diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-04 11:31:20 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-04 11:31:20 -0700 |
commit | cfeafd94668910334a77c9437a18212baf9f5610 (patch) | |
tree | b863f4f9688ac141f65b62a69addd0f9bfcc2126 /drivers/base | |
parent | 228dfe98a313f6b6bff5da8b2c5e650e297ebf1a (diff) | |
parent | 273aaa24369cb8d0f246bb16f7122b91a1ef5188 (diff) | |
download | linux-cfeafd94668910334a77c9437a18212baf9f5610.tar.gz linux-cfeafd94668910334a77c9437a18212baf9f5610.tar.bz2 linux-cfeafd94668910334a77c9437a18212baf9f5610.zip |
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()
...
Diffstat (limited to 'drivers/base')
-rw-r--r-- | drivers/base/arch_topology.c | 100 | ||||
-rw-r--r-- | drivers/base/base.h | 1 | ||||
-rw-r--r-- | drivers/base/cacheinfo.c | 145 | ||||
-rw-r--r-- | drivers/base/core.c | 123 | ||||
-rw-r--r-- | drivers/base/dd.c | 59 | ||||
-rw-r--r-- | drivers/base/devtmpfs.c | 1 | ||||
-rw-r--r-- | drivers/base/firmware_loader/main.c | 4 | ||||
-rw-r--r-- | drivers/base/firmware_loader/sysfs.c | 10 | ||||
-rw-r--r-- | drivers/base/node.c | 4 | ||||
-rw-r--r-- | drivers/base/power/domain.c | 2 | ||||
-rw-r--r-- | drivers/base/topology.c | 32 |
11 files changed, 334 insertions, 147 deletions
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 579c851a2bd7..0424b59b695e 100644 --- a/drivers/base/arch_topology.c +++ b/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 diff --git a/drivers/base/base.h b/drivers/base/base.h index ab71403d102f..b3a43a164dcd 100644 --- a/drivers/base/base.h +++ b/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; diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index dad296229161..4b5cd08c5a65 100644 --- a/drivers/base/cacheinfo.c +++ b/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) diff --git a/drivers/base/core.c b/drivers/base/core.c index 460d6f163e41..753e7cca0f40 100644 --- a/drivers/base/core.c +++ b/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); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 11b0fb6414d3..70f79fc71539 100644 --- a/drivers/base/dd.c +++ b/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)); @@ -634,6 +609,15 @@ re_probe: 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; } diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 8a3ddbae3b70..e4bffeabf344 100644 --- a/drivers/base/devtmpfs.c +++ b/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; } diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index ac3f34e80194..7c3590fd97c2 100644 --- a/drivers/base/firmware_loader/main.c +++ b/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) diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c index 5b0b85b70b6f..77bad32c481a 100644 --- a/drivers/base/firmware_loader/sysfs.c +++ b/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; diff --git a/drivers/base/node.c b/drivers/base/node.c index 0ac6376ef7a1..eb0f43784c2b 100644 --- a/drivers/base/node.c +++ b/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 diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 55a10e6d4e2a..5a2e0232862e 100644 --- a/drivers/base/power/domain.c +++ b/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); diff --git a/drivers/base/topology.c b/drivers/base/topology.c index ac6ad9ab67f9..89f98be5c5b9 100644 --- a/drivers/base/topology.c +++ b/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[] = { |