Merge tag 'driver-core-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core / kernfs updates from Greg KH:
 "Here is the set of driver core and kernfs changes for 6.0-rc1.

  The "biggest" thing in here is some scalability improvements for
  kernfs for large systems. Other than that, included in here are:

   - arch topology and cache info changes that have been reviewed and
     discussed a lot.

   - potential error path cleanup fixes

   - deferred driver probe cleanups

   - firmware loader cleanups and tweaks

   - documentation updates

   - other small things

  All of these have been in the linux-next tree for a while with no
  reported problems"

* tag 'driver-core-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (63 commits)
  docs: embargoed-hardware-issues: fix invalid AMD contact email
  firmware_loader: Replace kmap() with kmap_local_page()
  sysfs docs: ABI: Fix typo in comment
  kobject: fix Kconfig.debug "its" grammar
  kernfs: Fix typo 'the the' in comment
  docs: driver-api: firmware: add driver firmware guidelines. (v3)
  arch_topology: Fix cache attributes detection in the CPU hotplug path
  ACPI: PPTT: Leave the table mapped for the runtime usage
  cacheinfo: Use atomic allocation for percpu cache attributes
  drivers/base: fix userspace break from using bin_attributes for cpumap and cpulist
  MAINTAINERS: Change mentions of mpm to olivia
  docs: ABI: sysfs-devices-soc: Update Lee Jones' email address
  docs: ABI: sysfs-class-pwm: Update Lee Jones' email address
  Documentation/process: Add embargoed HW contact for LLVM
  Revert "kernfs: Change kernfs_notify_list to llist."
  ACPI: Remove the unused find_acpi_cpu_cache_topology()
  arch_topology: Warn that topology for nested clusters is not supported
  arch_topology: Add support for parsing sockets in /cpu-map
  arch_topology: Set cluster identifier in each core/thread from /cpu-map
  arch_topology: Limit span of cpu_clustergroup_mask()
  ...

Documentation/ABI/stable/sysfs-module

@@ -38,7 +38,7 @@ What:		/sys/module/<MODULENAME>/srcversion
 Date:		Jun 2005
 Description:
 		If the module source has MODULE_VERSION, this file will contain
-		the checksum of the the source code.
+		the checksum of the source code.
 
 What:		/sys/module/<MODULENAME>/version
 Date:		Jun 2005

Documentation/ABI/testing/sysfs-class-pwm

@@ -81,7 +81,7 @@ Description:
 What:		/sys/class/pwm/pwmchip<N>/pwmX/capture
 Date:		June 2016
 KernelVersion:	4.8
-Contact:	Lee Jones <lee.jones@linaro.org>
+Contact:	Lee Jones <lee@kernel.org>
 Description:
 		Capture information about a PWM signal. The output format is a
 		pair unsigned integers (period and duty cycle), separated by a

Documentation/ABI/testing/sysfs-class-rtrs-client

@@ -78,7 +78,7 @@ What:		/sys/class/rtrs-client/<session-name>/paths/<src@dst>/hca_name
 Date:		Feb 2020
 KernelVersion:	5.7
 Contact:	Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
-Description:	RO, Contains the the name of HCA the connection established on.
+Description:	RO, Contains the name of HCA the connection established on.
 
 What:		/sys/class/rtrs-client/<session-name>/paths/<src@dst>/hca_port
 Date:		Feb 2020

Documentation/ABI/testing/sysfs-class-rtrs-server

@@ -24,7 +24,7 @@ What:		/sys/class/rtrs-server/<session-name>/paths/<src@dst>/hca_name
 Date:		Feb 2020
 KernelVersion:	5.7
 Contact:	Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
-Description:	RO, Contains the the name of HCA the connection established on.
+Description:	RO, Contains the name of HCA the connection established on.
 
 What:		/sys/class/rtrs-server/<session-name>/paths/<src@dst>/hca_port
 Date:		Feb 2020

Documentation/ABI/testing/sysfs-devices-platform-ACPI-TAD

@@ -74,7 +74,7 @@ Description:
 
 		Reads also cause the AC alarm timer status to be reset.
 
-		Another way to reset the the status of the AC alarm timer is to
+		Another way to reset the status of the AC alarm timer is to
 		write (the number) 0 to this file.
 
 		If the status return value indicates that the timer has expired,

Documentation/ABI/testing/sysfs-devices-power

@@ -303,5 +303,5 @@ Date:		Apr 2010
 Contact:	Dominik Brodowski <linux@dominikbrodowski.net>
 Description:
 		Reports the runtime PM children usage count of a device, or
-		0 if the the children will be ignored.
+		0 if the children will be ignored.
 

Documentation/ABI/testing/sysfs-devices-soc

 What:		/sys/devices/socX
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		The /sys/devices/ directory contains a sub-directory for each
 		System-on-Chip (SoC) device on a running platform. Information
@@ -14,14 +14,14 @@ Description:
 
 What:		/sys/devices/socX/machine
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		Read-only attribute common to all SoCs. Contains the SoC machine
 		name (e.g. Ux500).
 
 What:		/sys/devices/socX/family
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		Read-only attribute common to all SoCs. Contains SoC family name
 		(e.g. DB8500).
@@ -59,7 +59,7 @@ Description:
 
 What:		/sys/devices/socX/soc_id
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		Read-only attribute supported by most SoCs. In the case of
 		ST-Ericsson's chips this contains the SoC serial number.
@@ -72,21 +72,21 @@ Description:
 
 What:		/sys/devices/socX/revision
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		Read-only attribute supported by most SoCs. Contains the SoC's
 		manufacturing revision number.
 
 What:		/sys/devices/socX/process
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		Read-only attribute supported ST-Ericsson's silicon. Contains the
 		the process by which the silicon chip was manufactured.
 
 What:		/sys/bus/soc
 Date:		January 2012
-contact:	Lee Jones <lee.jones@linaro.org>
+contact:	Lee Jones <lee@kernel.org>
 Description:
 		The /sys/bus/soc/ directory contains the usual sub-folders
 		expected under most buses. /sys/bus/soc/devices is of particular

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -67,8 +67,7 @@ Description:	Discover NUMA node a CPU belongs to
 		/sys/devices/system/cpu/cpu42/node2 -> ../../node/node2
 
 
-What:		/sys/devices/system/cpu/cpuX/topology/core_id
-		/sys/devices/system/cpu/cpuX/topology/core_siblings
+What:		/sys/devices/system/cpu/cpuX/topology/core_siblings
 		/sys/devices/system/cpu/cpuX/topology/core_siblings_list
 		/sys/devices/system/cpu/cpuX/topology/physical_package_id
 		/sys/devices/system/cpu/cpuX/topology/thread_siblings
@@ -84,10 +83,6 @@ Description:	CPU topology files that describe a logical CPU's relationship
 
 		Briefly, the files above are:
 
-		core_id: the CPU core ID of cpuX. Typically it is the
-		hardware platform's identifier (rather than the kernel's).
-		The actual value is architecture and platform dependent.
-
 		core_siblings: internal kernel map of cpuX's hardware threads
 		within the same physical_package_id.
 

Documentation/driver-api/firmware/core.rst

@@ -13,4 +13,5 @@ documents these features.
    direct-fs-lookup
    fallback-mechanisms
    lookup-order
+   firmware-usage-guidelines
 

Documentation/driver-api/firmware/firmware-usage-guidelines.rst

+===================
+Firmware Guidelines
+===================
+
+Users switching to a newer kernel should *not* have to install newer
+firmware files to keep their hardware working. At the same time updated
+firmware files must not cause any regressions for users of older kernel
+releases.
+
+Drivers that use firmware from linux-firmware should follow the rules in
+this guide. (Where there is limited control of the firmware,
+i.e. company doesn't support Linux, firmwares sourced from misc places,
+then of course these rules will not apply strictly.)
+
+* Firmware files shall be designed in a way that it allows checking for
+  firmware ABI version changes. It is recommended that firmware files be
+  versioned with at least a major/minor version. It is suggested that
+  the firmware files in linux-firmware be named with some device
+  specific name, and just the major version. The firmware version should
+  be stored in the firmware header, or as an exception, as part of the
+  firmware file name, in order to let the driver detact any non-ABI
+  fixes/changes. The firmware files in linux-firmware should be
+  overwritten with the newest compatible major version. Newer major
+  version firmware shall remain compatible with all kernels that load
+  that major number.
+
+* If the kernel support for the hardware is normally inactive, or the
+  hardware isn't available for public consumption, this can
+  be ignored, until the first kernel release that enables that hardware.
+  This means no major version bumps without the kernel retaining
+  backwards compatibility for the older major versions.  Minor version
+  bumps should not introduce new features that newer kernels depend on
+  non-optionally.
+
+* If a security fix needs lockstep firmware and kernel fixes in order to
+  be successful, then all supported major versions in the linux-firmware
+  repo that are required by currently supported stable/LTS kernels,
+  should be updated with the security fix. The kernel patches should
+  detect if the firmware is new enough to declare if the security issue
+  is fixed.  All communications around security fixes should point at
+  both the firmware and kernel fixes. If a security fix requires
+  deprecating old major versions, then this should only be done as a
+  last option, and be stated clearly in all communications.
+

Documentation/process/embargoed-hardware-issues.rst

@@ -244,7 +244,7 @@ disclosure of a particular issue, unless requested by a response team or by
 an involved disclosed party. The current ambassadors list:
 
   ============= ========================================================
-  AMD		Tom Lendacky <tom.lendacky@amd.com>
+  AMD		Tom Lendacky <thomas.lendacky@amd.com>
   Ampere	Darren Hart <darren@os.amperecomputing.com>
   ARM		Catalin Marinas <catalin.marinas@arm.com>
   IBM Power	Anton Blanchard <anton@linux.ibm.com>
@@ -264,6 +264,9 @@ an involved disclosed party. The current ambassadors list:
 
   Amazon
   Google	Kees Cook <keescook@chromium.org>
+
+  GCC
+  LLVM		Nick Desaulniers <ndesaulniers@google.com>
   ============= ========================================================
 
 If you want your organization to be added to the ambassadors list, please

Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst

@@ -174,7 +174,7 @@ CVE分配
 
   ============= ========================================================
   ARM
-  AMD		Tom Lendacky <tom.lendacky@amd.com>
+  AMD		Tom Lendacky <thomas.lendacky@amd.com>
   IBM
   Intel		Tony Luck <tony.luck@intel.com>
   Qualcomm	Trilok Soni <tsoni@codeaurora.org>

Documentation/translations/zh_TW/process/embargoed-hardware-issues.rst

@@ -177,7 +177,7 @@ CVE分配
 
   ============= ========================================================
   ARM
-  AMD		Tom Lendacky <tom.lendacky@amd.com>
+  AMD		Tom Lendacky <thomas.lendacky@amd.com>
   IBM
   Intel		Tony Luck <tony.luck@intel.com>
   Qualcomm	Trilok Soni <tsoni@codeaurora.org>

MAINTAINERS

@@ -7494,7 +7494,7 @@ F:	Documentation/admin-guide/media/em28xx*
 F:	drivers/media/usb/em28xx/
 
 EMBEDDED LINUX
-M:	Matt Mackall <mpm@selenic.com>
+M:	Olivia Mackall <olivia@selenic.com>
 M:	David Woodhouse <dwmw2@infradead.org>
 L:	linux-embedded@vger.kernel.org
 S:	Maintained
@@ -8902,7 +8902,7 @@ F:	include/trace/events/hwmon*.h
 K:	(devm_)?hwmon_device_(un)?register(|_with_groups|_with_info)
 
 HARDWARE RANDOM NUMBER GENERATOR CORE
-M:	Matt Mackall <mpm@selenic.com>
+M:	Olivia Mackall <olivia@selenic.com>
 M:	Herbert Xu <herbert@gondor.apana.org.au>
 L:	linux-crypto@vger.kernel.org
 S:	Odd fixes

arch/arm64/kernel/topology.c

@@ -89,8 +89,6 @@ int __init parse_acpi_topology(void)
 		return 0;
 
 	for_each_possible_cpu(cpu) {
-		int i, cache_id;
-
 		topology_id = find_acpi_cpu_topology(cpu, 0);
 		if (topology_id < 0)
 			return topology_id;
@@ -107,18 +105,6 @@ int __init parse_acpi_topology(void)
 		cpu_topology[cpu].cluster_id = topology_id;
 		topology_id = find_acpi_cpu_topology_package(cpu);
 		cpu_topology[cpu].package_id = topology_id;
-
-		i = acpi_find_last_cache_level(cpu);
-
-		if (i > 0) {
-			/*
-			 * this is the only part of cpu_topology that has
-			 * a direct relationship with the cache topology
-			 */
-			cache_id = find_acpi_cpu_cache_topology(cpu, i);
-			if (cache_id > 0)
-				cpu_topology[cpu].llc_id = cache_id;
-		}
 	}
 
 	return 0;

drivers/acpi/pptt.c

@@ -437,7 +437,8 @@ static void cache_setup_acpi_cpu(struct acpi_table_header *table,
 		pr_debug("found = %p %p\n", found_cache, cpu_node);
 		if (found_cache)
 			update_cache_properties(this_leaf, found_cache,
-			                        cpu_node, table->revision);
+						ACPI_TO_POINTER(ACPI_PTR_DIFF(cpu_node, table)),
+						table->revision);
 
 		index++;
 	}
@@ -532,21 +533,37 @@ static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 	return -ENOENT;
 }
 
+
+static struct acpi_table_header *acpi_get_pptt(void)
+{
+	static struct acpi_table_header *pptt;
+	acpi_status status;
+
+	/*
+	 * PPTT will be used at runtime on every CPU hotplug in path, so we
+	 * don't need to call acpi_put_table() to release the table mapping.
+	 */
+	if (!pptt) {
+		status = acpi_get_table(ACPI_SIG_PPTT, 0, &pptt);
+		if (ACPI_FAILURE(status))
+			acpi_pptt_warn_missing();
+	}
+
+	return pptt;
+}
+
 static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 {
 	struct acpi_table_header *table;
-	acpi_status status;
 	int retval;
 
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
+	table = acpi_get_pptt();
+	if (!table)
 		return -ENOENT;
-	}
+
 	retval = topology_get_acpi_cpu_tag(table, cpu, level, flag);
 	pr_debug("Topology Setup ACPI CPU %d, level %d ret = %d\n",
 		 cpu, level, retval);
-	acpi_put_table(table);
 
 	return retval;
 }
@@ -567,16 +584,13 @@ static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 static int check_acpi_cpu_flag(unsigned int cpu, int rev, u32 flag)
 {
 	struct acpi_table_header *table;
-	acpi_status status;
 	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
 	struct acpi_pptt_processor *cpu_node = NULL;
 	int ret = -ENOENT;
 
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
-		return ret;
-	}
+	table = acpi_get_pptt();
+	if (!table)
+		return -ENOENT;
 
 	if (table->revision >= rev)
 		cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
@@ -584,8 +598,6 @@ static int check_acpi_cpu_flag(unsigned int cpu, int rev, u32 flag)
 	if (cpu_node)
 		ret = (cpu_node->flags & flag) != 0;
 
-	acpi_put_table(table);
-
 	return ret;
 }
 
@@ -604,18 +616,15 @@ int acpi_find_last_cache_level(unsigned int cpu)
 	u32 acpi_cpu_id;
 	struct acpi_table_header *table;
 	int number_of_levels = 0;
-	acpi_status status;
+
+	table = acpi_get_pptt();
+	if (!table)
+		return -ENOENT;
 
 	pr_debug("Cache Setup find last level CPU=%d\n", cpu);
 
 	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
-	} else {
-		number_of_levels = acpi_find_cache_levels(table, acpi_cpu_id);
-		acpi_put_table(table);
-	}
+	number_of_levels = acpi_find_cache_levels(table, acpi_cpu_id);
 	pr_debug("Cache Setup find last level level=%d\n", number_of_levels);
 
 	return number_of_levels;
@@ -637,20 +646,16 @@ int acpi_find_last_cache_level(unsigned int cpu)
 int cache_setup_acpi(unsigned int cpu)
 {
 	struct acpi_table_header *table;
-	acpi_status status;
 
-	pr_debug("Cache Setup ACPI CPU %d\n", cpu);
-
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
+	table = acpi_get_pptt();
+	if (!table)
 		return -ENOENT;
-	}
+
+	pr_debug("Cache Setup ACPI CPU %d\n", cpu);
 
 	cache_setup_acpi_cpu(table, cpu);
-	acpi_put_table(table);
 
-	return status;
+	return 0;
 }
 
 /**
@@ -690,43 +695,6 @@ int find_acpi_cpu_topology(unsigned int cpu, int level)
 	return find_acpi_cpu_topology_tag(cpu, level, 0);
 }
 
-/**
- * find_acpi_cpu_cache_topology() - Determine a unique cache topology value
- * @cpu: Kernel logical CPU number
- * @level: The cache level for which we would like a unique ID
- *
- * Determine a unique ID for each unified cache in the system
- *
- * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
- * Otherwise returns a value which represents a unique topological feature.
- */
-int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
-{
-	struct acpi_table_header *table;
-	struct acpi_pptt_cache *found_cache;
-	acpi_status status;
-	u32 acpi_cpu_id = get_acpi_id_for_cpu(cpu);
-	struct acpi_pptt_processor *cpu_node = NULL;
-	int ret = -1;
-
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
-		return -ENOENT;
-	}
-
-	found_cache = acpi_find_cache_node(table, acpi_cpu_id,
-					   CACHE_TYPE_UNIFIED,
-					   level,
-					   &cpu_node);
-	if (found_cache)
-		ret = ACPI_PTR_DIFF(cpu_node, table);
-
-	acpi_put_table(table);
-
-	return ret;
-}
-
 /**
  * find_acpi_cpu_topology_package() - Determine a unique CPU package value
  * @cpu: Kernel logical CPU number
@@ -766,50 +734,38 @@ int find_acpi_cpu_topology_package(unsigned int cpu)
 int find_acpi_cpu_topology_cluster(unsigned int cpu)
 {
 	struct acpi_table_header *table;
-	acpi_status status;
 	struct acpi_pptt_processor *cpu_node, *cluster_node;
 	u32 acpi_cpu_id;
 	int retval;
 	int is_thread;
 
-	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
-	if (ACPI_FAILURE(status)) {
-		acpi_pptt_warn_missing();
+	table = acpi_get_pptt();
+	if (!table)
 		return -ENOENT;
-	}
 
 	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
 	cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
-	if (cpu_node == NULL || !cpu_node->parent) {
-		retval = -ENOENT;
-		goto put_table;
-	}
+	if (!cpu_node || !cpu_node->parent)
+		return -ENOENT;
 
 	is_thread = cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_IS_THREAD;
 	cluster_node = fetch_pptt_node(table, cpu_node->parent);
-	if (cluster_node == NULL) {
-		retval = -ENOENT;
-		goto put_table;
-	}
+	if (!cluster_node)
+		return -ENOENT;
+
 	if (is_thread) {
-		if (!cluster_node->parent) {
-			retval = -ENOENT;
-			goto put_table;
-		}
+		if (!cluster_node->parent)
+			return -ENOENT;
+
 		cluster_node = fetch_pptt_node(table, cluster_node->parent);
-		if (cluster_node == NULL) {
-			retval = -ENOENT;
-			goto put_table;
-		}
+		if (!cluster_node)
+			return -ENOENT;
 	}
 	if (cluster_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID)
 		retval = cluster_node->acpi_processor_id;
 	else
 		retval = ACPI_PTR_DIFF(cluster_node, table);
 
-put_table:
-	acpi_put_table(table);
-
 	return retval;
 }
 

drivers/base/arch_topology.c

@@ -7,6 +7,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
@@ -496,7 +497,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 }
 
 static int __init parse_core(struct device_node *core, int package_id,
-			     int core_id)
+			     int cluster_id, int core_id)
 {
 	char name[20];
 	bool leaf = true;
@@ -512,6 +513,7 @@ static int __init parse_core(struct device_node *core, int package_id,
 			cpu = get_cpu_for_node(t);
 			if (cpu >= 0) {
 				cpu_topology[cpu].package_id = package_id;
+				cpu_topology[cpu].cluster_id = cluster_id;
 				cpu_topology[cpu].core_id = core_id;
 				cpu_topology[cpu].thread_id = i;
 			} else if (cpu != -ENODEV) {
@@ -533,6 +535,7 @@ static int __init parse_core(struct device_node *core, int package_id,
 		}
 
 		cpu_topology[cpu].package_id = package_id;
+		cpu_topology[cpu].cluster_id = cluster_id;
 		cpu_topology[cpu].core_id = core_id;
 	} else if (leaf && cpu != -ENODEV) {
 		pr_err("%pOF: Can't get CPU for leaf core\n", core);
@@ -542,13 +545,13 @@ static int __init parse_core(struct device_node *core, int package_id,
 	return 0;
 }
 
-static int __init parse_cluster(struct device_node *cluster, int depth)
+static int __init parse_cluster(struct device_node *cluster, int package_id,
+				int cluster_id, int depth)
 {
 	char name[20];
 	bool leaf = true;
 	bool has_cores = false;
 	struct device_node *c;
-	static int package_id __initdata;
 	int core_id = 0;
 	int i, ret;
 
@@ -563,7 +566,9 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 		c = of_get_child_by_name(cluster, name);
 		if (c) {
 			leaf = false;
-			ret = parse_cluster(c, depth + 1);
+			ret = parse_cluster(c, package_id, i, depth + 1);
+			if (depth > 0)
+				pr_warn("Topology for clusters of clusters not yet supported\n");
 			of_node_put(c);
 			if (ret != 0)
 				return ret;
@@ -587,7 +592,8 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 			}
 
 			if (leaf) {
-				ret = parse_core(c, package_id, core_id++);
+				ret = parse_core(c, package_id, cluster_id,
+						 core_id++);
 			} else {
 				pr_err("%pOF: Non-leaf cluster with core %s\n",
 				       cluster, name);
@@ -604,10 +610,33 @@ static int __init parse_cluster(struct device_node *cluster, int depth)
 	if (leaf && !has_cores)
 		pr_warn("%pOF: empty cluster\n", cluster);
 
-	if (leaf)
+	return 0;
+}
+
+static int __init parse_socket(struct device_node *socket)
+{
+	char name[20];
+	struct device_node *c;
+	bool has_socket = false;
+	int package_id = 0, ret;
+
+	do {
+		snprintf(name, sizeof(name), "socket%d", package_id);
+		c = of_get_child_by_name(socket, name);
+		if (c) {
+			has_socket = true;
+			ret = parse_cluster(c, package_id, -1, 0);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
 		package_id++;
+	} while (c);
 
-	return 0;
+	if (!has_socket)
+		ret = parse_cluster(socket, 0, -1, 0);
+
+	return ret;
 }
 
 static int __init parse_dt_topology(void)
@@ -630,7 +659,7 @@ static int __init parse_dt_topology(void)
 	if (!map)
 		goto out;
 
-	ret = parse_cluster(map, 0);
+	ret = parse_socket(map);
 	if (ret != 0)
 		goto out_map;
 
@@ -641,8 +670,10 @@ static int __init parse_dt_topology(void)
 	 * only mark cores described in the DT as possible.
 	 */
 	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].package_id == -1)
+		if (cpu_topology[cpu].package_id < 0) {
 			ret = -EINVAL;
+			break;
+		}
 
 out_map:
 	of_node_put(map);
@@ -667,7 +698,8 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 		/* not numa in package, lets use the package siblings */
 		core_mask = &cpu_topology[cpu].core_sibling;
 	}
-	if (cpu_topology[cpu].llc_id != -1) {
+
+	if (last_level_cache_is_valid(cpu)) {
 		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
 			core_mask = &cpu_topology[cpu].llc_sibling;
 	}
@@ -686,19 +718,31 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 
 const struct cpumask *cpu_clustergroup_mask(int cpu)
 {
+	/*
+	 * Forbid cpu_clustergroup_mask() to span more or the same CPUs as
+	 * cpu_coregroup_mask().
+	 */
+	if (cpumask_subset(cpu_coregroup_mask(cpu),
+			   &cpu_topology[cpu].cluster_sibling))
+		return get_cpu_mask(cpu);
+
 	return &cpu_topology[cpu].cluster_sibling;
 }
 
 void update_siblings_masks(unsigned int cpuid)
 {
 	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
-	int cpu;
+	int cpu, ret;
+
+	ret = detect_cache_attributes(cpuid);
+	if (ret)
+		pr_info("Early cacheinfo failed, ret = %d\n", ret);
 
 	/* update core and thread sibling masks */
 	for_each_online_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
 
-		if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) {
+		if (last_level_cache_is_shared(cpu, cpuid)) {
 			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
 			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
 		}
@@ -706,15 +750,17 @@ void update_siblings_masks(unsigned int cpuid)
 		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;
 
-		if (cpuid_topo->cluster_id == cpu_topo->cluster_id &&
-		    cpuid_topo->cluster_id != -1) {
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+			continue;
+
+		if (cpuid_topo->cluster_id >= 0) {
 			cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling);
 			cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling);
 		}
 
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
 		if (cpuid_topo->core_id != cpu_topo->core_id)
 			continue;
 
@@ -750,7 +796,6 @@ void __init reset_cpu_topology(void)
 		cpu_topo->core_id = -1;
 		cpu_topo->cluster_id = -1;
 		cpu_topo->package_id = -1;
-		cpu_topo->llc_id = -1;
 
 		clear_cpu_topology(cpu);
 	}
@@ -780,15 +825,20 @@ __weak int __init parse_acpi_topology(void)
 #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
 void __init init_cpu_topology(void)
 {
+	int ret;
+
 	reset_cpu_topology();
+	ret = parse_acpi_topology();
+	if (!ret)
+		ret = of_have_populated_dt() && parse_dt_topology();
 
-	/*
-	 * Discard anything that was parsed if we hit an error so we
-	 * don't use partial information.
-	 */
-	if (parse_acpi_topology())
-		reset_cpu_topology();
-	else if (of_have_populated_dt() && parse_dt_topology())
+	if (ret) {
+		/*
+		 * Discard anything that was parsed if we hit an error so we
+		 * don't use partial information.
+		 */
 		reset_cpu_topology();
+		return;
+	}
 }
 #endif

drivers/base/base.h

@@ -160,6 +160,7 @@ extern int devres_release_all(struct device *dev);
 extern void device_block_probing(void);
 extern void device_unblock_probing(void);
 extern void deferred_probe_extend_timeout(void);
+extern void driver_deferred_probe_trigger(void);
 
 /* /sys/devices directory */
 extern struct kset *devices_kset;

drivers/base/cacheinfo.c

@@ -14,7 +14,7 @@
 #include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/init.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
@@ -25,19 +25,60 @@ static DEFINE_PER_CPU(struct cpu_cacheinfo, ci_cpu_cacheinfo);
 #define ci_cacheinfo(cpu)	(&per_cpu(ci_cpu_cacheinfo, cpu))
 #define cache_leaves(cpu)	(ci_cacheinfo(cpu)->num_leaves)
 #define per_cpu_cacheinfo(cpu)	(ci_cacheinfo(cpu)->info_list)
+#define per_cpu_cacheinfo_idx(cpu, idx)		\
+				(per_cpu_cacheinfo(cpu) + (idx))
 
 struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu)
 {
 	return ci_cacheinfo(cpu);
 }
 
-#ifdef CONFIG_OF
 static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 					   struct cacheinfo *sib_leaf)
 {
+	/*
+	 * For non DT/ACPI systems, assume unique level 1 caches,
+	 * system-wide shared caches for all other levels. This will be used
+	 * only if arch specific code has not populated shared_cpu_map
+	 */
+	if (!(IS_ENABLED(CONFIG_OF) || IS_ENABLED(CONFIG_ACPI)))
+		return !(this_leaf->level == 1);
+
+	if ((sib_leaf->attributes & CACHE_ID) &&
+	    (this_leaf->attributes & CACHE_ID))
+		return sib_leaf->id == this_leaf->id;
+
 	return sib_leaf->fw_token == this_leaf->fw_token;
 }
 
+bool last_level_cache_is_valid(unsigned int cpu)
+{
+	struct cacheinfo *llc;
+
+	if (!cache_leaves(cpu))
+		return false;
+
+	llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
+
+	return (llc->attributes & CACHE_ID) || !!llc->fw_token;
+
+}
+
+bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y)
+{
+	struct cacheinfo *llc_x, *llc_y;
+
+	if (!last_level_cache_is_valid(cpu_x) ||
+	    !last_level_cache_is_valid(cpu_y))
+		return false;
+
+	llc_x = per_cpu_cacheinfo_idx(cpu_x, cache_leaves(cpu_x) - 1);
+	llc_y = per_cpu_cacheinfo_idx(cpu_y, cache_leaves(cpu_y) - 1);
+
+	return cache_leaves_are_shared(llc_x, llc_y);
+}
+
+#ifdef CONFIG_OF
 /* OF properties to query for a given cache type */
 struct cache_type_info {
 	const char *size_prop;
@@ -157,27 +198,16 @@ static int cache_setup_of_node(unsigned int cpu)
 {
 	struct device_node *np;
 	struct cacheinfo *this_leaf;
-	struct device *cpu_dev = get_cpu_device(cpu);
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	unsigned int index = 0;
 
-	/* skip if fw_token is already populated */
-	if (this_cpu_ci->info_list->fw_token) {
-		return 0;
-	}
-
-	if (!cpu_dev) {
-		pr_err("No cpu device for CPU %d\n", cpu);
-		return -ENODEV;
-	}
-	np = cpu_dev->of_node;
+	np = of_cpu_device_node_get(cpu);
 	if (!np) {
 		pr_err("Failed to find cpu%d device node\n", cpu);
 		return -ENOENT;
 	}
 
 	while (index < cache_leaves(cpu)) {
-		this_leaf = this_cpu_ci->info_list + index;
+		this_leaf = per_cpu_cacheinfo_idx(cpu, index);
 		if (this_leaf->level != 1)
 			np = of_find_next_cache_node(np);
 		else
@@ -196,16 +226,6 @@ static int cache_setup_of_node(unsigned int cpu)
 }
 #else
 static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
-static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
-					   struct cacheinfo *sib_leaf)
-{
-	/*
-	 * For non-DT/ACPI systems, assume unique level 1 caches, system-wide
-	 * shared caches for all other levels. This will be used only if
-	 * arch specific code has not populated shared_cpu_map
-	 */
-	return !(this_leaf->level == 1);
-}
 #endif
 
 int __weak cache_setup_acpi(unsigned int cpu)
@@ -215,6 +235,18 @@ int __weak cache_setup_acpi(unsigned int cpu)
 
 unsigned int coherency_max_size;
 
+static int cache_setup_properties(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (of_have_populated_dt())
+		ret = cache_setup_of_node(cpu);
+	else if (!acpi_disabled)
+		ret = cache_setup_acpi(cpu);
+
+	return ret;
+}
+
 static int cache_shared_cpu_map_setup(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
@@ -225,21 +257,21 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 	if (this_cpu_ci->cpu_map_populated)
 		return 0;
 
-	if (of_have_populated_dt())
-		ret = cache_setup_of_node(cpu);
-	else if (!acpi_disabled)
-		ret = cache_setup_acpi(cpu);
-
-	if (ret)
-		return ret;
+	/*
+	 * skip setting up cache properties if LLC is valid, just need
+	 * to update the shared cpu_map if the cache attributes were
+	 * populated early before all the cpus are brought online
+	 */
+	if (!last_level_cache_is_valid(cpu)) {
+		ret = cache_setup_properties(cpu);
+		if (ret)
+			return ret;
+	}
 
 	for (index = 0; index < cache_leaves(cpu); index++) {
 		unsigned int i;
 
-		this_leaf = this_cpu_ci->info_list + index;
-		/* skip if shared_cpu_map is already populated */
-		if (!cpumask_empty(&this_leaf->shared_cpu_map))
-			continue;
+		this_leaf = per_cpu_cacheinfo_idx(cpu, index);
 
 		cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
 		for_each_online_cpu(i) {
@@ -247,7 +279,8 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 
 			if (i == cpu || !sib_cpu_ci->info_list)
 				continue;/* skip if itself or no cacheinfo */
-			sib_leaf = sib_cpu_ci->info_list + index;
+
+			sib_leaf = per_cpu_cacheinfo_idx(i, index);
 			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
 				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
 				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
@@ -263,23 +296,19 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 
 static void cache_shared_cpu_map_remove(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf, *sib_leaf;
 	unsigned int sibling, index;
 
 	for (index = 0; index < cache_leaves(cpu); index++) {
-		this_leaf = this_cpu_ci->info_list + index;
+		this_leaf = per_cpu_cacheinfo_idx(cpu, index);
 		for_each_cpu(sibling, &this_leaf->shared_cpu_map) {
-			struct cpu_cacheinfo *sib_cpu_ci;
-
-			if (sibling == cpu) /* skip itself */
-				continue;
+			struct cpu_cacheinfo *sib_cpu_ci =
+						get_cpu_cacheinfo(sibling);
 
-			sib_cpu_ci = get_cpu_cacheinfo(sibling);
-			if (!sib_cpu_ci->info_list)
-				continue;
+			if (sibling == cpu || !sib_cpu_ci->info_list)
+				continue;/* skip if itself or no cacheinfo */
 
-			sib_leaf = sib_cpu_ci->info_list + index;
+			sib_leaf = per_cpu_cacheinfo_idx(sibling, index);
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
 		}
@@ -310,17 +339,28 @@ int __weak populate_cache_leaves(unsigned int cpu)
 	return -ENOENT;
 }
 
-static int detect_cache_attributes(unsigned int cpu)
+int detect_cache_attributes(unsigned int cpu)
 {
 	int ret;
 
+	/* Since early detection of the cacheinfo is allowed via this
+	 * function and this also gets called as CPU hotplug callbacks via
+	 * cacheinfo_cpu_online, the initialisation can be skipped and only
+	 * CPU maps can be updated as the CPU online status would be update
+	 * if called via cacheinfo_cpu_online path.
+	 */
+	if (per_cpu_cacheinfo(cpu))
+		goto update_cpu_map;
+
 	if (init_cache_level(cpu) || !cache_leaves(cpu))
 		return -ENOENT;
 
 	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
-					 sizeof(struct cacheinfo), GFP_KERNEL);
-	if (per_cpu_cacheinfo(cpu) == NULL)
+					 sizeof(struct cacheinfo), GFP_ATOMIC);
+	if (per_cpu_cacheinfo(cpu) == NULL) {
+		cache_leaves(cpu) = 0;
 		return -ENOMEM;
+	}
 
 	/*
 	 * populate_cache_leaves() may completely setup the cache leaves and
@@ -329,6 +369,8 @@ static int detect_cache_attributes(unsigned int cpu)
 	ret = populate_cache_leaves(cpu);
 	if (ret)
 		goto free_ci;
+
+update_cpu_map:
 	/*
 	 * For systems using DT for cache hierarchy, fw_token
 	 * and shared_cpu_map will be set up here only if they are
@@ -614,7 +656,6 @@ static int cache_add_dev(unsigned int cpu)
 	int rc;
 	struct device *ci_dev, *parent;
 	struct cacheinfo *this_leaf;
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	const struct attribute_group **cache_groups;
 
 	rc = cpu_cache_sysfs_init(cpu);
@@ -623,7 +664,7 @@ static int cache_add_dev(unsigned int cpu)
 
 	parent = per_cpu_cache_dev(cpu);
 	for (i = 0; i < cache_leaves(cpu); i++) {
-		this_leaf = this_cpu_ci->info_list + i;
+		this_leaf = per_cpu_cacheinfo_idx(cpu, i);
 		if (this_leaf->disable_sysfs)
 			continue;
 		if (this_leaf->type == CACHE_TYPE_NOCACHE)

drivers/base/core.c

@@ -54,6 +54,7 @@ static unsigned int defer_sync_state_count = 1;
 static DEFINE_MUTEX(fwnode_link_lock);
 static bool fw_devlink_is_permissive(void);
 static bool fw_devlink_drv_reg_done;
+static bool fw_devlink_best_effort;
 
 /**
  * fwnode_link_add - Create a link between two fwnode_handles.
@@ -976,6 +977,12 @@ static void device_links_missing_supplier(struct device *dev)
 	}
 }
 
+static bool dev_is_best_effort(struct device *dev)
+{
+	return (fw_devlink_best_effort && dev->can_match) ||
+		(dev->fwnode && (dev->fwnode->flags & FWNODE_FLAG_BEST_EFFORT));
+}
+
 /**
  * device_links_check_suppliers - Check presence of supplier drivers.
  * @dev: Consumer device.
@@ -995,7 +1002,7 @@ static void device_links_missing_supplier(struct device *dev)
 int device_links_check_suppliers(struct device *dev)
 {
 	struct device_link *link;
-	int ret = 0;
+	int ret = 0, fwnode_ret = 0;
 	struct fwnode_handle *sup_fw;
 
 	/*
@@ -1008,12 +1015,17 @@ int device_links_check_suppliers(struct device *dev)
 		sup_fw = list_first_entry(&dev->fwnode->suppliers,
 					  struct fwnode_link,
 					  c_hook)->supplier;
-		dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwP\n",
-			      sup_fw);
-		mutex_unlock(&fwnode_link_lock);
-		return -EPROBE_DEFER;
+		if (!dev_is_best_effort(dev)) {
+			fwnode_ret = -EPROBE_DEFER;
+			dev_err_probe(dev, -EPROBE_DEFER,
+				    "wait for supplier %pfwP\n", sup_fw);
+		} else {
+			fwnode_ret = -EAGAIN;
+		}
 	}
 	mutex_unlock(&fwnode_link_lock);
+	if (fwnode_ret == -EPROBE_DEFER)
+		return fwnode_ret;
 
 	device_links_write_lock();
 
@@ -1023,6 +1035,14 @@ int device_links_check_suppliers(struct device *dev)
 
 		if (link->status != DL_STATE_AVAILABLE &&
 		    !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) {
+
+			if (dev_is_best_effort(dev) &&
+			    link->flags & DL_FLAG_INFERRED &&
+			    !link->supplier->can_match) {
+				ret = -EAGAIN;
+				continue;
+			}
+
 			device_links_missing_supplier(dev);
 			dev_err_probe(dev, -EPROBE_DEFER,
 				      "supplier %s not ready\n",
@@ -1035,7 +1055,8 @@ int device_links_check_suppliers(struct device *dev)
 	dev->links.status = DL_DEV_PROBING;
 
 	device_links_write_unlock();
-	return ret;
+
+	return ret ? ret : fwnode_ret;
 }
 
 /**
@@ -1300,6 +1321,18 @@ void device_links_driver_bound(struct device *dev)
 			 * save to drop the managed link completely.
 			 */
 			device_link_drop_managed(link);
+		} else if (dev_is_best_effort(dev) &&
+			   link->flags & DL_FLAG_INFERRED &&
+			   link->status != DL_STATE_CONSUMER_PROBE &&
+			   !link->supplier->can_match) {
+			/*
+			 * When dev_is_best_effort() is true, we ignore device
+			 * links to suppliers that don't have a driver.  If the
+			 * consumer device still managed to probe, there's no
+			 * point in maintaining a device link in a weird state
+			 * (consumer probed before supplier). So delete it.
+			 */
+			device_link_drop_managed(link);
 		} else {
 			WARN_ON(link->status != DL_STATE_CONSUMER_PROBE);
 			WRITE_ONCE(link->status, DL_STATE_ACTIVE);
@@ -1592,7 +1625,7 @@ static int __init fw_devlink_setup(char *arg)
 }
 early_param("fw_devlink", fw_devlink_setup);
 
-static bool fw_devlink_strict;
+static bool fw_devlink_strict = true;
 static int __init fw_devlink_strict_setup(char *arg)
 {
 	return strtobool(arg, &fw_devlink_strict);
@@ -1666,6 +1699,62 @@ void fw_devlink_drivers_done(void)
 	device_links_write_unlock();
 }
 
+/**
+ * wait_for_init_devices_probe - Try to probe any device needed for init
+ *
+ * Some devices might need to be probed and bound successfully before the kernel
+ * boot sequence can finish and move on to init/userspace. For example, a
+ * network interface might need to be bound to be able to mount a NFS rootfs.
+ *
+ * With fw_devlink=on by default, some of these devices might be blocked from
+ * probing because they are waiting on a optional supplier that doesn't have a
+ * driver. While fw_devlink will eventually identify such devices and unblock
+ * the probing automatically, it might be too late by the time it unblocks the
+ * probing of devices. For example, the IP4 autoconfig might timeout before
+ * fw_devlink unblocks probing of the network interface.
+ *
+ * This function is available to temporarily try and probe all devices that have
+ * a driver even if some of their suppliers haven't been added or don't have
+ * drivers.
+ *
+ * The drivers can then decide which of the suppliers are optional vs mandatory
+ * and probe the device if possible. By the time this function returns, all such
+ * "best effort" probes are guaranteed to be completed. If a device successfully
+ * probes in this mode, we delete all fw_devlink discovered dependencies of that
+ * device where the supplier hasn't yet probed successfully because they have to
+ * be optional dependencies.
+ *
+ * Any devices that didn't successfully probe go back to being treated as if
+ * this function was never called.
+ *
+ * This also means that some devices that aren't needed for init and could have
+ * waited for their optional supplier to probe (when the supplier's module is
+ * loaded later on) would end up probing prematurely with limited functionality.
+ * So call this function only when boot would fail without it.
+ */
+void __init wait_for_init_devices_probe(void)
+{
+	if (!fw_devlink_flags || fw_devlink_is_permissive())
+		return;
+
+	/*
+	 * Wait for all ongoing probes to finish so that the "best effort" is
+	 * only applied to devices that can't probe otherwise.
+	 */
+	wait_for_device_probe();
+
+	pr_info("Trying to probe devices needed for running init ...\n");
+	fw_devlink_best_effort = true;
+	driver_deferred_probe_trigger();
+
+	/*
+	 * Wait for all "best effort" probes to finish before going back to
+	 * normal enforcement.
+	 */
+	wait_for_device_probe();
+	fw_devlink_best_effort = false;
+}
+
 static void fw_devlink_unblock_consumers(struct device *dev)
 {
 	struct device_link *link;
@@ -3843,6 +3932,26 @@ struct device *device_find_child_by_name(struct device *parent,
 }
 EXPORT_SYMBOL_GPL(device_find_child_by_name);
 
+static int match_any(struct device *dev, void *unused)
+{
+	return 1;
+}
+
+/**
+ * device_find_any_child - device iterator for locating a child device, if any.
+ * @parent: parent struct device
+ *
+ * This is similar to the device_find_child() function above, but it
+ * returns a reference to a child device, if any.
+ *
+ * NOTE: you will need to drop the reference with put_device() after use.
+ */
+struct device *device_find_any_child(struct device *parent)
+{
+	return device_find_child(parent, NULL, match_any);
+}
+EXPORT_SYMBOL_GPL(device_find_any_child);
+
 int __init devices_init(void)
 {
 	devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL);

drivers/base/dd.c

@@ -172,7 +172,7 @@ static bool driver_deferred_probe_enable;
  * changes in the midst of a probe, then deferred processing should be triggered
  * again.
  */
-static void driver_deferred_probe_trigger(void)
+void driver_deferred_probe_trigger(void)
 {
 	if (!driver_deferred_probe_enable)
 		return;
@@ -256,7 +256,12 @@ static int deferred_devs_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(deferred_devs);
 
+#ifdef CONFIG_MODULES
+int driver_deferred_probe_timeout = 10;
+#else
 int driver_deferred_probe_timeout;
+#endif
+
 EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout);
 
 static int __init deferred_probe_timeout_setup(char *str)
@@ -269,42 +274,12 @@ static int __init deferred_probe_timeout_setup(char *str)
 }
 __setup("deferred_probe_timeout=", deferred_probe_timeout_setup);
 
-/**
- * driver_deferred_probe_check_state() - Check deferred probe state
- * @dev: device to check
- *
- * Return:
- * * -ENODEV if initcalls have completed and modules are disabled.
- * * -ETIMEDOUT if the deferred probe timeout was set and has expired
- *   and modules are enabled.
- * * -EPROBE_DEFER in other cases.
- *
- * Drivers or subsystems can opt-in to calling this function instead of directly
- * returning -EPROBE_DEFER.
- */
-int driver_deferred_probe_check_state(struct device *dev)
-{
-	if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) {
-		dev_warn(dev, "ignoring dependency for device, assuming no driver\n");
-		return -ENODEV;
-	}
-
-	if (!driver_deferred_probe_timeout && initcalls_done) {
-		dev_warn(dev, "deferred probe timeout, ignoring dependency\n");
-		return -ETIMEDOUT;
-	}
-
-	return -EPROBE_DEFER;
-}
-EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state);
-
 static void deferred_probe_timeout_work_func(struct work_struct *work)
 {
 	struct device_private *p;
 
 	fw_devlink_drivers_done();
 
-	driver_deferred_probe_timeout = 0;
 	driver_deferred_probe_trigger();
 	flush_work(&deferred_probe_work);
 
@@ -580,7 +555,7 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 {
 	bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) &&
 			   !drv->suppress_bind_attrs;
-	int ret;
+	int ret, link_ret;
 
 	if (defer_all_probes) {
 		/*
@@ -592,9 +567,9 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 		return -EPROBE_DEFER;
 	}
 
-	ret = device_links_check_suppliers(dev);
-	if (ret)
-		return ret;
+	link_ret = device_links_check_suppliers(dev);
+	if (link_ret == -EPROBE_DEFER)
+		return link_ret;
 
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
 		 drv->bus->name, __func__, drv->name, dev_name(dev));
@@ -633,6 +608,15 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 
 	ret = call_driver_probe(dev, drv);
 	if (ret) {
+		/*
+		 * If fw_devlink_best_effort is active (denoted by -EAGAIN), the
+		 * device might actually probe properly once some of its missing
+		 * suppliers have probed. So, treat this as if the driver
+		 * returned -EPROBE_DEFER.
+		 */
+		if (link_ret == -EAGAIN)
+			ret = -EPROBE_DEFER;
+
 		/*
 		 * Return probe errors as positive values so that the callers
 		 * can distinguish them from other errors.
@@ -1115,6 +1099,7 @@ static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie)
 static int __driver_attach(struct device *dev, void *data)
 {
 	struct device_driver *drv = data;
+	bool async = false;
 	int ret;
 
 	/*
@@ -1153,9 +1138,11 @@ static int __driver_attach(struct device *dev, void *data)
 		if (!dev->driver && !dev->p->async_driver) {
 			get_device(dev);
 			dev->p->async_driver = drv;
-			async_schedule_dev(__driver_attach_async_helper, dev);
+			async = true;
 		}
 		device_unlock(dev);
+		if (async)
+			async_schedule_dev(__driver_attach_async_helper, dev);
 		return 0;
 	}
 

drivers/base/devtmpfs.c

@@ -482,6 +482,7 @@ int __init devtmpfs_init(void)
 	if (err) {
 		printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
 		unregister_filesystem(&dev_fs_type);
+		thread = NULL;
 		return err;
 	}
 

drivers/base/firmware_loader/main.c

@@ -435,11 +435,11 @@ static int fw_decompress_xz_pages(struct device *dev, struct fw_priv *fw_priv,
 
 		/* decompress onto the new allocated page */
 		page = fw_priv->pages[fw_priv->nr_pages - 1];
-		xz_buf.out = kmap(page);
+		xz_buf.out = kmap_local_page(page);
 		xz_buf.out_pos = 0;
 		xz_buf.out_size = PAGE_SIZE;
 		xz_ret = xz_dec_run(xz_dec, &xz_buf);
-		kunmap(page);
+		kunmap_local(xz_buf.out);
 		fw_priv->size += xz_buf.out_pos;
 		/* partial decompression means either end or error */
 		if (xz_buf.out_pos != PAGE_SIZE)

drivers/base/firmware_loader/sysfs.c

@@ -242,19 +242,17 @@ static void firmware_rw(struct fw_priv *fw_priv, char *buffer,
 			loff_t offset, size_t count, bool read)
 {
 	while (count) {
-		void *page_data;
 		int page_nr = offset >> PAGE_SHIFT;
 		int page_ofs = offset & (PAGE_SIZE - 1);
 		int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count);
 
-		page_data = kmap(fw_priv->pages[page_nr]);
-
 		if (read)
-			memcpy(buffer, page_data + page_ofs, page_cnt);
+			memcpy_from_page(buffer, fw_priv->pages[page_nr],
+					 page_ofs, page_cnt);
 		else
-			memcpy(page_data + page_ofs, buffer, page_cnt);
+			memcpy_to_page(fw_priv->pages[page_nr], page_ofs,
+				       buffer, page_cnt);
 
-		kunmap(fw_priv->pages[page_nr]);
 		buffer += page_cnt;
 		offset += page_cnt;
 		count -= page_cnt;

drivers/base/node.c

@@ -45,7 +45,7 @@ static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpumap, 0);
+static BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES);
 
 static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 				   struct bin_attribute *attr, char *buf,
@@ -66,7 +66,7 @@ static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpulist, 0);
+static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
 
 /**
  * struct node_access_nodes - Access class device to hold user visible

drivers/base/power/domain.c

@@ -2733,7 +2733,7 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 		mutex_unlock(&gpd_list_lock);
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		return driver_deferred_probe_check_state(base_dev);
+		return -ENODEV;
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);

drivers/base/topology.c

@@ -62,47 +62,47 @@ define_id_show_func(ppin, "0x%llx");
 static DEVICE_ATTR_ADMIN_RO(ppin);
 
 define_siblings_read_func(thread_siblings, sibling_cpumask);
-static BIN_ATTR_RO(thread_siblings, 0);
-static BIN_ATTR_RO(thread_siblings_list, 0);
+static BIN_ATTR_RO(thread_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(thread_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_cpus, sibling_cpumask);
-static BIN_ATTR_RO(core_cpus, 0);
-static BIN_ATTR_RO(core_cpus_list, 0);
+static BIN_ATTR_RO(core_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_siblings, core_cpumask);
-static BIN_ATTR_RO(core_siblings, 0);
-static BIN_ATTR_RO(core_siblings_list, 0);
+static BIN_ATTR_RO(core_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 #ifdef TOPOLOGY_CLUSTER_SYSFS
 define_siblings_read_func(cluster_cpus, cluster_cpumask);
-static BIN_ATTR_RO(cluster_cpus, 0);
-static BIN_ATTR_RO(cluster_cpus_list, 0);
+static BIN_ATTR_RO(cluster_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(cluster_cpus_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 #ifdef TOPOLOGY_DIE_SYSFS
 define_siblings_read_func(die_cpus, die_cpumask);
-static BIN_ATTR_RO(die_cpus, 0);
-static BIN_ATTR_RO(die_cpus_list, 0);
+static BIN_ATTR_RO(die_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(die_cpus_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 define_siblings_read_func(package_cpus, core_cpumask);
-static BIN_ATTR_RO(package_cpus, 0);
-static BIN_ATTR_RO(package_cpus_list, 0);
+static BIN_ATTR_RO(package_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(package_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 #ifdef TOPOLOGY_BOOK_SYSFS
 define_id_show_func(book_id, "%d");
 static DEVICE_ATTR_RO(book_id);
 define_siblings_read_func(book_siblings, book_cpumask);
-static BIN_ATTR_RO(book_siblings, 0);
-static BIN_ATTR_RO(book_siblings_list, 0);
+static BIN_ATTR_RO(book_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(book_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 #ifdef TOPOLOGY_DRAWER_SYSFS
 define_id_show_func(drawer_id, "%d");
 static DEVICE_ATTR_RO(drawer_id);
 define_siblings_read_func(drawer_siblings, drawer_cpumask);
-static BIN_ATTR_RO(drawer_siblings, 0);
-static BIN_ATTR_RO(drawer_siblings_list, 0);
+static BIN_ATTR_RO(drawer_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(drawer_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 static struct bin_attribute *bin_attrs[] = {

drivers/iommu/of_iommu.c

@@ -40,7 +40,7 @@ static int of_iommu_xlate(struct device *dev,
 	 * a proper probe-ordering dependency mechanism in future.
 	 */
 	if (!ops)
-		return driver_deferred_probe_check_state(dev);
+		return -ENODEV;
 
 	if (!try_module_get(ops->owner))
 		return -ENODEV;

drivers/net/mdio/fwnode_mdio.c

@@ -47,9 +47,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
 	 * just fall back to poll mode
 	 */
 	if (rc == -EPROBE_DEFER)
-		rc = driver_deferred_probe_check_state(&phy->mdio.dev);
-	if (rc == -EPROBE_DEFER)
-		return rc;
+		rc = -ENODEV;
 
 	if (rc > 0) {
 		phy->irq = rc;

drivers/of/base.c

@@ -1919,6 +1919,8 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align))
 			of_property_read_string(of_aliases, "stdout", &name);
 		if (name)
 			of_stdout = of_find_node_opts_by_path(name, &of_stdout_options);
+		if (of_stdout)
+			of_stdout->fwnode.flags |= FWNODE_FLAG_BEST_EFFORT;
 	}
 
 	if (!of_aliases)

drivers/pinctrl/devicetree.c

@@ -129,7 +129,7 @@ static int dt_to_map_one_config(struct pinctrl *p,
 		np_pctldev = of_get_next_parent(np_pctldev);
 		if (!np_pctldev || of_node_is_root(np_pctldev)) {
 			of_node_put(np_pctldev);
-			ret = driver_deferred_probe_check_state(p->dev);
+			ret = -ENODEV;
 			/* keep deferring if modules are enabled */
 			if (IS_ENABLED(CONFIG_MODULES) && !allow_default && ret < 0)
 				ret = -EPROBE_DEFER;

drivers/spi/spi.c

@@ -2687,11 +2687,6 @@ int spi_slave_abort(struct spi_device *spi)
 }
 EXPORT_SYMBOL_GPL(spi_slave_abort);
 
-static int match_true(struct device *dev, void *data)
-{
-	return 1;
-}
-
 static ssize_t slave_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
@@ -2699,7 +2694,7 @@ static ssize_t slave_show(struct device *dev, struct device_attribute *attr,
 						   dev);
 	struct device *child;
 
-	child = device_find_child(&ctlr->dev, NULL, match_true);
+	child = device_find_any_child(&ctlr->dev);
 	return sprintf(buf, "%s\n",
 		       child ? to_spi_device(child)->modalias : NULL);
 }
@@ -2718,7 +2713,7 @@ static ssize_t slave_store(struct device *dev, struct device_attribute *attr,
 	if (rc != 1 || !name[0])
 		return -EINVAL;
 
-	child = device_find_child(&ctlr->dev, NULL, match_true);
+	child = device_find_any_child(&ctlr->dev);
 	if (child) {
 		/* Remove registered slave */
 		device_unregister(child);

fs/kernfs/dir.c

@@ -1343,14 +1343,17 @@ static void __kernfs_remove(struct kernfs_node *kn)
 {
 	struct kernfs_node *pos;
 
+	/* Short-circuit if non-root @kn has already finished removal. */
+	if (!kn)
+		return;
+
 	lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem);
 
 	/*
-	 * Short-circuit if non-root @kn has already finished removal.
 	 * This is for kernfs_remove_self() which plays with active ref
 	 * after removal.
 	 */
-	if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
+	if (kn->parent && RB_EMPTY_NODE(&kn->rb))
 		return;
 
 	pr_debug("kernfs %s: removing\n", kn->name);

fs/kernfs/kernfs-internal.h

@@ -164,4 +164,8 @@ void kernfs_drain_open_files(struct kernfs_node *kn);
  */
 extern const struct inode_operations kernfs_symlink_iops;
 
+/*
+ * kernfs locks
+ */
+extern struct kernfs_global_locks *kernfs_locks;
 #endif	/* __KERNFS_INTERNAL_H */

fs/kernfs/mount.c

@@ -20,6 +20,7 @@
 #include "kernfs-internal.h"
 
 struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
+struct kernfs_global_locks *kernfs_locks;
 
 static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 {
@@ -387,6 +388,22 @@ void kernfs_kill_sb(struct super_block *sb)
 	kfree(info);
 }
 
+static void __init kernfs_mutex_init(void)
+{
+	int count;
+
+	for (count = 0; count < NR_KERNFS_LOCKS; count++)
+		mutex_init(&kernfs_locks->open_file_mutex[count]);
+}
+
+static void __init kernfs_lock_init(void)
+{
+	kernfs_locks = kmalloc(sizeof(struct kernfs_global_locks), GFP_KERNEL);
+	WARN_ON(!kernfs_locks);
+
+	kernfs_mutex_init();
+}
+
 void __init kernfs_init(void)
 {
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
@@ -397,4 +414,6 @@ void __init kernfs_init(void)
 	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",
 					      sizeof(struct kernfs_iattrs),
 					      0, SLAB_PANIC, NULL);
+
+	kernfs_lock_init();
 }

include/linux/acpi.h

@@ -1431,7 +1431,6 @@ int find_acpi_cpu_topology(unsigned int cpu, int level);
 int find_acpi_cpu_topology_cluster(unsigned int cpu);
 int find_acpi_cpu_topology_package(unsigned int cpu);
 int find_acpi_cpu_topology_hetero_id(unsigned int cpu);
-int find_acpi_cpu_cache_topology(unsigned int cpu, int level);
 #else
 static inline int acpi_pptt_cpu_is_thread(unsigned int cpu)
 {
@@ -1453,10 +1452,6 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
 {
 	return -EINVAL;
 }
-static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
-{
-	return -EINVAL;
-}
 #endif
 
 #ifdef CONFIG_ACPI_PCC

include/linux/arch_topology.h

@@ -68,7 +68,6 @@ struct cpu_topology {
 	int core_id;
 	int cluster_id;
 	int package_id;
-	int llc_id;
 	cpumask_t thread_sibling;
 	cpumask_t core_sibling;
 	cpumask_t cluster_sibling;

include/linux/cacheinfo.h

@@ -82,6 +82,9 @@ struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
 int init_cache_level(unsigned int cpu);
 int populate_cache_leaves(unsigned int cpu);
 int cache_setup_acpi(unsigned int cpu);
+bool last_level_cache_is_valid(unsigned int cpu);
+bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y);
+int detect_cache_attributes(unsigned int cpu);
 #ifndef CONFIG_ACPI_PPTT
 /*
  * acpi_find_last_cache_level is only called on ACPI enabled

include/linux/cpumask.h

@@ -1071,4 +1071,22 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
 	[0] =  1UL							\
 } }
 
+/*
+ * Provide a valid theoretical max size for cpumap and cpulist sysfs files
+ * to avoid breaking userspace which may allocate a buffer based on the size
+ * reported by e.g. fstat.
+ *
+ * for cpumap NR_CPUS * 9/32 - 1 should be an exact length.
+ *
+ * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up
+ * to 2 orders of magnitude larger than 8192. And then we divide by 2 to
+ * cover a worst-case of every other cpu being on one of two nodes for a
+ * very large NR_CPUS.
+ *
+ *  Use PAGE_SIZE as a minimum for smaller configurations.
+ */
+#define CPUMAP_FILE_MAX_BYTES  ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \
+					? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE)
+#define CPULIST_FILE_MAX_BYTES  (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE)
+
 #endif /* __LINUX_CPUMASK_H */

include/linux/device.h

@@ -905,6 +905,8 @@ struct device *device_find_child(struct device *dev, void *data,
 				 int (*match)(struct device *dev, void *data));
 struct device *device_find_child_by_name(struct device *parent,
 					 const char *name);
+struct device *device_find_any_child(struct device *parent);
+
 int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
 		enum dpm_order dpm_order);

include/linux/device/driver.h

@@ -129,6 +129,7 @@ extern struct device_driver *driver_find(const char *name,
 					 struct bus_type *bus);
 extern int driver_probe_done(void);
 extern void wait_for_device_probe(void);
+void __init wait_for_init_devices_probe(void);
 
 /* sysfs interface for exporting driver attributes */
 
@@ -241,7 +242,6 @@ driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev)
 
 extern int driver_deferred_probe_timeout;
 void driver_deferred_probe_add(struct device *dev);
-int driver_deferred_probe_check_state(struct device *dev);
 void driver_init(void);
 
 /**

include/linux/firmware/trusted_foundations.h

@@ -71,12 +71,16 @@ static inline void register_trusted_foundations(
 
 static inline void of_register_trusted_foundations(void)
 {
+	struct device_node *np = of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations");
+
+	if (!np)
+		return;
+	of_node_put(np);
 	/*
 	 * If we find the target should enable TF but does not support it,
 	 * fail as the system won't be able to do much anyway
 	 */
-	if (of_find_compatible_node(NULL, NULL, "tlm,trusted-foundations"))
-		register_trusted_foundations(NULL);
+	register_trusted_foundations(NULL);
 }
 
 static inline bool trusted_foundations_registered(void)

include/linux/fwnode.h

@@ -27,11 +27,15 @@ struct device;
  *			     driver needs its child devices to be bound with
  *			     their respective drivers as soon as they are
  *			     added.
+ * BEST_EFFORT: The fwnode/device needs to probe early and might be missing some
+ *		suppliers. Only enforce ordering with suppliers that have
+ *		drivers.
  */
 #define FWNODE_FLAG_LINKS_ADDED			BIT(0)
 #define FWNODE_FLAG_NOT_DEVICE			BIT(1)
 #define FWNODE_FLAG_INITIALIZED			BIT(2)
 #define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD	BIT(3)
+#define FWNODE_FLAG_BEST_EFFORT			BIT(4)
 
 struct fwnode_handle {
 	struct fwnode_handle *secondary;

include/linux/kernfs.h

@@ -18,6 +18,7 @@
 #include <linux/uidgid.h>
 #include <linux/wait.h>
 #include <linux/rwsem.h>
+#include <linux/cache.h>
 
 struct file;
 struct dentry;
@@ -34,6 +35,62 @@ struct kernfs_fs_context;
 struct kernfs_open_node;
 struct kernfs_iattrs;
 
+/*
+ * NR_KERNFS_LOCK_BITS determines size (NR_KERNFS_LOCKS) of hash
+ * table of locks.
+ * Having a small hash table would impact scalability, since
+ * more and more kernfs_node objects will end up using same lock
+ * and having a very large hash table would waste memory.
+ *
+ * At the moment size of hash table of locks is being set based on
+ * the number of CPUs as follows:
+ *
+ * NR_CPU      NR_KERNFS_LOCK_BITS      NR_KERNFS_LOCKS
+ *   1                  1                       2
+ *  2-3                 2                       4
+ *  4-7                 4                       16
+ *  8-15                6                       64
+ *  16-31               8                       256
+ *  32 and more         10                      1024
+ *
+ * The above relation between NR_CPU and number of locks is based
+ * on some internal experimentation which involved booting qemu
+ * with different values of smp, performing some sysfs operations
+ * on all CPUs and observing how increase in number of locks impacts
+ * completion time of these sysfs operations on each CPU.
+ */
+#ifdef CONFIG_SMP
+#define NR_KERNFS_LOCK_BITS (2 * (ilog2(NR_CPUS < 32 ? NR_CPUS : 32)))
+#else
+#define NR_KERNFS_LOCK_BITS     1
+#endif
+
+#define NR_KERNFS_LOCKS     (1 << NR_KERNFS_LOCK_BITS)
+
+/*
+ * There's one kernfs_open_file for each open file and one kernfs_open_node
+ * for each kernfs_node with one or more open files.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * kernfs_open_file.
+ *
+ * kernfs_open_files are chained at kernfs_open_node->files, which is
+ * protected by kernfs_global_locks.open_file_mutex[i].
+ *
+ * To reduce possible contention in sysfs access, arising due to single
+ * locks, use an array of locks (e.g. open_file_mutex) and use kernfs_node
+ * object address as hash keys to get the index of these locks.
+ *
+ * Hashed mutexes are safe to use here because operations using these don't
+ * rely on global exclusion.
+ *
+ * In future we intend to replace other global locks with hashed ones as well.
+ * kernfs_global_locks acts as a holder for all such hash tables.
+ */
+struct kernfs_global_locks {
+	struct mutex open_file_mutex[NR_KERNFS_LOCKS];
+};
+
 enum kernfs_node_type {
 	KERNFS_DIR		= 0x0001,
 	KERNFS_FILE		= 0x0002,
@@ -114,7 +171,7 @@ struct kernfs_elem_symlink {
 
 struct kernfs_elem_attr {
 	const struct kernfs_ops	*ops;
-	struct kernfs_open_node	*open;
+	struct kernfs_open_node __rcu	*open;
 	loff_t			size;
 	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
 };

lib/Kconfig.debug

@@ -1560,7 +1560,7 @@ config DEBUG_KOBJECT_RELEASE
 	help
 	  kobjects are reference counted objects.  This means that their
 	  last reference count put is not predictable, and the kobject can
-	  live on past the point at which a driver decides to drop it's
+	  live on past the point at which a driver decides to drop its
 	  initial reference to the kobject gained on allocation.  An
 	  example of this would be a struct device which has just been
 	  unregistered.

net/ipv4/ipconfig.c

@@ -1434,6 +1434,7 @@ __be32 __init root_nfs_parse_addr(char *name)
 static int __init wait_for_devices(void)
 {
 	int i;
+	bool try_init_devs = true;
 
 	for (i = 0; i < DEVICE_WAIT_MAX; i++) {
 		struct net_device *dev;
@@ -1452,6 +1453,11 @@ static int __init wait_for_devices(void)
 		rtnl_unlock();
 		if (found)
 			return 0;
+		if (try_init_devs &&
+		    (ROOT_DEV == Root_NFS || ROOT_DEV == Root_CIFS)) {
+			try_init_devs = false;
+			wait_for_init_devices_probe();
+		}
 		ssleep(1);
 	}
 	return -ENODEV;