))
 			snprintf(fb_name, IFNAMSIZ, "dev%%d");
+
+		netdev_for_each_altname_safe(dev, name_node, tmp)
+			if (netdev_name_in_use(&init_net, name_node->name)) {
+				netdev_name_node_del(name_node);
+				synchronize_rcu();
+				__netdev_name_node_alt_destroy(name_node);
+			}
+
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",

net/core/dev.h

···
 
 #define netdev_for_each_altname(dev, namenode)				\
 	list_for_each_entry((namenode), &(dev)->name_node->list, list)
+#define netdev_for_each_altname_safe(dev, namenode, next)		\
+	list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \
+				 list)
 
 int netdev_name_node_alt_create(struct net_device *dev, const char *name);
 int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);

net/core/filter.c

···
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netkit.h>
 #include <linux/un.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dev.h"
 
···
 	memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
 	skb_frag_size_add(frag, offset);
 	sinfo->xdp_frags_size += offset;
+	if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		xsk_buff_get_tail(xdp)->data_end += offset;
 
 	return 0;
+}
+
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+				   struct xdp_mem_info *mem_info, bool release)
+{
+	struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+	if (release) {
+		xsk_buff_del_tail(zc_frag);
+		__xdp_return(NULL, mem_info, false, zc_frag);
+	} else {
+		zc_frag->data_end -= shrink;
+	}
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+				int shrink)
+{
+	struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+	bool release = skb_frag_size(frag) == shrink;
+
+	if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+		bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+		goto out;
+	}
+
+	if (release) {
+		struct page *page = skb_frag_page(frag);
+
+		__xdp_return(page_address(page), mem_info, false, NULL);
+	}
+
+out:
+	return release;
 }
 
 static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
···
 
 		len_free += shrink;
 		offset -= shrink;
-
-		if (skb_frag_size(frag) == shrink) {
-			struct page *page = skb_frag_page(frag);
-
-			__xdp_return(page_address(page), &xdp->rxq->mem,
-				     false, NULL);
+		if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
 			n_frags_free++;
 		} else {
 			skb_frag_size_sub(frag, shrink);

net/core/request_sock.c

···
 
 void reqsk_queue_alloc(struct request_sock_queue *queue)
 {
-	spin_lock_init(&queue->rskq_lock);
-
-	spin_lock_init(&queue->fastopenq.lock);
 	queue->fastopenq.rskq_rst_head = NULL;
 	queue->fastopenq.rskq_rst_tail = NULL;
 	queue->fastopenq.qlen = 0;

net/core/sock.c

···
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
···
 {
 	struct sock *sk = p;
 
-	return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
-	       sk_busy_loop_timeout(sk, start_time);
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+		return true;
+
+	if (sk_is_udp(sk) &&
+	    !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
+		return true;
+
+	return sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */

net/ipv4/af_inet.c

···
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 

net/ipv4/inet_connection_sock.c

···
 	}
 	if (req)
 		reqsk_put(req);
+
+	if (newsk)
+		inet_init_csk_locks(newsk);
+
 	return newsk;
 out_err:
 	newsk = NULL;

net/ipv4/tcp.c

···
 		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
 			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
+			smp_mb__after_atomic();
 		}
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED.

net/ipv6/af_inet6.c

···
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
+	if (INET_PROTOSW_ICSK & answer_flags)
+		inet_init_csk_locks(sk);
+
 	inet = inet_sk(sk);
 	inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
 

net/llc/af_llc.c

···
  */
 static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
+	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
-	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	int flags = msg->msg_flags;
 	int noblock = flags & MSG_DONTWAIT;
+	int rc = -EINVAL, copied = 0, hdrlen, hh_len;
 	struct sk_buff *skb = NULL;
+	struct net_device *dev;
 	size_t size = 0;
-	int rc = -EINVAL, copied = 0, hdrlen;
 
 	dprintk("%s: sending from %02X to %02X\n", __func__,
 		llc->laddr.lsap, llc->daddr.lsap);
···
 		if (rc)
 			goto out;
 	}
-	hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr);
+	dev = llc->dev;
+	hh_len = LL_RESERVED_SPACE(dev);
+	hdrlen = llc_ui_header_len(sk, addr);
 	size = hdrlen + len;
-	if (size > llc->dev->mtu)
-		size = llc->dev->mtu;
+	size = min_t(size_t, size, READ_ONCE(dev->mtu));
 	copied = size - hdrlen;
 	rc = -EINVAL;
 	if (copied < 0)
 		goto out;
 	release_sock(sk);
-	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
+	skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc);
 	lock_sock(sk);
 	if (!skb)
 		goto out;
-	skb->dev      = llc->dev;
+	if (sock_flag(sk, SOCK_ZAPPED) ||
+	    llc->dev != dev ||
+	    hdrlen != llc_ui_header_len(sk, addr) ||
+	    hh_len != LL_RESERVED_SPACE(dev) ||
+	    size > READ_ONCE(dev->mtu))
+		goto out;
+	skb->dev      = dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
-	skb_reserve(skb, hdrlen);
+	skb_reserve(skb, hh_len + hdrlen);
 	rc = memcpy_from_msg(skb_put(skb, copied), msg, copied);
 	if (rc)
 		goto out;

net/llc/llc_core.c

···
 	.func = llc_rcv,
 };
 
-static struct packet_type llc_tr_packet_type __read_mostly = {
-	.type = cpu_to_be16(ETH_P_TR_802_2),
-	.func = llc_rcv,
-};
-
 static int __init llc_init(void)
 {
 	dev_add_pack(&llc_packet_type);
-	dev_add_pack(&llc_tr_packet_type);
 	return 0;
 }
 
 static void __exit llc_exit(void)
 {
 	dev_remove_pack(&llc_packet_type);
-	dev_remove_pack(&llc_tr_packet_type);
 }
 
 module_init(llc_init);

net/mac80211/Kconfig

···
 	depends on KUNIT
 	depends on MAC80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test mac80211 internals with kunit.
 

net/mac80211/sta_info.c

···
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(sta->link); i++) {
-		if (!(sta->sta.valid_links & BIT(i)))
+		struct link_sta_info *link_sta;
+
+		link_sta = rcu_access_pointer(sta->link[i]);
+		if (!link_sta)
 			continue;
 
 		sta_remove_link(sta, i, false);
···
 
 	if (ieee80211_vif_is_mesh(&sdata->vif))
 		mesh_accept_plinks_update(sdata);
+
+	ieee80211_check_fast_xmit(sta);
 
 	return 0;
  out_remove:

net/mac80211/tx.c

···
 	    sdata->vif.type == NL80211_IFTYPE_STATION)
 		goto out;
 
-	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+	if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded)
 		goto out;
 
 	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||

net/netfilter/nf_tables_api.c

···
 #include <net/sock.h>
 
 #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+#define NFT_SET_MAX_ANONLEN 16
 
 unsigned int nf_tables_net_id __read_mostly;
 
···
 	p = strchr(name, '%');
 	if (p != NULL) {
 		if (p[1] != 'd' || strchr(p + 2, '%'))
+			return -EINVAL;
+
+		if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN)
 			return -EINVAL;
 
 		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
···
 	data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
 
 	switch (data->verdict.code) {
-	default:
-		switch (data->verdict.code & NF_VERDICT_MASK) {
-		case NF_ACCEPT:
-		case NF_DROP:
-		case NF_QUEUE:
-			break;
-		default:
-			return -EINVAL;
-		}
-		fallthrough;
+	case NF_ACCEPT:
+	case NF_DROP:
+	case NF_QUEUE:
+		break;
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
···
 
 		data->verdict.chain = chain;
 		break;
+	default:
+		return -EINVAL;
 	}
 
 	desc->len = sizeof(data->verdict);

net/netfilter/nft_chain_filter.c

···
 				  unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct nft_base_chain *basechain;
 	struct nftables_pernet *nft_net;
-	struct nft_table *table;
 	struct nft_chain *chain, *nr;
+	struct nft_table *table;
 	struct nft_ctx ctx = {
 		.net	= dev_net(dev),
 	};
···
 	nft_net = nft_pernet(ctx.net);
 	mutex_lock(&nft_net->commit_mutex);
 	list_for_each_entry(table, &nft_net->tables, list) {
-		if (table->family != NFPROTO_NETDEV)
+		if (table->family != NFPROTO_NETDEV &&
+		    table->family != NFPROTO_INET)
 			continue;
 
 		ctx.family = table->family;
 		ctx.table = table;
 		list_for_each_entry_safe(chain, nr, &table->chains, list) {
 			if (!nft_is_base_chain(chain))
+				continue;
+
+			basechain = nft_base_chain(chain);
+			if (table->family == NFPROTO_INET &&
+			    basechain->ops.hooknum != NF_INET_INGRESS)
 				continue;
 
 			ctx.chain = chain;

net/netfilter/nft_compat.c

···
 	unsigned int hook_mask = 0;
 	int ret;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
···
 	struct xt_match *match = expr->ops->data;
 	unsigned int hook_mask = 0;
 	int ret;
+
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_BRIDGE &&
+	    ctx->family != NFPROTO_ARP)
+		return -EOPNOTSUPP;
 
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =

net/netfilter/nft_flow_offload.c

···
 {
 	unsigned int hook_mask = (1 << NF_INET_FORWARD);
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, hook_mask);
 }
 

net/netfilter/nft_limit.c

···
 static int nft_limit_init(struct nft_limit_priv *priv,
 			  const struct nlattr * const tb[], bool pkts)
 {
+	u64 unit, tokens, rate_with_burst;
 	bool invert = false;
-	u64 unit, tokens;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
 	    tb[NFTA_LIMIT_UNIT] == NULL)
 		return -EINVAL;
 
 	priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE]));
+	if (priv->rate == 0)
+		return -EINVAL;
+
 	unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT]));
-	priv->nsecs = unit * NSEC_PER_SEC;
-	if (priv->rate == 0 || priv->nsecs < unit)
+	if (check_mul_overflow(unit, NSEC_PER_SEC, &priv->nsecs))
 		return -EOVERFLOW;
 
 	if (tb[NFTA_LIMIT_BURST])
···
 	if (pkts && priv->burst == 0)
 		priv->burst = NFT_LIMIT_PKT_BURST_DEFAULT;
 
-	if (priv->rate + priv->burst < priv->rate)
+	if (check_add_overflow(priv->rate, priv->burst, &rate_with_burst))
 		return -EOVERFLOW;
 
 	if (pkts) {
-		tokens = div64_u64(priv->nsecs, priv->rate) * priv->burst;
+		u64 tmp = div64_u64(priv->nsecs, priv->rate);
+
+		if (check_mul_overflow(tmp, priv->burst, &tokens))
+			return -EOVERFLOW;
 	} else {
+		u64 tmp;
+
 		/* The token bucket size limits the number of tokens can be
 		 * accumulated. tokens_max specifies the bucket size.
 		 * tokens_max = unit * (rate + burst) / rate.
 		 */
-		tokens = div64_u64(priv->nsecs * (priv->rate + priv->burst),
-				 priv->rate);
+		if (check_mul_overflow(priv->nsecs, rate_with_burst, &tmp))
+			return -EOVERFLOW;
+
+		tokens = div64_u64(tmp, priv->rate);
 	}
 
 	if (tb[NFTA_LIMIT_FLAGS]) {

net/netfilter/nft_nat.c

···
 	struct nft_nat *priv = nft_expr_priv(expr);
 	int err;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
 	if (err < 0)
 		return err;

net/netfilter/nft_rt.c

···
 	const struct nft_rt *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->key) {
 	case NFT_RT_NEXTHOP4:
 	case NFT_RT_NEXTHOP6:

net/netfilter/nft_socket.c

···
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_PRE_ROUTING) |
 					(1 << NF_INET_LOCAL_IN) |

net/netfilter/nft_synproxy.c

···
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		err = nf_synproxy_ipv4_init(snet, ctx->net);
 		if (err)
 			goto nf_ct_failure;
···
 		break;
 #endif
 	case NFPROTO_INET:
-	case NFPROTO_BRIDGE:
 		nf_synproxy_ipv4_fini(snet, ctx->net);
 		nf_synproxy_ipv6_fini(snet, ctx->net);
 		break;
···
 				 const struct nft_expr *expr,
 				 const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
 						    (1 << NF_INET_FORWARD));
 }

net/netfilter/nft_tproxy.c

···
 			       const struct nft_expr *expr,
 			       const struct nft_data **data)
 {
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
 }
 

net/netfilter/nft_xfrm.c

···
 	const struct nft_xfrm *priv = nft_expr_priv(expr);
 	unsigned int hooks;
 
+	if (ctx->family != NFPROTO_IPV4 &&
+	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET)
+		return -EOPNOTSUPP;
+
 	switch (priv->dir) {
 	case XFRM_POLICY_IN:
 		hooks = (1 << NF_INET_FORWARD) |

net/netlink/af_netlink.c

···
 	if (is_vmalloc_addr(skb->head)) {
 		if (!skb->cloned ||
 		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
-			vfree(skb->head);
+			vfree_atomic(skb->head);
 
 		skb->head = NULL;
 	}

net/rds/af_rds.c

···
 
 	rs->rs_rx_traces = trace.rx_traces;
 	for (i = 0; i < rs->rs_rx_traces; i++) {
-		if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) {
+		if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) {
 			rs->rs_rx_traces = 0;
 			return -EFAULT;
 		}

net/sched/cls_api.c

···
 	     chain_prev = chain,
 		     chain = __tcf_get_next_chain(block, chain),
 		     tcf_chain_put(chain_prev)) {
+		if (chain->tmplt_ops && add)
+			chain->tmplt_ops->tmplt_reoffload(chain, true, cb,
+							  cb_priv);
 		for (tp = __tcf_get_next_proto(chain, NULL); tp;
 		     tp_prev = tp,
 			     tp = __tcf_get_next_proto(chain, tp),
···
 				goto err_playback_remove;
 			}
 		}
+		if (chain->tmplt_ops && !add)
+			chain->tmplt_ops->tmplt_reoffload(chain, false, cb,
+							  cb_priv);
 	}
 
 	return 0;
···
 	ops = tcf_proto_lookup_ops(name, true, extack);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
-	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
+	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump ||
+	    !ops->tmplt_reoffload) {
 		NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
 		module_put(ops->owner);
 		return -EOPNOTSUPP;

net/sched/cls_flower.c

···
 	kfree(tmplt);
 }
 
+static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add,
+			       flow_setup_cb_t *cb, void *cb_priv)
+{
+	struct fl_flow_tmplt *tmplt = chain->tmplt_priv;
+	struct flow_cls_offload cls_flower = {};
+
+	cls_flower.rule = flow_rule_alloc(0);
+	if (!cls_flower.rule)
+		return;
+
+	cls_flower.common.chain_index = chain->index;
+	cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE :
+				   FLOW_CLS_TMPLT_DESTROY;
+	cls_flower.cookie = (unsigned long) tmplt;
+	cls_flower.rule->match.dissector = &tmplt->dissector;
+	cls_flower.rule->match.mask = &tmplt->mask;
+	cls_flower.rule->match.key = &tmplt->dummy_key;
+
+	cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+	kfree(cls_flower.rule);
+}
+
 static int fl_dump_key_val(struct sk_buff *skb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
···
 	.bind_class	= fl_bind_class,
 	.tmplt_create	= fl_tmplt_create,
 	.tmplt_destroy	= fl_tmplt_destroy,
+	.tmplt_reoffload = fl_tmplt_reoffload,
 	.tmplt_dump	= fl_tmplt_dump,
 	.get_exts	= fl_get_exts,
 	.owner		= THIS_MODULE,

net/smc/smc_diag.c

···
 	}
 	if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd &&
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
-	    !list_empty(&smc->conn.lgr->list)) {
+	    !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) {
 		struct smc_connection *conn = &smc->conn;
 		struct smcd_diag_dmbinfo dinfo;
 		struct smcd_dev *smcd = conn->lgr->smcd;

net/sunrpc/svcsock.c

···
 				ARRAY_SIZE(rqstp->rq_bvec), xdr);
 
 	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-		      count, 0);
+		      count, rqstp->rq_res.len);
 	err = sock_sendmsg(svsk->sk_sock, &msg);
 	if (err == -ECONNREFUSED) {
 		/* ICMP error on earlier request. */
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
-			      count, 0);
+			      count, rqstp->rq_res.len);
 		err = sock_sendmsg(svsk->sk_sock, &msg);
 	}
 

net/wireless/Kconfig

···
 	depends on KUNIT
 	depends on CFG80211
 	default KUNIT_ALL_TESTS
-	depends on !KERNEL_6_2
 	help
 	  Enable this option to test cfg80211 functions with kunit.
 

net/wireless/nl80211.c

···
 		}
 		wiphy_unlock(&rdev->wiphy);
 
+		if_start = 0;
 		wp_idx++;
 	}
  out:

net/xdp/xsk.c

···
 		contd = XDP_PKT_CONTD;
 
 	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err || likely(!frags))
-		goto out;
+	if (err)
+		goto err;
+	if (likely(!frags))
+		return 0;
 
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
···
 		len = pos->xdp.data_end - pos->xdp.data;
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
-			return err;
+			goto err;
 		list_del(&pos->xskb_list_node);
 	}
 
-out:
+	return 0;
+err:
+	xsk_buff_free(xdp);
 	return err;
 }
 

net/xdp/xsk_buff_pool.c

···
 
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
+	xskb->xdp.flags = 0;
 
 	if (pool->dma_need_sync) {
 		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,

samples/cgroup/.gitignore

···
+/cgroup_event_listener
+/memcg_event_listener
+

scripts/Makefile.extrawarn

···
 KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation)
-KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow)
 KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation)
 
 KBUILD_CPPFLAGS += -Wundef
···
 KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
-KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
 ifdef CONFIG_CC_IS_CLANG

security/apparmor/lsm.c

···
 	 * Cache permissions granted by the previous exec check, with
 	 * implicit read and executable mmap which are required to
 	 * actually execute the image.
+	 *
+	 * Illogically, FMODE_EXEC is in f_flags, not f_mode.
 	 */
-	if (current->in_execve) {
+	if (file->f_flags & __FMODE_EXEC) {
 		fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
 		return 0;
 	}

security/keys/encrypted-keys/encrypted.c

···
 			break;
 		}
 		*decrypted_data = strsep(&datablob, " \t");
-		if (!*decrypted_data) {
-			pr_info("encrypted_key: decrypted_data is missing\n");
-			break;
-		}
 		ret = 0;
 		break;
 	case Opt_load:

security/tomoyo/tomoyo.c

···
 static int tomoyo_file_open(struct file *f)
 {
 	/* Don't check read permission here if called from execve(). */
-	if (current->in_execve)
+	/* Illogically, FMODE_EXEC is in f_flags, not f_mode. */
+	if (f->f_flags & __FMODE_EXEC)
 		return 0;
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
 					    f->f_flags);

tools/arch/x86/include/asm/cpufeatures.h

···
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
···
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
···
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */

tools/arch/x86/include/asm/msr-index.h

···
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
···
 /* Auto-reload via MSR instead of DS area */
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
+
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
 
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more

tools/arch/x86/include/uapi/asm/kvm.h

···
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */

tools/arch/x86/lib/memcpy_64.S

···
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright 2002 Andi Kleen */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
···
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)

tools/arch/x86/lib/memset_64.S

···
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
···
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)

tools/include/asm-generic/unaligned.h

···
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
···
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
···
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)

tools/include/uapi/asm-generic/unistd.h

···
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 462
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/drm.h

···
 /**
  * DRM_CAP_ASYNC_PAGE_FLIP
  *
- * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
  */
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
 /**
···
  * :ref:`drm_sync_objects`.
  */
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
 
 /* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
···
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
 /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
···
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
···
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 struct drm_syncobj_timeline_wait {
···
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 /**
···
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
 #define DRM_IOCTL_SYNCOBJ_EVENTFD	DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
+
+/**
+ * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer.
+ *
+ * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable
+ * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept
+ * alive. When the plane no longer uses the framebuffer (because the
+ * framebuffer is replaced with another one, or the plane is disabled), the
+ * framebuffer is cleaned up.
+ *
+ * This is useful to implement flicker-free transitions between two processes.
+ *
+ * Depending on the threat model, user-space may want to ensure that the
+ * framebuffer doesn't expose any sensitive user information: closed
+ * framebuffers attached to a plane can be read back by the next DRM master.
+ */
+#define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
 
 /*
  * Device specific ioctls should only be in their respective headers

tools/include/uapi/drm/i915_drm.h

···
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
- * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
  * EXEC_OBJECT_CAPTURE.
  */
 #define I915_PARAM_HAS_EXEC_CAPTURE	 45
···
 	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engine classess on which the object is being read, and the
+	 * the engine classes on which the object is being read, and the
 	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
···
 	__u32 handle;
 
 	/* Advice: either the buffer will be needed again in the near future,
-	 *         or wont be and could be discarded under memory pressure.
+	 *         or won't be and could be discarded under memory pressure.
 	 */
 	__u32 madv;
 
···
  * 	// enough to hold our array of engines. The kernel will fill out the
  * 	// item.length for us, which is the number of bytes we need.
  * 	//
- * 	// Alternatively a large buffer can be allocated straight away enabling
+ *	// Alternatively a large buffer can be allocated straightaway enabling
  * 	// querying in one pass, in which case item.length should contain the
  * 	// length of the provided buffer.
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
···
  * 	// Now that we allocated the required number of bytes, we call the ioctl
  * 	// again, this time with the data_ptr pointing to our newly allocated
  * 	// blob, which the kernel can then populate with info on all engines.
- * 	item.data_ptr = (uintptr_t)&info,
+ *	item.data_ptr = (uintptr_t)&info;
  *
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
  * 	if (err) ...
···
 /**
  * struct drm_i915_engine_info
  *
- * Describes one engine and it's capabilities as known to the driver.
+ * Describes one engine and its capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
 	/** @engine: Engine class and instance. */

tools/include/uapi/linux/fcntl.h

···
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */

tools/include/uapi/linux/kvm.h

···
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
···
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
···
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
···
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
···
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
···
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
···
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
···
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
···
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
···
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
···
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
···
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
···
 
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
 
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/mount.h

···
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */

tools/include/uapi/linux/stat.h

···
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 

tools/perf/Documentation/perf-list.txt

···
 --json::
 Output in JSON format.
 
+-o::
+--output=::
+	Output file name. By default output is written to stdout.
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------

tools/perf/Makefile.perf

···
   SHELLCHECK := $(shell which shellcheck 2> /dev/null)
 endif
 
+# shellcheck is using in tools/perf/tests/Build with option -a/--check-sourced (
+# introduced in v0.4.7) and -S/--severity (introduced in v0.6.0). So make the
+# minimal shellcheck version as v0.6.0.
+ifneq ($(SHELLCHECK),)
+  ifeq ($(shell expr $(shell $(SHELLCHECK) --version | grep version: | \
+        sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 060), 1)
+    SHELLCHECK :=
+  endif
+endif
+
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
 export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK
 

tools/perf/builtin-list.c

···
  * functions.
  */
 struct print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/**
 	 * @pmu_glob: Optionally restrict PMU and metric matching to PMU or
 	 * debugfs subsystem name.
···
 {
 	struct print_state *print_state = ps;
 
-	if (!print_state->name_only && pager_in_use())
-		printf("\nList of pre-defined events (to be used in -e or -M):\n\n");
+	if (!print_state->name_only && pager_in_use()) {
+		fprintf(print_state->fp,
+			"\nList of pre-defined events (to be used in -e or -M):\n\n");
+	}
 }
 
 static void default_print_end(void *print_state __maybe_unused) {}
 
-static void wordwrap(const char *s, int start, int max, int corr)
+static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 {
 	int column = start;
 	int n;
···
 		int wlen = strcspn(s, " \t\n");
 
 		if ((column + wlen >= max && column > start) || saw_newline) {
-			printf("\n%*s", start, "");
+			fprintf(fp, "\n%*s", start, "");
 			column = start + corr;
 		}
-		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s);
 		if (n <= 0)
 			break;
 		saw_newline = s[wlen] == '\n';
···
 {
 	struct print_state *print_state = ps;
 	int pos;
+	FILE *fp = print_state->fp;
 
 	if (deprecated && !print_state->deprecated)
 		return;
···
 
 	if (print_state->name_only) {
 		if (event_alias && strlen(event_alias))
-			printf("%s ", event_alias);
+			fprintf(fp, "%s ", event_alias);
 		else
-			printf("%s ", event_name);
+			fprintf(fp, "%s ", event_name);
 		return;
 	}
 
 	if (strcmp(print_state->last_topic, topic ?: "")) {
 		if (topic)
-			printf("\n%s:\n", topic);
+			fprintf(fp, "\n%s:\n", topic);
 		zfree(&print_state->last_topic);
 		print_state->last_topic = strdup(topic ?: "");
 	}
 
 	if (event_alias && strlen(event_alias))
-		pos = printf("  %s OR %s", event_name, event_alias);
+		pos = fprintf(fp, "  %s OR %s", event_name, event_alias);
 	else
-		pos = printf("  %s", event_name);
+		pos = fprintf(fp, "  %s", event_name);
 
 	if (!topic && event_type_desc) {
 		for (; pos < 53; pos++)
-			putchar(' ');
-		printf("[%s]\n", event_type_desc);
+			fputc(' ', fp);
+		fprintf(fp, "[%s]\n", event_type_desc);
 	} else
-		putchar('\n');
+		fputc('\n', fp);
 
 	if (desc && print_state->desc) {
 		char *desc_with_unit = NULL;
···
 					      ? "%s. Unit: %s" : "%s Unit: %s",
 					    desc, pmu_name);
 		}
-		printf("%*s", 8, "[");
-		wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 		free(desc_with_unit);
 	}
 	long_desc = long_desc ?: desc;
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 
 	if (print_state->detailed && encoding_desc) {
-		printf("%*s", 8, "");
-		wordwrap(encoding_desc, 8, pager_get_columns(), 0);
-		putchar('\n');
+		fprintf(fp, "%*s", 8, "");
+		wordwrap(fp, encoding_desc, 8, pager_get_columns(), 0);
+		fputc('\n', fp);
 	}
 }
 
···
 				const char *unit __maybe_unused)
 {
 	struct print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
 	if (print_state->event_glob &&
 	    (!print_state->metrics || !name || !strglobmatch(name, print_state->event_glob)) &&
···
 
 	if (!print_state->name_only && !print_state->last_metricgroups) {
 		if (print_state->metricgroups) {
-			printf("\nMetric Groups:\n");
+			fprintf(fp, "\nMetric Groups:\n");
 			if (!print_state->metrics)
-				putchar('\n');
+				fputc('\n', fp);
 		} else {
-			printf("\nMetrics:\n\n");
+			fprintf(fp, "\nMetrics:\n\n");
 		}
 	}
 	if (!print_state->last_metricgroups ||
 	    strcmp(print_state->last_metricgroups, group ?: "")) {
 		if (group && print_state->metricgroups) {
 			if (print_state->name_only)
-				printf("%s ", group);
+				fprintf(fp, "%s ", group);
 			else if (print_state->metrics) {
 				const char *gdesc = describe_metricgroup(group);
 
 				if (gdesc)
-					printf("\n%s: [%s]\n", group, gdesc);
+					fprintf(fp, "\n%s: [%s]\n", group, gdesc);
 				else
-					printf("\n%s:\n", group);
+					fprintf(fp, "\n%s:\n", group);
 			} else
-				printf("%s\n", group);
+				fprintf(fp, "%s\n", group);
 		}
 		zfree(&print_state->last_metricgroups);
 		print_state->last_metricgroups = strdup(group ?: "");
···
 	if (print_state->name_only) {
 		if (print_state->metrics &&
 		    !strlist__has_entry(print_state->visited_metrics, name)) {
-			printf("%s ", name);
+			fprintf(fp, "%s ", name);
 			strlist__add(print_state->visited_metrics, name);
 		}
 		return;
 	}
-	printf("  %s\n", name);
+	fprintf(fp, "  %s\n", name);
 
 	if (desc && print_state->desc) {
-		printf("%*s", 8, "[");
-		wordwrap(desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (expr && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(expr, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, expr, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (threshold && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(threshold, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, threshold, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 }
 
 struct json_print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/** Should a separator be printed prior to the next item? */
 	bool need_sep;
 };
 
-static void json_print_start(void *print_state __maybe_unused)
+static void json_print_start(void *ps)
 {
-	printf("[\n");
+	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
+
+	fprintf(fp, "[\n");
 }
 
 static void json_print_end(void *ps)
 {
 	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
-	printf("%s]\n", print_state->need_sep ? "\n" : "");
+	fprintf(fp, "%s]\n", print_state->need_sep ? "\n" : "");
 }
 
-static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
+static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ...)
 {
 	va_list args;
 
···
 		}
 	}
 	va_end(args);
-	fputs(buf->buf, stdout);
+	fputs(buf->buf, fp);
 }
 
 static void json_print_event(void *ps, const char *pmu_name, const char *topic,
···
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (pmu_name) {
-		fix_escape_printf(&buf, "\t\"Unit\": \"%S\"", pmu_name);
+		fix_escape_fprintf(fp, &buf, "\t\"Unit\": \"%S\"", pmu_name);
 		need_sep = true;
 	}
 	if (topic) {
-		fix_escape_printf(&buf, "%s\t\"Topic\": \"%S\"", need_sep ? ",\n" : "", topic);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Topic\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   topic);
 		need_sep = true;
 	}
 	if (event_name) {
-		fix_escape_printf(&buf, "%s\t\"EventName\": \"%S\"", need_sep ? ",\n" : "",
-				  event_name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_name);
 		need_sep = true;
 	}
 	if (event_alias && strlen(event_alias)) {
-		fix_escape_printf(&buf, "%s\t\"EventAlias\": \"%S\"", need_sep ? ",\n" : "",
-				  event_alias);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventAlias\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_alias);
 		need_sep = true;
 	}
 	if (scale_unit && strlen(scale_unit)) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "",
-				  scale_unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   scale_unit);
 		need_sep = true;
 	}
 	if (event_type_desc) {
-		fix_escape_printf(&buf, "%s\t\"EventType\": \"%S\"", need_sep ? ",\n" : "",
-				  event_type_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventType\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_type_desc);
 		need_sep = true;
 	}
 	if (deprecated) {
-		fix_escape_printf(&buf, "%s\t\"Deprecated\": \"%S\"", need_sep ? ",\n" : "",
-				  deprecated ? "1" : "0");
+		fix_escape_fprintf(fp, &buf, "%s\t\"Deprecated\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   deprecated ? "1" : "0");
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
 	if (encoding_desc) {
-		fix_escape_printf(&buf, "%s\t\"Encoding\": \"%S\"", need_sep ? ",\n" : "",
-				  encoding_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Encoding\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   encoding_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
···
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (group) {
-		fix_escape_printf(&buf, "\t\"MetricGroup\": \"%S\"", group);
+		fix_escape_fprintf(fp, &buf, "\t\"MetricGroup\": \"%S\"", group);
 		need_sep = true;
 	}
 	if (name) {
-		fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   name);
 		need_sep = true;
 	}
 	if (expr) {
-		fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricExpr\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   expr);
 		need_sep = true;
 	}
 	if (threshold) {
-		fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "",
-				  threshold);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricThreshold\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   threshold);
 		need_sep = true;
 	}
 	if (unit) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   unit);
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
···
 int cmd_list(int argc, const char **argv)
 {
 	int i, ret = 0;
-	struct print_state default_ps = {};
-	struct print_state json_ps = {};
+	struct print_state default_ps = {
+		.fp = stdout,
+	};
+	struct print_state json_ps = {
+		.fp = stdout,
+	};
 	void *ps = &default_ps;
 	struct print_callbacks print_cb = {
 		.print_start = default_print_start,
···
 	};
 	const char *cputype = NULL;
 	const char *unit_name = NULL;
+	const char *output_path = NULL;
 	bool json = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &default_ps.name_only, "Dump raw events"),
···
 			    "Print longer event descriptions."),
 		OPT_BOOLEAN(0, "details", &default_ps.detailed,
 			    "Print information on the perf event names and expressions used internally by events."),
+		OPT_STRING('o', "output", &output_path, "file", "output file name"),
 		OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated,
 			    "Print deprecated events."),
 		OPT_STRING(0, "cputype", &cputype, "cpu type",
···
 
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (output_path) {
+		default_ps.fp = fopen(output_path, "w");
+		json_ps.fp = default_ps.fp;
+	}
 
 	setup_pager();
 
···
 	free(default_ps.last_topic);
 	free(default_ps.last_metricgroups);
 	strlist__delete(default_ps.visited_metrics);
+	if (output_path)
+		fclose(default_ps.fp);
+
 	return ret;
 }

tools/perf/builtin-record.c

···
 	}
 
 	if (rec->switch_output.num_files) {
-		rec->switch_output.filenames = calloc(sizeof(char *),
-						      rec->switch_output.num_files);
+		rec->switch_output.filenames = calloc(rec->switch_output.num_files,
+						      sizeof(char *));
 		if (!rec->switch_output.filenames) {
 			err = -EINVAL;
 			goto out_opts;

tools/perf/builtin-top.c

···
 
 static void prompt_integer(int *target, const char *msg)
 {
-	char *buf = malloc(0), *p;
+	char *buf = NULL, *p;
 	size_t dummy = 0;
 	int tmp;
 

tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json

···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
···
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
···
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.FPDIV@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
···
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
···
     },
     {
         "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / tma_info_core_clks",
         "MetricName": "tma_info_core_ipc",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.ALL@ / INST_RETIRED.ANY",
         "MetricName": "tma_info_core_upi",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_branch_mispredict_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BACLEARS.ANY",
         "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.CALL",
         "MetricName": "tma_info_inst_mix_ipcall",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
         "MetricName": "tma_info_inst_mix_ipfarbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Load",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_inst_mix_ipload",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_taken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT",
         "MetricName": "tma_info_inst_mix_ipmisp_indirect",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RETURN",
         "MetricName": "tma_info_inst_mix_ipmisp_ret",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipmispredict",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Store",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricName": "tma_info_inst_mix_ipstore",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_atom"
     },
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
···
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
···
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
+        "MetricExpr": "min(tma_backend_bound, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
···
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.MS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.OTHER_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
···
     {
         "BriefDescription": "Counts the number of issue slots  that result in retirement slots.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
···
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.PGWALK_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+        "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
         "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
···
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * ([e-mail]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([e-mail]_DATA_RD.L3_HIT.SNOOP_HITM@ + [e-mail]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
···
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - [e-mail]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([e-mail]_DATA_RD.L3_HIT.SNOOP_HITM@ + [e-mail]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "[e-mail]_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
         "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
···
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
···
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
···
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
···
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200",
···
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
···
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
         "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
···
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
···
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
···
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
···
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
···
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
···
     },
     {
         "BriefDescription": "Fraction of branches that are non-taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_nt",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_tk",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_core_core_clks",
         "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_core_coreipc",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "[e-mail]_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
···
     },
     {
         "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FRONTEND_RETIRED.ANY_DSB_MISS",
         "MetricGroup": "DSBmiss;Fed",
         "MetricName": "tma_info_frontend_ipdsb_miss_ret",
         "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
···
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "[e-mail]@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
···
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
···
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
···
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
···
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
···
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
···
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
         "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
···
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
         "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
···
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
         "MetricThreshold": "tma_info_inst_mix_ipload < 3",
···
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
         "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
···
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
         "MetricGroup": "Prefetches",
         "MetricName": "tma_info_inst_mix_ipswpf",
         "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
···
     },
     {
         "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
         "MetricThreshold": "tma_info_inst_mix_iptb < 13",
···
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / MEM_LOAD_COMPLETED.L1_MISS_ANY",
         "MetricGroup": "Mem;MemoryBound;MemoryLat",
         "MetricName": "tma_info_memory_load_miss_real_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / L1D_PEND_MISS.PENDING_CYCLES",
         "MetricGroup": "Mem;MemoryBW;MemoryBound",
         "MetricName": "tma_info_memory_mlp",
         "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
···
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD@ / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_data_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l3_miss_latency",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per a microcode Assist invocation",
-        "MetricExpr": "INST_RETIRED.ANY / [e-mail]\\,umask\\=0x1B@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / [e-mail]\\,umask\\=0x1B@",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
         "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
···
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
···
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricGroup": "HPC;Summary",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
         "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
···
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
···
     },
     {
         "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
         "MetricGroup": "Mem;SoC",
         "MetricName": "tma_info_system_mem_request_latency",
···
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
         "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
···
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks",
         "MetricGroup": "Ret;Summary",
         "MetricName": "tma_info_thread_ipc",
         "Unit": "cpu_core"
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
-        "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+        "MetricExpr": "[e-mail]@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
         "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
···
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_2_3_10@ / (3 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
···
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
         "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
···
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
···
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
···
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
···
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_0@ / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
···
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_1@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
···
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_6@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
         "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
         "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
         "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
-        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group",
         "MetricName": "tma_serializing_operation",
         "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))",
···
     },
     {
         "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.",
-        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+        "MetricExpr": "cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group",
         "MetricName": "tma_shuffles",
         "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
-        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
         "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))",
···
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
         "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
···
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
-        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
···
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
···
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
         "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
         "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",

tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json

···
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
···
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
···
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
···
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json

···
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
···
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
···
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
···
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
···
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
···
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
···
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
···
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
···
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
···
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
···
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
···
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
···
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
···
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
···
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
···
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",

tools/perf/tests/shell/daemon.sh

···
 	# start daemon
 	daemon_start ${config} test
 
-	# send 2 signals
-	perf daemon signal --config ${config} --session test
-	perf daemon signal --config ${config}
-
-	# stop daemon
-	daemon_exit ${config}
-
-	# count is 2 perf.data for signals and 1 for perf record finished
-	count=`ls ${base}/session-test/*perf.data* | wc -l`
-	if [ ${count} -ne 3 ]; then
+        # send 2 signals then exit. Do this in a loop watching the number of
+        # files to avoid races. If the loop retries more than 600 times then
+        # give up.
+	local retries=0
+	local signals=0
+	local success=0
+	while [ ${retries} -lt 600 ] && [ ${success} -eq 0 ]; do
+		local files
+		files=`ls ${base}/session-test/*perf.data* 2> /dev/null | wc -l`
+		if [ ${signals} -eq 0 ]; then
+			perf daemon signal --config ${config} --session test
+			signals=1
+		elif [ ${signals} -eq 1 ] && [ $files -ge 1 ]; then
+			perf daemon signal --config ${config}
+			signals=2
+		elif [ ${signals} -eq 2 ] && [ $files -ge 2 ]; then
+			daemon_exit ${config}
+			signals=3
+		elif [ ${signals} -eq 3 ] && [ $files -ge 3 ]; then
+			success=1
+		fi
+		retries=$((${retries} +1))
+	done
+	if [ ${success} -eq 0 ]; then
 		error=1
 		echo "FAILED: perf data no generated"
 	fi

tools/perf/tests/shell/list.sh

···
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
-err=0
 
 shelldir=$(dirname "$0")
 # shellcheck source=lib/setup_python.sh
 . "${shelldir}"/lib/setup_python.sh
 
+list_output=$(mktemp /tmp/__perf_test.list_output.json.XXXXX)
+
+cleanup() {
+  rm -f "${list_output}"
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
 test_list_json() {
   echo "Json output test"
-  perf list -j | $PYTHON -m json.tool
+  perf list -j -o "${list_output}"
+  $PYTHON -m json.tool "${list_output}"
   echo "Json output test [Success]"
 }
 
 test_list_json
-exit $err
+cleanup
+exit 0

tools/perf/tests/shell/script.sh

···
 	echo "DB test"
 
 	# Check if python script is supported
-	libpython=$(perf version --build-options | grep python | grep -cv OFF)
-	if [ "${libpython}" != "1" ] ; then
+        if perf version --build-options | grep python | grep -q OFF ; then
 		echo "SKIP: python scripting is not supported"
 		err=2
 		return
···
 def call_path_table(*args):
     print(f'call_path_table({args}')
 _end_of_file_
-	perf record -g -o "${perfdatafile}" true
+	case $(uname -m)
+	in s390x)
+		cmd_flags="--call-graph dwarf -e cpu-clock";;
+	*)
+		cmd_flags="-g";;
+	esac
+
+	perf record $cmd_flags -o "${perfdatafile}" true
 	perf script -i "${perfdatafile}" -s "${db_test}"
 	echo "DB test [Success]"
 }

tools/perf/trace/beauty/statx.c

···
 	P_FLAG(BTIME);
 	P_FLAG(MNT_ID);
 	P_FLAG(DIOALIGN);
+	P_FLAG(MNT_ID_UNIQUE);
 
 #undef P_FLAG
 

tools/perf/util/hist.c

···
 	}
 
 	if (symbol_conf.res_sample) {
-		he->res_samples = calloc(sizeof(struct res_sample),
-					symbol_conf.res_sample);
+		he->res_samples = calloc(symbol_conf.res_sample,
+					sizeof(struct res_sample));
 		if (!he->res_samples)
 			goto err_srcline;
 	}

tools/perf/util/include/linux/linkage.h

···
 	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
 #endif
 
+#ifndef SYM_FUNC_ALIAS_MEMFUNC
+#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
 // In the kernel sources (include/linux/cfi_types.h), this has a different
 // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
 // definition:

tools/perf/util/metricgroup.c

···
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
 
-	metric_events = calloc(sizeof(void *), ids_size + 1);
+	metric_events = calloc(ids_size + 1, sizeof(void *));
 	if (!metric_events)
 		return -ENOMEM;
 

tools/perf/util/print-events.c

···
 
 	put_tracing_file(events_path);
 	if (events_fd < 0) {
-		printf("Error: failed to open tracing events directory\n");
+		pr_err("Error: failed to open tracing events directory\n");
 		return;
 	}
 

tools/perf/util/synthetic-events.c

···
 	if (thread_nr > n)
 		thread_nr = n;
 
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	synthesize_threads = calloc(thread_nr, sizeof(pthread_t));
 	if (synthesize_threads == NULL)
 		goto free_dirent;
 
-	args = calloc(sizeof(*args), thread_nr);
+	args = calloc(thread_nr, sizeof(*args));
 	if (args == NULL)
 		goto free_threads;
 

tools/testing/selftests/drivers/net/bonding/bond_options.sh

···
 	local mode=$1
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect"
 	done
 }
···
 	fi
 
 	for primary_reselect in 0 1 2; do
-		prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
+		prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
 		log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect"
 	done
 }
···
 
 	for mode in $modes; do
 		prio_miimon $mode
-		prio_arp $mode
-		prio_ns $mode
 	done
+	prio_arp "active-backup"
+	prio_ns "active-backup"
 }
 
 arp_validate_test()

tools/testing/selftests/drivers/net/bonding/settings

···
-timeout=120
+timeout=1200

tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh

···
 	echo 1 > $NSIM_DEV_SYS/new_port
     fi
     NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ifconfig $NSIM_NETDEV up
 
     msg="new NIC device created"
     exp0=( 0 0 0 0 )
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     overflow_table0 "destroy NIC"
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
···
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
     ifconfig $NSIM_NETDEV up
 
     msg="create VxLANs v6"
···
 
 echo 2 > $NSIM_DEV_SYS/del_port
 echo 2 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
 check_tables
 
 msg="replace VxLAN in overflow table"

tools/testing/selftests/net/config

···
 CONFIG_USER_NS=y
 CONFIG_NET_NS=y
+CONFIG_BONDING=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_TEST_BPF=m
 CONFIG_NUMA=y
···
 CONFIG_NET_IPVTI=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
+CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
+CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
 CONFIG_IFB=y
+CONFIG_INET_DIAG=y
+CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
···
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IPV6_GRE=m
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_L2TP_ETH=m
+CONFIG_L2TP_IP=m
+CONFIG_L2TP=m
+CONFIG_L2TP_V3=y
+CONFIG_MACSEC=m
+CONFIG_MACVLAN=y
+CONFIG_MACVTAP=y
+CONFIG_MPLS=y
+CONFIG_MPTCP=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_U32=m
+CONFIG_NET_IPGRE_DEMUX=m
+CONFIG_NET_IPGRE=m
+CONFIG_NET_SCH_FQ_CODEL=m
+CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_PSAMPLE=m
+CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
 CONFIG_KALLSYMS=y
+CONFIG_TLS=m
 CONFIG_TRACEPOINTS=y
 CONFIG_NET_DROP_MONITOR=m
 CONFIG_NETDEVSIM=m
···
 CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4_GENERIC=y
 CONFIG_AMT=m
+CONFIG_TUN=y
 CONFIG_VXLAN=m
 CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
+CONFIG_XFRM_INTERFACE=m

tools/testing/selftests/net/rps_default_mask.sh

···
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 readonly ksft_skip=4
···
 
 	rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus)
 	printf "%-60s" "$msg"
+
+	# In case there is more than 32 CPUs we need to remove commas from masks
+	rps_mask=${rps_mask//,}
+	expected_rps_mask=${expected_rps_mask//,}
 	if [ $rps_mask -eq $expected_rps_mask ]; then
 		echo "[ ok ]"
 	else

tools/testing/selftests/net/so_incoming_cpu.c

···
 #define _GNU_SOURCE
 #include <sched.h>
 
+#include <fcntl.h>
+
 #include <netinet/in.h>
 #include <sys/socket.h>
 #include <sys/sysinfo.h>
 
 #include "../kselftest_harness.h"
 
-#define CLIENT_PER_SERVER	32 /* More sockets, more reliable */
-#define NR_SERVER		self->nproc
-#define NR_CLIENT		(CLIENT_PER_SERVER * NR_SERVER)
-
 FIXTURE(so_incoming_cpu)
 {
-	int nproc;
 	int *servers;
 	union {
 		struct sockaddr addr;
···
 	.when_to_set = AFTER_ALL_LISTEN,
 };
 
+static void write_sysctl(struct __test_metadata *_metadata,
+			 char *filename, char *string)
+{
+	int fd, len, ret;
+
+	fd = open(filename, O_WRONLY);
+	ASSERT_NE(fd, -1);
+
+	len = strlen(string);
+	ret = write(fd, string, len);
+	ASSERT_EQ(ret, len);
+}
+
+static void setup_netns(struct __test_metadata *_metadata)
+{
+	ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+	ASSERT_EQ(system("ip link set lo up"), 0);
+
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/ip_local_port_range", "10000 60001");
+	write_sysctl(_metadata, "/proc/sys/net/ipv4/tcp_tw_reuse", "0");
+}
+
+#define NR_PORT				(60001 - 10000 - 1)
+#define NR_CLIENT_PER_SERVER_DEFAULT	32
+static int nr_client_per_server, nr_server, nr_client;
+
 FIXTURE_SETUP(so_incoming_cpu)
 {
-	self->nproc = get_nprocs();
-	ASSERT_LE(2, self->nproc);
+	setup_netns(_metadata);
 
-	self->servers = malloc(sizeof(int) * NR_SERVER);
+	nr_server = get_nprocs();
+	ASSERT_LE(2, nr_server);
+
+	if (NR_CLIENT_PER_SERVER_DEFAULT * nr_server < NR_PORT)
+		nr_client_per_server = NR_CLIENT_PER_SERVER_DEFAULT;
+	else
+		nr_client_per_server = NR_PORT / nr_server;
+
+	nr_client = nr_client_per_server * nr_server;
+
+	self->servers = malloc(sizeof(int) * nr_server);
 	ASSERT_NE(self->servers, NULL);
 
 	self->in_addr.sin_family = AF_INET;
···
 {
 	int i;
 
-	for (i = 0; i < NR_SERVER; i++)
+	for (i = 0; i < nr_server; i++)
 		close(self->servers[i]);
 
 	free(self->servers);
···
 	if (variant->when_to_set == BEFORE_LISTEN)
 		set_so_incoming_cpu(_metadata, fd, cpu);
 
-	/* We don't use CLIENT_PER_SERVER here not to block
+	/* We don't use nr_client_per_server here not to block
 	 * this test at connect() if SO_INCOMING_CPU is broken.
 	 */
-	ret = listen(fd, NR_CLIENT);
+	ret = listen(fd, nr_client);
 	ASSERT_EQ(ret, 0);
 
 	if (variant->when_to_set == AFTER_LISTEN)
···
 {
 	int i, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		self->servers[i] = create_server(_metadata, self, variant, i);
 
 		if (i == 0) {
···
 	}
 
 	if (variant->when_to_set == AFTER_ALL_LISTEN) {
-		for (i = 0; i < NR_SERVER; i++)
+		for (i = 0; i < nr_server; i++)
 			set_so_incoming_cpu(_metadata, self->servers[i], i);
 	}
 }
···
 	cpu_set_t cpu_set;
 	int i, j, fd, ret;
 
-	for (i = 0; i < NR_SERVER; i++) {
+	for (i = 0; i < nr_server; i++) {
 		CPU_ZERO(&cpu_set);
 
 		CPU_SET(i, &cpu_set);
···
 		ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 		ASSERT_EQ(ret, 0);
 
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			fd  = socket(AF_INET, SOCK_STREAM, 0);
 			ASSERT_NE(fd, -1);
 
···
 	int i, j, fd, cpu, ret, total = 0;
 	socklen_t len = sizeof(int);
 
-	for (i = 0; i < NR_SERVER; i++) {
-		for (j = 0; j < CLIENT_PER_SERVER; j++) {
+	for (i = 0; i < nr_server; i++) {
+		for (j = 0; j < nr_client_per_server; j++) {
 			/* If we see -EAGAIN here, SO_INCOMING_CPU is broken */
 			fd = accept(self->servers[i], &self->addr, &self->addrlen);
 			ASSERT_NE(fd, -1);
···
 		}
 	}
 
-	ASSERT_EQ(total, NR_CLIENT);
+	ASSERT_EQ(total, nr_client);
 	TH_LOG("SO_INCOMING_CPU is very likely to be "
 	       "working correctly with %d sockets.", total);
 }