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()
  ...

9 files changed, 92 insertions, 10 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7e7a33b6c8d7..f6d4539c3895 100644
--- a/include/linux/acpi.h
+++ b/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
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 58cbe18d825c..a07b510e7dc5 100644
--- a/include/linux/arch_topology.h
+++ b/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;
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 4ff37cb763ae..00b7a6ae8617 100644
--- a/include/linux/cacheinfo.h
+++ b/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
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index fe29ac7cc469..4592d0845941 100644
--- a/include/linux/cpumask.h
+++ b/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 */
diff --git a/include/linux/device.h b/include/linux/device.h
index dc941997795c..424b55df0272 100644
--- a/include/linux/device.h
+++ b/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);
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index 700453017e1c..7acaabde5396 100644
--- a/include/linux/device/driver.h
+++ b/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);
 
 /**
diff --git a/include/linux/firmware/trusted_foundations.h b/include/linux/firmware/trusted_foundations.h
index be5984bda592..931b6c5c72df 100644
--- a/include/linux/firmware/trusted_foundations.h
+++ b/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)
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 9a81c4410b9f..89b9bdfca925 100644
--- a/include/linux/fwnode.h
+++ b/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;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index e2ae15a6225e..367044d7708c 100644
--- a/include/linux/kernfs.h
+++ b/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() */
 };