diff options
Diffstat (limited to 'kernel')
50 files changed, 2213 insertions, 1653 deletions
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index a5c9359d516f..ede31601a363 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -7,4 +7,5 @@ obj-$(CONFIG_CGROUP_RDMA) += rdma.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CPUSETS_V1) += cpuset-v1.o obj-$(CONFIG_CGROUP_MISC) += misc.o +obj-$(CONFIG_CGROUP_DMEM) += dmem.o obj-$(CONFIG_CGROUP_DEBUG) += debug.o diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c new file mode 100644 index 000000000000..fbe34299673d --- /dev/null +++ b/kernel/cgroup/dmem.c @@ -0,0 +1,857 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2023-2024 Intel Corporation (Maarten Lankhorst <dev@lankhorst.se>) + * Copyright 2024 Red Hat (Maxime Ripard <mripard@kernel.org>) + * Partially based on the rdma and misc controllers, which bear the following copyrights: + * + * Copyright 2020 Google LLC + * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> + */ + +#include <linux/cgroup.h> +#include <linux/cgroup_dmem.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/page_counter.h> +#include <linux/parser.h> +#include <linux/slab.h> + +struct dmem_cgroup_region { + /** + * @ref: References keeping the region alive. + * Keeps the region reference alive after a succesful RCU lookup. + */ + struct kref ref; + + /** @rcu: RCU head for freeing */ + struct rcu_head rcu; + + /** + * @region_node: Linked into &dmem_cgroup_regions list. + * Protected by RCU and global spinlock. + */ + struct list_head region_node; + + /** + * @pools: List of pools linked to this region. + * Protected by global spinlock only + */ + struct list_head pools; + + /** @size: Size of region, in bytes */ + u64 size; + + /** @name: Name describing the node, set by dmem_cgroup_register_region */ + char *name; + + /** + * @unregistered: Whether the region is unregistered by its caller. + * No new pools should be added to the region afterwards. + */ + bool unregistered; +}; + +struct dmemcg_state { + struct cgroup_subsys_state css; + + struct list_head pools; +}; + +struct dmem_cgroup_pool_state { + struct dmem_cgroup_region *region; + struct dmemcg_state *cs; + + /* css node, RCU protected against region teardown */ + struct list_head css_node; + + /* dev node, no RCU protection required */ + struct list_head region_node; + + struct rcu_head rcu; + + struct page_counter cnt; + + bool inited; +}; + +/* + * 3 operations require locking protection: + * - Registering and unregistering region to/from list, requires global lock. + * - Adding a dmem_cgroup_pool_state to a CSS, removing when CSS is freed. + * - Adding a dmem_cgroup_pool_state to a region list. + * + * Since for the most common operations RCU provides enough protection, I + * do not think more granular locking makes sense. Most protection is offered + * by RCU and the lockless operating page_counter. + */ +static DEFINE_SPINLOCK(dmemcg_lock); +static LIST_HEAD(dmem_cgroup_regions); + +static inline struct dmemcg_state * +css_to_dmemcs(struct cgroup_subsys_state *css) +{ + return container_of(css, struct dmemcg_state, css); +} + +static inline struct dmemcg_state *get_current_dmemcs(void) +{ + return css_to_dmemcs(task_get_css(current, dmem_cgrp_id)); +} + +static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg) +{ + return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL; +} + +static void free_cg_pool(struct dmem_cgroup_pool_state *pool) +{ + list_del(&pool->region_node); + kfree(pool); +} + +static void +set_resource_min(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_min(&pool->cnt, val); +} + +static void +set_resource_low(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_low(&pool->cnt, val); +} + +static void +set_resource_max(struct dmem_cgroup_pool_state *pool, u64 val) +{ + page_counter_set_max(&pool->cnt, val); +} + +static u64 get_resource_low(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.low) : 0; +} + +static u64 get_resource_min(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.min) : 0; +} + +static u64 get_resource_max(struct dmem_cgroup_pool_state *pool) +{ + return pool ? READ_ONCE(pool->cnt.max) : PAGE_COUNTER_MAX; +} + +static u64 get_resource_current(struct dmem_cgroup_pool_state *pool) +{ + return pool ? page_counter_read(&pool->cnt) : 0; +} + +static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool) +{ + set_resource_min(rpool, 0); + set_resource_low(rpool, 0); + set_resource_max(rpool, PAGE_COUNTER_MAX); +} + +static void dmemcs_offline(struct cgroup_subsys_state *css) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(css); + struct dmem_cgroup_pool_state *pool; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &dmemcs->pools, css_node) + reset_all_resource_limits(pool); + rcu_read_unlock(); +} + +static void dmemcs_free(struct cgroup_subsys_state *css) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(css); + struct dmem_cgroup_pool_state *pool, *next; + + spin_lock(&dmemcg_lock); + list_for_each_entry_safe(pool, next, &dmemcs->pools, css_node) { + /* + *The pool is dead and all references are 0, + * no need for RCU protection with list_del_rcu or freeing. + */ + list_del(&pool->css_node); + free_cg_pool(pool); + } + spin_unlock(&dmemcg_lock); + + kfree(dmemcs); +} + +static struct cgroup_subsys_state * +dmemcs_alloc(struct cgroup_subsys_state *parent_css) +{ + struct dmemcg_state *dmemcs = kzalloc(sizeof(*dmemcs), GFP_KERNEL); + if (!dmemcs) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&dmemcs->pools); + return &dmemcs->css; +} + +static struct dmem_cgroup_pool_state * +find_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region) +{ + struct dmem_cgroup_pool_state *pool; + + list_for_each_entry_rcu(pool, &dmemcs->pools, css_node, spin_is_locked(&dmemcg_lock)) + if (pool->region == region) + return pool; + + return NULL; +} + +static struct dmem_cgroup_pool_state *pool_parent(struct dmem_cgroup_pool_state *pool) +{ + if (!pool->cnt.parent) + return NULL; + + return container_of(pool->cnt.parent, typeof(*pool), cnt); +} + +static void +dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool) +{ + struct page_counter *climit; + struct cgroup_subsys_state *css, *next_css; + struct dmemcg_state *dmemcg_iter; + struct dmem_cgroup_pool_state *pool, *parent_pool; + bool found_descendant; + + climit = &limit_pool->cnt; + + rcu_read_lock(); + parent_pool = pool = limit_pool; + css = &limit_pool->cs->css; + + /* + * This logic is roughly equivalent to css_foreach_descendant_pre, + * except we also track the parent pool to find out which pool we need + * to calculate protection values for. + * + * We can stop the traversal once we find test_pool among the + * descendants since we don't really care about any others. + */ + while (pool != test_pool) { + next_css = css_next_child(NULL, css); + if (next_css) { + parent_pool = pool; + } else { + while (css != &limit_pool->cs->css) { + next_css = css_next_child(css, css->parent); + if (next_css) + break; + css = css->parent; + parent_pool = pool_parent(parent_pool); + } + /* + * We can only hit this when test_pool is not a + * descendant of limit_pool. + */ + if (WARN_ON_ONCE(css == &limit_pool->cs->css)) + break; + } + css = next_css; + + found_descendant = false; + dmemcg_iter = container_of(css, struct dmemcg_state, css); + + list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { + if (pool_parent(pool) == parent_pool) { + found_descendant = true; + break; + } + } + if (!found_descendant) + continue; + + page_counter_calculate_protection( + climit, &pool->cnt, true); + } + rcu_read_unlock(); +} + +/** + * dmem_cgroup_state_evict_valuable() - Check if we should evict from test_pool + * @limit_pool: The pool for which we hit limits + * @test_pool: The pool for which to test + * @ignore_low: Whether we have to respect low watermarks. + * @ret_hit_low: Pointer to whether it makes sense to consider low watermark. + * + * This function returns true if we can evict from @test_pool, false if not. + * When returning false and @ignore_low is false, @ret_hit_low may + * be set to true to indicate this function can be retried with @ignore_low + * set to true. + * + * Return: bool + */ +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low) +{ + struct dmem_cgroup_pool_state *pool = test_pool; + struct page_counter *ctest; + u64 used, min, low; + + /* Can always evict from current pool, despite limits */ + if (limit_pool == test_pool) + return true; + + if (limit_pool) { + if (!parent_dmemcs(limit_pool->cs)) + return true; + + for (pool = test_pool; pool && limit_pool != pool; pool = pool_parent(pool)) + {} + + if (!pool) + return false; + } else { + /* + * If there is no cgroup limiting memory usage, use the root + * cgroup instead for limit calculations. + */ + for (limit_pool = test_pool; pool_parent(limit_pool); limit_pool = pool_parent(limit_pool)) + {} + } + + ctest = &test_pool->cnt; + + dmem_cgroup_calculate_protection(limit_pool, test_pool); + + used = page_counter_read(ctest); + min = READ_ONCE(ctest->emin); + + if (used <= min) + return false; + + if (!ignore_low) { + low = READ_ONCE(ctest->elow); + if (used > low) + return true; + + *ret_hit_low = true; + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_state_evict_valuable); + +static struct dmem_cgroup_pool_state * +alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, + struct dmem_cgroup_pool_state **allocpool) +{ + struct dmemcg_state *parent = parent_dmemcs(dmemcs); + struct dmem_cgroup_pool_state *pool, *ppool = NULL; + + if (!*allocpool) { + pool = kzalloc(sizeof(*pool), GFP_NOWAIT); + if (!pool) + return ERR_PTR(-ENOMEM); + } else { + pool = *allocpool; + *allocpool = NULL; + } + + pool->region = region; + pool->cs = dmemcs; + + if (parent) + ppool = find_cg_pool_locked(parent, region); + + page_counter_init(&pool->cnt, + ppool ? &ppool->cnt : NULL, true); + reset_all_resource_limits(pool); + + list_add_tail_rcu(&pool->css_node, &dmemcs->pools); + list_add_tail(&pool->region_node, ®ion->pools); + + if (!parent) + pool->inited = true; + else + pool->inited = ppool ? ppool->inited : false; + return pool; +} + +static struct dmem_cgroup_pool_state * +get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, + struct dmem_cgroup_pool_state **allocpool) +{ + struct dmem_cgroup_pool_state *pool, *ppool, *retpool; + struct dmemcg_state *p, *pp; + + /* + * Recursively create pool, we may not initialize yet on + * recursion, this is done as a separate step. + */ + for (p = dmemcs; p; p = parent_dmemcs(p)) { + pool = find_cg_pool_locked(p, region); + if (!pool) + pool = alloc_pool_single(p, region, allocpool); + + if (IS_ERR(pool)) + return pool; + + if (p == dmemcs && pool->inited) + return pool; + + if (pool->inited) + break; + } + + retpool = pool = find_cg_pool_locked(dmemcs, region); + for (p = dmemcs, pp = parent_dmemcs(dmemcs); pp; p = pp, pp = parent_dmemcs(p)) { + if (pool->inited) + break; + + /* ppool was created if it didn't exist by above loop. */ + ppool = find_cg_pool_locked(pp, region); + + /* Fix up parent links, mark as inited. */ + pool->cnt.parent = &ppool->cnt; + pool->inited = true; + + pool = ppool; + } + + return retpool; +} + +static void dmemcg_free_rcu(struct rcu_head *rcu) +{ + struct dmem_cgroup_region *region = container_of(rcu, typeof(*region), rcu); + struct dmem_cgroup_pool_state *pool, *next; + + list_for_each_entry_safe(pool, next, ®ion->pools, region_node) + free_cg_pool(pool); + kfree(region->name); + kfree(region); +} + +static void dmemcg_free_region(struct kref *ref) +{ + struct dmem_cgroup_region *cgregion = container_of(ref, typeof(*cgregion), ref); + + call_rcu(&cgregion->rcu, dmemcg_free_rcu); +} + +/** + * dmem_cgroup_unregister_region() - Unregister a previously registered region. + * @region: The region to unregister. + * + * This function undoes dmem_cgroup_register_region. + */ +void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) +{ + struct list_head *entry; + + if (!region) + return; + + spin_lock(&dmemcg_lock); + + /* Remove from global region list */ + list_del_rcu(®ion->region_node); + + list_for_each_rcu(entry, ®ion->pools) { + struct dmem_cgroup_pool_state *pool = + container_of(entry, typeof(*pool), region_node); + + list_del_rcu(&pool->css_node); + } + + /* + * Ensure any RCU based lookups fail. Additionally, + * no new pools should be added to the dead region + * by get_cg_pool_unlocked. + */ + region->unregistered = true; + spin_unlock(&dmemcg_lock); + + kref_put(®ion->ref, dmemcg_free_region); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_unregister_region); + +/** + * dmem_cgroup_register_region() - Register a regions for dev cgroup. + * @size: Size of region to register, in bytes. + * @fmt: Region parameters to register + * + * This function registers a node in the dmem cgroup with the + * name given. After calling this function, the region can be + * used for allocations. + * + * Return: NULL or a struct on success, PTR_ERR on failure. + */ +struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *fmt, ...) +{ + struct dmem_cgroup_region *ret; + char *region_name; + va_list ap; + + if (!size) + return NULL; + + va_start(ap, fmt); + region_name = kvasprintf(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!region_name) + return ERR_PTR(-ENOMEM); + + ret = kzalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) { + kfree(region_name); + return ERR_PTR(-ENOMEM); + } + + INIT_LIST_HEAD(&ret->pools); + ret->name = region_name; + ret->size = size; + kref_init(&ret->ref); + + spin_lock(&dmemcg_lock); + list_add_tail_rcu(&ret->region_node, &dmem_cgroup_regions); + spin_unlock(&dmemcg_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_register_region); + +static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name) +{ + struct dmem_cgroup_region *region; + + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node, spin_is_locked(&dmemcg_lock)) + if (!strcmp(name, region->name) && + kref_get_unless_zero(®ion->ref)) + return region; + + return NULL; +} + +/** + * dmem_cgroup_pool_state_put() - Drop a reference to a dmem_cgroup_pool_state + * @pool: &dmem_cgroup_pool_state + * + * Called to drop a reference to the limiting pool returned by + * dmem_cgroup_try_charge(). + */ +void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) +{ + if (pool) + css_put(&pool->cs->css); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put); + +static struct dmem_cgroup_pool_state * +get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) +{ + struct dmem_cgroup_pool_state *pool, *allocpool = NULL; + + /* fastpath lookup? */ + rcu_read_lock(); + pool = find_cg_pool_locked(cg, region); + if (pool && !READ_ONCE(pool->inited)) + pool = NULL; + rcu_read_unlock(); + + while (!pool) { + spin_lock(&dmemcg_lock); + if (!region->unregistered) + pool = get_cg_pool_locked(cg, region, &allocpool); + else + pool = ERR_PTR(-ENODEV); + spin_unlock(&dmemcg_lock); + + if (pool == ERR_PTR(-ENOMEM)) { + pool = NULL; + if (WARN_ON(allocpool)) + continue; + + allocpool = kzalloc(sizeof(*allocpool), GFP_KERNEL); + if (allocpool) { + pool = NULL; + continue; + } + } + } + + kfree(allocpool); + return pool; +} + +/** + * dmem_cgroup_uncharge() - Uncharge a pool. + * @pool: Pool to uncharge. + * @size: Size to uncharge. + * + * Undoes the effects of dmem_cgroup_try_charge. + * Must be called with the returned pool as argument, + * and same @index and @size. + */ +void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) +{ + if (!pool) + return; + + page_counter_uncharge(&pool->cnt, size); + css_put(&pool->cs->css); +} +EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge); + +/** + * dmem_cgroup_try_charge() - Try charging a new allocation to a region. + * @region: dmem region to charge + * @size: Size (in bytes) to charge. + * @ret_pool: On succesfull allocation, the pool that is charged. + * @ret_limit_pool: On a failed allocation, the limiting pool. + * + * This function charges the @region region for a size of @size bytes. + * + * If the function succeeds, @ret_pool is set, which must be passed to + * dmem_cgroup_uncharge() when undoing the allocation. + * + * When this function fails with -EAGAIN and @ret_limit_pool is non-null, it + * will be set to the pool for which the limit is hit. This can be used for + * eviction as argument to dmem_cgroup_evict_valuable(). This reference must be freed + * with @dmem_cgroup_pool_state_put(). + * + * Return: 0 on success, -EAGAIN on hitting a limit, or a negative errno on failure. + */ +int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool) +{ + struct dmemcg_state *cg; + struct dmem_cgroup_pool_state *pool; + struct page_counter *fail; + int ret; + + *ret_pool = NULL; + if (ret_limit_pool) + *ret_limit_pool = NULL; + + /* + * hold on to css, as cgroup can be removed but resource + * accounting happens on css. + */ + cg = get_current_dmemcs(); + + pool = get_cg_pool_unlocked(cg, region); + if (IS_ERR(pool)) { + ret = PTR_ERR(pool); + goto err; + } + + if (!page_counter_try_charge(&pool->cnt, size, &fail)) { + if (ret_limit_pool) { + *ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt); + css_get(&(*ret_limit_pool)->cs->css); + } + ret = -EAGAIN; + goto err; + } + + /* On success, reference from get_current_dmemcs is transferred to *ret_pool */ + *ret_pool = pool; + return 0; + +err: + css_put(&cg->css); + return ret; +} +EXPORT_SYMBOL_GPL(dmem_cgroup_try_charge); + +static int dmem_cgroup_region_capacity_show(struct seq_file *sf, void *v) +{ + struct dmem_cgroup_region *region; + + rcu_read_lock(); + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) { + seq_puts(sf, region->name); + seq_printf(sf, " %llu\n", region->size); + } + rcu_read_unlock(); + return 0; +} + +static int dmemcg_parse_limit(char *options, struct dmem_cgroup_region *region, + u64 *new_limit) +{ + char *end; + + if (!strcmp(options, "max")) { + *new_limit = PAGE_COUNTER_MAX; + return 0; + } + + *new_limit = memparse(options, &end); + if (*end != '\0') + return -EINVAL; + + return 0; +} + +static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + void (*apply)(struct dmem_cgroup_pool_state *, u64)) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(of_css(of)); + int err = 0; + + while (buf && !err) { + struct dmem_cgroup_pool_state *pool = NULL; + char *options, *region_name; + struct dmem_cgroup_region *region; + u64 new_limit; + + options = buf; + buf = strchr(buf, '\n'); + if (buf) + *buf++ = '\0'; + + options = strstrip(options); + + /* eat empty lines */ + if (!options[0]) + continue; + + region_name = strsep(&options, " \t"); + if (!region_name[0]) + continue; + + rcu_read_lock(); + region = dmemcg_get_region_by_name(region_name); + rcu_read_unlock(); + + if (!region) + return -EINVAL; + + err = dmemcg_parse_limit(options, region, &new_limit); + if (err < 0) + goto out_put; + + pool = get_cg_pool_unlocked(dmemcs, region); + if (IS_ERR(pool)) { + err = PTR_ERR(pool); + goto out_put; + } + + /* And commit */ + apply(pool, new_limit); + +out_put: + kref_put(®ion->ref, dmemcg_free_region); + } + + + return err ?: nbytes; +} + +static int dmemcg_limit_show(struct seq_file *sf, void *v, + u64 (*fn)(struct dmem_cgroup_pool_state *)) +{ + struct dmemcg_state *dmemcs = css_to_dmemcs(seq_css(sf)); + struct dmem_cgroup_region *region; + + rcu_read_lock(); + list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) { + struct dmem_cgroup_pool_state *pool = find_cg_pool_locked(dmemcs, region); + u64 val; + + seq_puts(sf, region->name); + + val = fn(pool); + if (val < PAGE_COUNTER_MAX) + seq_printf(sf, " %lld\n", val); + else + seq_puts(sf, " max\n"); + } + rcu_read_unlock(); + + return 0; +} + +static int dmem_cgroup_region_current_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_current); +} + +static int dmem_cgroup_region_min_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_min); +} + +static ssize_t dmem_cgroup_region_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_min); +} + +static int dmem_cgroup_region_low_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_low); +} + +static ssize_t dmem_cgroup_region_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_low); +} + +static int dmem_cgroup_region_max_show(struct seq_file *sf, void *v) +{ + return dmemcg_limit_show(sf, v, get_resource_max); +} + +static ssize_t dmem_cgroup_region_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return dmemcg_limit_write(of, buf, nbytes, off, set_resource_max); +} + +static struct cftype files[] = { + { + .name = "capacity", + .seq_show = dmem_cgroup_region_capacity_show, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { + .name = "current", + .seq_show = dmem_cgroup_region_current_show, + }, + { + .name = "min", + .write = dmem_cgroup_region_min_write, + .seq_show = dmem_cgroup_region_min_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "low", + .write = dmem_cgroup_region_low_write, + .seq_show = dmem_cgroup_region_low_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "max", + .write = dmem_cgroup_region_max_write, + .seq_show = dmem_cgroup_region_max_show, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* Zero entry terminates. */ +}; + +struct cgroup_subsys dmem_cgrp_subsys = { + .css_alloc = dmemcs_alloc, + .css_free = dmemcs_free, + .css_offline = dmemcs_offline, + .legacy_cftypes = files, + .dfl_cftypes = files, +}; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 529adb1f5859..5432418c0fea 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -31,6 +31,10 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK config GENERIC_PENDING_IRQ bool +# Deduce delayed migration from top-level interrupt chip flags +config GENERIC_PENDING_IRQ_CHIPFLAGS + bool + # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION bool @@ -141,6 +145,12 @@ config GENERIC_IRQ_DEBUGFS If you don't know what to do here, say N. +# Clear forwarded VM interrupts during kexec. +# This option ensures the kernel clears active states for interrupts +# forwarded to virtual machines (VMs) during a machine kexec. +config GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD + bool + endmenu config GENERIC_IRQ_MULTI_HANDLER diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index f19d3080bf11..c0f44c06d69d 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o kexec.o obj-$(CONFIG_IRQ_TIMINGS) += timings.o ifeq ($(CONFIG_TEST_IRQ_TIMINGS),y) CFLAGS_timings.o += -DDEBUG diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 271e9139de77..c901436ebd9f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1114,13 +1114,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) trigger = irqd_get_trigger_type(&desc->irq_data); irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | - IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); + IRQD_TRIGGER_MASK | IRQD_LEVEL); if (irq_settings_has_no_balance_set(desc)) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); if (irq_settings_is_per_cpu(desc)) irqd_set(&desc->irq_data, IRQD_PER_CPU); - if (irq_settings_can_move_pcntxt(desc)) - irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT); if (irq_settings_is_level(desc)) irqd_set(&desc->irq_data, IRQD_LEVEL); diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c6ffb97966be..ca142b9a4db3 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -53,6 +53,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), + BIT_MASK_DESCR(IRQCHIP_MOVE_DEFERRED), }; static void @@ -108,7 +109,6 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_NO_BALANCING), BIT_MASK_DESCR(IRQD_SINGLE_TARGET), - BIT_MASK_DESCR(IRQD_MOVE_PCNTXT), BIT_MASK_DESCR(IRQD_AFFINITY_SET), BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 32ffcbb87fa1..c4a8bca5f2b0 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -162,6 +162,7 @@ void irq_gc_mask_disable_and_ack_set(struct irq_data *d) irq_reg_writel(gc, mask, ct->regs.ack); irq_gc_unlock(gc); } +EXPORT_SYMBOL_GPL(irq_gc_mask_disable_and_ack_set); /** * irq_gc_eoi - EOI interrupt diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index fe0272cd84a5..a979523640d0 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -421,7 +421,7 @@ irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, #ifdef CONFIG_GENERIC_PENDING_IRQ static inline bool irq_can_move_pcntxt(struct irq_data *data) { - return irqd_can_move_in_process_context(data); + return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED); } static inline bool irq_move_pending(struct irq_data *data) { @@ -441,10 +441,6 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } -static inline bool handle_enforce_irqctx(struct irq_data *data) -{ - return irqd_is_handle_enforce_irqctx(data); -} bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) @@ -471,10 +467,6 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } -static inline bool handle_enforce_irqctx(struct irq_data *data) -{ - return false; -} #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0253e77fcd9a..287830739783 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -708,7 +708,7 @@ int handle_irq_desc(struct irq_desc *desc) return -EINVAL; data = irq_desc_get_irq_data(desc); - if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) + if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); diff --git a/kernel/irq/kexec.c b/kernel/irq/kexec.c new file mode 100644 index 000000000000..1a3deffe6b5b --- /dev/null +++ b/kernel/irq/kexec.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdesc.h> +#include <linux/irqnr.h> + +#include "internals.h" + +void machine_kexec_mask_interrupts(void) +{ + struct irq_desc *desc; + unsigned int i; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int check_eoi = 1; + + chip = irq_desc_get_chip(desc); + if (!chip || !irqd_is_started(&desc->irq_data)) + continue; + + if (IS_ENABLED(CONFIG_GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD)) { + /* + * First try to remove the active state from an interrupt which is forwarded + * to a VM. If the interrupt is not forwarded, try to EOI the interrupt. + */ + check_eoi = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + } + + if (check_eoi && chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) + chip->irq_eoi(&desc->irq_data); + + irq_shutdown(desc); + } +} diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f0803d6bd296..f300bb6be3bd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1182,45 +1182,38 @@ out_unlock: } /* - * Interrupts which are not explicitly requested as threaded - * interrupts rely on the implicit bh/preempt disable of the hard irq - * context. So we need to disable bh here to avoid deadlocks and other - * side effects. + * Interrupts explicitly requested as threaded interrupts want to be + * preemptible - many of them need to sleep and wait for slow busses to + * complete. */ -static irqreturn_t -irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) +static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action) { - irqreturn_t ret; + irqreturn_t ret = action->thread_fn(action->irq, action->dev_id); - local_bh_disable(); - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) - local_irq_disable(); - ret = action->thread_fn(action->irq, action->dev_id); if (ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); irq_finalize_oneshot(desc, action); - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) - local_irq_enable(); - local_bh_enable(); return ret; } /* - * Interrupts explicitly requested as threaded interrupts want to be - * preemptible - many of them need to sleep and wait for slow busses to - * complete. + * Interrupts which are not explicitly requested as threaded + * interrupts rely on the implicit bh/preempt disable of the hard irq + * context. So we need to disable bh here to avoid deadlocks and other + * side effects. */ -static irqreturn_t irq_thread_fn(struct irq_desc *desc, - struct irqaction *action) +static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret; - ret = action->thread_fn(action->irq, action->dev_id); - if (ret == IRQ_HANDLED) - atomic_inc(&desc->threads_handled); - - irq_finalize_oneshot(desc, action); + local_bh_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); + ret = irq_thread_fn(desc, action); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); + local_bh_enable(); return ret; } diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index b07a2d732ffb..1b7fa72968bd 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -53,7 +53,7 @@ static int irq_sw_resend(struct irq_desc *desc) * Validate whether this interrupt can be safely injected from * non interrupt context */ - if (handle_enforce_irqctx(&desc->irq_data)) + if (irqd_is_handle_enforce_irqctx(&desc->irq_data)) return -EINVAL; /* diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 7b7efb1a114b..00b3bd127692 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -11,7 +11,6 @@ enum { _IRQ_NOREQUEST = IRQ_NOREQUEST, _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, - _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, @@ -142,11 +141,6 @@ static inline void irq_settings_set_noprobe(struct irq_desc *desc) desc->status_use_accessors |= _IRQ_NOPROBE; } -static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc) -{ - return desc->status_use_accessors & _IRQ_MOVE_PCNTXT; -} - static inline bool irq_settings_can_autoenable(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOAUTOEN); diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index c43e2ac2f8de..4b7315e99bd6 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -509,6 +509,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) /** * irq_timings_next_event - Return when the next event is supposed to arrive + * @now: current time * * During the last busy cycle, the number of interrupts is incremented * and stored in the irq_timings structure. This information is diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index c0caa14880c3..6fcc46f3eb39 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1007,7 +1007,7 @@ int kernel_kexec(void) error = -EBUSY; goto Restore_console; } - suspend_console(); + console_suspend_all(); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Resume_console; @@ -1061,7 +1061,7 @@ int kernel_kexec(void) Resume_devices: dpm_resume_end(PMSG_RESTORE); Resume_console: - resume_console(); + console_resume_all(); thaw_processes(); Restore_console: pm_restore_console(); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 3c21c31796db..0cd39954d5a1 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -347,6 +347,7 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, * /sys/kernel/livepatch/<patch>/transition * /sys/kernel/livepatch/<patch>/force * /sys/kernel/livepatch/<patch>/replace + * /sys/kernel/livepatch/<patch>/stack_order * /sys/kernel/livepatch/<patch>/<object> * /sys/kernel/livepatch/<patch>/<object>/patched * /sys/kernel/livepatch/<patch>/<object>/<function,sympos> @@ -452,15 +453,38 @@ static ssize_t replace_show(struct kobject *kobj, return sysfs_emit(buf, "%d\n", patch->replace); } +static ssize_t stack_order_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch, *this_patch; + int stack_order = 0; + + this_patch = container_of(kobj, struct klp_patch, kobj); + + mutex_lock(&klp_mutex); + + klp_for_each_patch(patch) { + stack_order++; + if (patch == this_patch) + break; + } + + mutex_unlock(&klp_mutex); + + return sysfs_emit(buf, "%d\n", stack_order); +} + static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled); static struct kobj_attribute transition_kobj_attr = __ATTR_RO(transition); static struct kobj_attribute force_kobj_attr = __ATTR_WO(force); static struct kobj_attribute replace_kobj_attr = __ATTR_RO(replace); +static struct kobj_attribute stack_order_kobj_attr = __ATTR_RO(stack_order); static struct attribute *klp_patch_attrs[] = { &enabled_kobj_attr.attr, &transition_kobj_attr.attr, &force_kobj_attr.attr, &replace_kobj_attr.attr, + &stack_order_kobj_attr.attr, NULL }; ATTRIBUTE_GROUPS(klp_patch); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index de95ec07e477..cc33470f4de9 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -106,7 +106,7 @@ static const struct kernel_param_ops lt_bind_ops = { module_param_cb(bind_readers, <_bind_ops, &bind_readers, 0644); module_param_cb(bind_writers, <_bind_ops, &bind_writers, 0644); -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask); +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); static struct task_struct *stats_task; static struct task_struct **writer_tasks; @@ -1358,7 +1358,7 @@ static int __init lock_torture_init(void) if (torture_init_error(firsterr)) goto unwind; if (cpumask_nonempty(bind_writers)) - torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers); + torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers, true); create_reader: if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress)) @@ -1369,7 +1369,7 @@ static int __init lock_torture_init(void) if (torture_init_error(firsterr)) goto unwind; if (cpumask_nonempty(bind_readers)) - torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers); + torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers, true); } if (stat_interval > 0) { firsterr = torture_create_kthread(lock_torture_stats, NULL, diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1f87aa01ba44..c9f60670a261 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -411,7 +411,7 @@ int hibernation_snapshot(int platform_mode) goto Thaw; } - suspend_console(); + console_suspend_all(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); @@ -437,7 +437,7 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) pm_restore_gfp_mask(); - resume_console(); + console_resume_all(); dpm_complete(msg); Close: @@ -547,7 +547,7 @@ int hibernation_restore(int platform_mode) int error; pm_prepare_console(); - suspend_console(); + console_suspend_all(); pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { @@ -561,7 +561,7 @@ int hibernation_restore(int platform_mode) } dpm_resume_end(PMSG_RECOVER); pm_restore_gfp_mask(); - resume_console(); + console_resume_all(); pm_restore_console(); return error; } @@ -586,7 +586,7 @@ int hibernation_platform_enter(void) goto Close; entering_platform_hibernation = true; - suspend_console(); + console_suspend_all(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -634,7 +634,7 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); - resume_console(); + console_resume_all(); Close: hibernation_ops->end(); @@ -896,7 +896,7 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data) if (error) goto dpm_complete; - suspend_console(); + console_suspend_all(); error = dpm_suspend(PMSG_FREEZE); if (error) @@ -920,7 +920,7 @@ skip: dpm_resume: dpm_resume(PMSG_THAW); - resume_console(); + console_resume_all(); dpm_complete: dpm_complete(PMSG_THAW); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 09f8397bae15..c3da3db58cdf 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -502,7 +502,7 @@ int suspend_devices_and_enter(suspend_state_t state) if (error) goto Close; - suspend_console(); + console_suspend_all(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -521,9 +521,9 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); - trace_suspend_resume(TPS("resume_console"), state, true); - resume_console(); - trace_suspend_resume(TPS("resume_console"), state, false); + trace_suspend_resume(TPS("console_resume_all"), state, true); + console_resume_all(); + trace_suspend_resume(TPS("console_resume_all"), state, false); Close: platform_resume_end(state); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 74b4734a87b9..1cfc943af62c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2751,11 +2751,11 @@ module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** - * suspend_console - suspend the console subsystem + * console_suspend_all - suspend the console subsystem * * This disables printk() while we go into suspend states */ -void suspend_console(void) +void console_suspend_all(void) { struct console *con; @@ -2778,7 +2778,7 @@ void suspend_console(void) synchronize_srcu(&console_srcu); } -void resume_console(void) +void console_resume_all(void) { struct console_flush_type ft; struct console *con; @@ -3360,7 +3360,12 @@ void console_unblank(void) */ cookie = console_srcu_read_lock(); for_each_console_srcu(c) { - if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) { + short flags = console_srcu_read_flags(c); + + if (flags & CON_SUSPENDED) + continue; + + if ((flags & CON_ENABLED) && c->unblank) { found_unblank = true; break; } @@ -3397,7 +3402,12 @@ void console_unblank(void) cookie = console_srcu_read_lock(); for_each_console_srcu(c) { - if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) + short flags = console_srcu_read_flags(c); + + if (flags & CON_SUSPENDED) + continue; + + if ((flags & CON_ENABLED) && c->unblank) c->unblank(); } console_srcu_read_unlock(cookie); @@ -3515,10 +3525,10 @@ struct tty_driver *console_device(int *index) /* * Prevent further output on the passed console device so that (for example) - * serial drivers can disable console output before suspending a port, and can + * serial drivers can suspend console output before suspending a port, and can * re-enable output afterwards. */ -void console_stop(struct console *console) +void console_suspend(struct console *console) { __pr_flush(console, 1000, true); console_list_lock(); @@ -3533,9 +3543,9 @@ void console_stop(struct console *console) */ synchronize_srcu(&console_srcu); } -EXPORT_SYMBOL(console_stop); +EXPORT_SYMBOL(console_suspend); -void console_start(struct console *console) +void console_resume(struct console *console) { struct console_flush_type ft; bool is_nbcon; @@ -3560,7 +3570,7 @@ void console_start(struct console *console) __pr_flush(console, 1000, true); } -EXPORT_SYMBOL(console_start); +EXPORT_SYMBOL(console_resume); #ifdef CONFIG_PRINTK static int unregister_console_locked(struct console *console); diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 9b0b52e1836f..6af90510a1ca 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -53,6 +53,37 @@ config RCU_TORTURE_TEST Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_TORTURE_TEST_CHK_RDR_STATE + tristate "Check rcutorture reader state" + depends on RCU_TORTURE_TEST + default n + help + This option causes rcutorture to check the desired rcutorture + reader state for each segment against the actual context. + Note that PREEMPT_COUNT must be enabled if the preempt-disabled + and bh-disabled checks are to take effect, and that PREEMPT_RCU + must be enabled for the RCU-nesting checks to take effect. + These checks add overhead, and this Kconfig options is therefore + disabled by default. + + Say Y here if you want rcutorture reader contexts checked. + Say N if you are unsure. + +config RCU_TORTURE_TEST_LOG_CPU + tristate "Log CPU for rcutorture failures" + depends on RCU_TORTURE_TEST + default n + help + This option causes rcutorture to decorate each entry of its + log of failure/close-call rcutorture reader segments with the + number of the CPU that the reader was running on at the time. + This information can be useful, but it does incur additional + overhead, overhead that can make both failures and close calls + less probable. + + Say Y here if you want CPU IDs logged. + Say N if you are unsure. + config RCU_REF_SCALE_TEST tristate "Scalability tests for read-side synchronization (RCU and others)" depends on DEBUG_KERNEL diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 612d27690335..d26fb1d33ed9 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -92,12 +92,20 @@ torture_param(bool, gp_cond_exp, false, "Use conditional/async expedited GP wait torture_param(bool, gp_cond_full, false, "Use conditional/async full-state GP wait primitives"); torture_param(bool, gp_cond_exp_full, false, "Use conditional/async full-stateexpedited GP wait primitives"); +torture_param(int, gp_cond_wi, 16 * USEC_PER_SEC / HZ, + "Wait interval for normal conditional grace periods, us (default 16 jiffies)"); +torture_param(int, gp_cond_wi_exp, 128, + "Wait interval for expedited conditional grace periods, us (default 128 us)"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(bool, gp_normal, false, "Use normal (non-expedited) GP wait primitives"); torture_param(bool, gp_poll, false, "Use polling GP wait primitives"); torture_param(bool, gp_poll_exp, false, "Use polling expedited GP wait primitives"); torture_param(bool, gp_poll_full, false, "Use polling full-state GP wait primitives"); torture_param(bool, gp_poll_exp_full, false, "Use polling full-state expedited GP wait primitives"); +torture_param(int, gp_poll_wi, 16 * USEC_PER_SEC / HZ, + "Wait interval for normal polled grace periods, us (default 16 jiffies)"); +torture_param(int, gp_poll_wi_exp, 128, + "Wait interval for expedited polled grace periods, us (default 128 us)"); torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives"); torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers"); torture_param(int, leakpointer, 0, "Leak pointer dereferences from readers"); @@ -109,9 +117,11 @@ torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable"); torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disable"); torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)"); +torture_param(int, preempt_duration, 0, "Preemption duration (ms), zero to disable"); +torture_param(int, preempt_interval, MSEC_PER_SEC, "Interval between preemptions (ms)"); torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)"); torture_param(int, read_exit_burst, 16, "# of read-then-exit bursts per episode, zero to disable"); -torture_param(int, reader_flavor, 0x1, "Reader flavors to use, one per bit."); +torture_param(int, reader_flavor, SRCU_READ_FLAVOR_NORMAL, "Reader flavors to use, one per bit."); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -149,6 +159,7 @@ static struct task_struct **fwd_prog_tasks; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; static struct task_struct *read_exit_task; +static struct task_struct *preempt_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -259,10 +270,13 @@ struct rt_read_seg { unsigned long rt_delay_ms; unsigned long rt_delay_us; bool rt_preempted; + int rt_cpu; + int rt_end_cpu; }; static int err_segs_recorded; static struct rt_read_seg err_segs[RCUTORTURE_RDR_MAX_SEGS]; static int rt_read_nsegs; +static int rt_read_preempted; static const char *rcu_torture_writer_state_getname(void) { @@ -353,7 +367,8 @@ struct rcu_torture_ops { void (*read_delay)(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp); void (*readunlock)(int idx); - int (*readlock_held)(void); + int (*readlock_held)(void); // lockdep. + int (*readlock_nesting)(void); // actual nesting, if available, -1 if not. unsigned long (*get_gp_seq)(void); unsigned long (*gp_diff)(unsigned long new, unsigned long old); void (*deferred_free)(struct rcu_torture *p); @@ -390,6 +405,7 @@ struct rcu_torture_ops { void (*get_gp_data)(int *flags, unsigned long *gp_seq); void (*gp_slow_register)(atomic_t *rgssp); void (*gp_slow_unregister)(atomic_t *rgssp); + bool (*reader_blocked)(void); long cbflood_max; int irq_capable; int can_boost; @@ -448,10 +464,8 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) rtrsp->rt_delay_us = shortdelay_us; } if (!preempt_count() && - !(torture_random(rrsp) % (nrealreaders * 500))) { + !(torture_random(rrsp) % (nrealreaders * 500))) torture_preempt_schedule(); /* QS only if preemptible. */ - rtrsp->rt_preempted = true; - } } static void rcu_torture_read_unlock(int idx) @@ -459,6 +473,15 @@ static void rcu_torture_read_unlock(int idx) rcu_read_unlock(); } +static int rcu_torture_readlock_nesting(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + return rcu_preempt_depth(); + if (IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return (preempt_count() & PREEMPT_MASK); + return -1; +} + /* * Update callback in the pipe. This should be invoked after a grace period. */ @@ -548,6 +571,7 @@ static struct rcu_torture_ops rcu_ops = { .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, .readlock_held = torture_readlock_not_held, + .readlock_nesting = rcu_torture_readlock_nesting, .get_gp_seq = rcu_get_gp_seq, .gp_diff = rcu_seq_diff, .deferred_free = rcu_torture_deferred_free, @@ -573,6 +597,7 @@ static struct rcu_torture_ops rcu_ops = { .start_gp_poll_exp_full = start_poll_synchronize_rcu_expedited_full, .poll_gp_state_exp = poll_state_synchronize_rcu, .cond_sync_exp = cond_synchronize_rcu_expedited, + .cond_sync_exp_full = cond_synchronize_rcu_expedited_full, .call = call_rcu_hurry, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, @@ -582,6 +607,9 @@ static struct rcu_torture_ops rcu_ops = { .get_gp_data = rcutorture_get_gp_data, .gp_slow_register = rcu_gp_slow_register, .gp_slow_unregister = rcu_gp_slow_unregister, + .reader_blocked = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU) + ? has_rcu_reader_blocked + : NULL, .irq_capable = 1, .can_boost = IS_ENABLED(CONFIG_RCU_BOOST), .extendables = RCUTORTURE_MAX_EXTEND, @@ -628,6 +656,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .exp_sync = synchronize_rcu_busted, .call = call_rcu_busted, .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, .name = "busted" }; @@ -650,17 +679,17 @@ static int srcu_torture_read_lock(void) int idx; int ret = 0; - if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) { + if ((reader_flavor & SRCU_READ_FLAVOR_NORMAL) || !(reader_flavor & SRCU_READ_FLAVOR_ALL)) { idx = srcu_read_lock(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx; } - if (reader_flavor & 0x2) { + if (reader_flavor & SRCU_READ_FLAVOR_NMI) { idx = srcu_read_lock_nmisafe(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx << 1; } - if (reader_flavor & 0x4) { + if (reader_flavor & SRCU_READ_FLAVOR_LITE) { idx = srcu_read_lock_lite(srcu_ctlp); WARN_ON_ONCE(idx & ~0x1); ret += idx << 2; @@ -690,11 +719,11 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) static void srcu_torture_read_unlock(int idx) { WARN_ON_ONCE((reader_flavor && (idx & ~reader_flavor)) || (!reader_flavor && (idx & ~0x1))); - if (reader_flavor & 0x4) + if (reader_flavor & SRCU_READ_FLAVOR_LITE) srcu_read_unlock_lite(srcu_ctlp, (idx & 0x4) >> 2); - if (reader_flavor & 0x2) + if (reader_flavor & SRCU_READ_FLAVOR_NMI) srcu_read_unlock_nmisafe(srcu_ctlp, (idx & 0x2) >> 1); - if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) + if ((reader_flavor & SRCU_READ_FLAVOR_NORMAL) || !(reader_flavor & SRCU_READ_FLAVOR_ALL)) srcu_read_unlock(srcu_ctlp, idx & 0x1); } @@ -857,7 +886,7 @@ static void synchronize_rcu_trivial(void) int cpu; for_each_online_cpu(cpu) { - torture_sched_setaffinity(current->pid, cpumask_of(cpu)); + torture_sched_setaffinity(current->pid, cpumask_of(cpu), true); WARN_ON_ONCE(raw_smp_processor_id() != cpu); } } @@ -1347,6 +1376,7 @@ static void rcu_torture_write_types(void) pr_alert("%s: gp_sync without primitives.\n", __func__); } pr_alert("%s: Testing %d update types.\n", __func__, nsynctypes); + pr_info("%s: gp_cond_wi %d gp_cond_wi_exp %d gp_poll_wi %d gp_poll_wi_exp %d\n", __func__, gp_cond_wi, gp_cond_wi_exp, gp_poll_wi, gp_poll_wi_exp); } /* @@ -1513,7 +1543,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET: rcu_torture_writer_state = RTWS_COND_GET; gp_snap = cur_ops->get_gp_state(); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC; cur_ops->cond_sync(gp_snap); rcu_torture_pipe_update(old_rp); @@ -1521,7 +1552,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_EXP: rcu_torture_writer_state = RTWS_COND_GET_EXP; gp_snap = cur_ops->get_gp_state_exp(); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi_exp, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_EXP; cur_ops->cond_sync_exp(gp_snap); rcu_torture_pipe_update(old_rp); @@ -1529,7 +1561,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_FULL: rcu_torture_writer_state = RTWS_COND_GET_FULL; cur_ops->get_gp_state_full(&gp_snap_full); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_FULL; cur_ops->cond_sync_full(&gp_snap_full); rcu_torture_pipe_update(old_rp); @@ -1537,7 +1570,8 @@ rcu_torture_writer(void *arg) case RTWS_COND_GET_EXP_FULL: rcu_torture_writer_state = RTWS_COND_GET_EXP_FULL; cur_ops->get_gp_state_full(&gp_snap_full); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_cond_wi_exp, + 1000, &rand); rcu_torture_writer_state = RTWS_COND_SYNC_EXP_FULL; cur_ops->cond_sync_exp_full(&gp_snap_full); rcu_torture_pipe_update(old_rp); @@ -1557,8 +1591,8 @@ rcu_torture_writer(void *arg) break; } WARN_ON_ONCE(ulo_size > 0 && i >= ulo_size); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi, + 1000, &rand); } rcu_torture_pipe_update(old_rp); break; @@ -1578,8 +1612,8 @@ rcu_torture_writer(void *arg) break; } WARN_ON_ONCE(rgo_size > 0 && i >= rgo_size); - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi, + 1000, &rand); } rcu_torture_pipe_update(old_rp); break; @@ -1588,8 +1622,8 @@ rcu_torture_writer(void *arg) gp_snap = cur_ops->start_gp_poll_exp(); rcu_torture_writer_state = RTWS_POLL_WAIT_EXP; while (!cur_ops->poll_gp_state_exp(gp_snap)) - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi_exp, + 1000, &rand); rcu_torture_pipe_update(old_rp); break; case RTWS_POLL_GET_EXP_FULL: @@ -1597,8 +1631,8 @@ rcu_torture_writer(void *arg) cur_ops->start_gp_poll_exp_full(&gp_snap_full); rcu_torture_writer_state = RTWS_POLL_WAIT_EXP_FULL; while (!cur_ops->poll_gp_state_full(&gp_snap_full)) - torture_hrtimeout_jiffies(torture_random(&rand) % 16, - &rand); + torture_hrtimeout_us(torture_random(&rand) % gp_poll_wi_exp, + 1000, &rand); rcu_torture_pipe_update(old_rp); break; case RTWS_SYNC: @@ -1835,6 +1869,44 @@ static void rcu_torture_reader_do_mbchk(long myid, struct rcu_torture *rtp, smp_store_release(&rtrcp_assigner->rtc_chkrdr, -1); // Assigner can again assign. } +// Verify the specified RCUTORTURE_RDR* state. +#define ROEC_ARGS "%s %s: Current %#x To add %#x To remove %#x preempt_count() %#x\n", __func__, s, curstate, new, old, preempt_count() +static void rcutorture_one_extend_check(char *s, int curstate, int new, int old, bool insoftirq) +{ + if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST_CHK_RDR_STATE)) + return; + + WARN_ONCE(!(curstate & RCUTORTURE_RDR_IRQ) && irqs_disabled(), ROEC_ARGS); + WARN_ONCE((curstate & RCUTORTURE_RDR_IRQ) && !irqs_disabled(), ROEC_ARGS); + + // If CONFIG_PREEMPT_COUNT=n, further checks are unreliable. + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + WARN_ONCE((curstate & (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH)) && + !(preempt_count() & SOFTIRQ_MASK), ROEC_ARGS); + WARN_ONCE((curstate & (RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED)) && + !(preempt_count() & PREEMPT_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->readlock_nesting && + (curstate & (RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2)) && + cur_ops->readlock_nesting() == 0, ROEC_ARGS); + + // Timer handlers have all sorts of stuff disabled, so ignore + // unintended disabling. + if (insoftirq) + return; + + WARN_ONCE(cur_ops->extendables && + !(curstate & (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH)) && + (preempt_count() & SOFTIRQ_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->extendables && + !(curstate & (RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED)) && + (preempt_count() & PREEMPT_MASK), ROEC_ARGS); + WARN_ONCE(cur_ops->readlock_nesting && + !(curstate & (RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2)) && + cur_ops->readlock_nesting() > 0, ROEC_ARGS); +} + /* * Do one extension of an RCU read-side critical section using the * current reader state in readstate (set to zero for initial entry @@ -1844,10 +1916,11 @@ static void rcu_torture_reader_do_mbchk(long myid, struct rcu_torture *rtp, * beginning or end of the critical section and if there was actually a * change, do a ->read_delay(). */ -static void rcutorture_one_extend(int *readstate, int newstate, +static void rcutorture_one_extend(int *readstate, int newstate, bool insoftirq, struct torture_random_state *trsp, struct rt_read_seg *rtrsp) { + bool first; unsigned long flags; int idxnew1 = -1; int idxnew2 = -1; @@ -1856,8 +1929,10 @@ static void rcutorture_one_extend(int *readstate, int newstate, int statesnew = ~*readstate & newstate; int statesold = *readstate & ~newstate; + first = idxold1 == 0; WARN_ON_ONCE(idxold2 < 0); WARN_ON_ONCE(idxold2 & ~RCUTORTURE_RDR_ALLBITS); + rcutorture_one_extend_check("before change", idxold1, statesnew, statesold, insoftirq); rtrsp->rt_readstate = newstate; /* First, put new protection in place to avoid critical-section gap. */ @@ -1876,6 +1951,21 @@ static void rcutorture_one_extend(int *readstate, int newstate, if (statesnew & RCUTORTURE_RDR_RCU_2) idxnew2 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_2) & RCUTORTURE_RDR_MASK_2; + // Complain unless both the old and the new protection is in place. + rcutorture_one_extend_check("during change", + idxold1 | statesnew, statesnew, statesold, insoftirq); + + // Sample CPU under both sets of protections to reduce confusion. + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU)) { + int cpu = raw_smp_processor_id(); + rtrsp->rt_cpu = cpu; + if (!first) { + rtrsp[-1].rt_end_cpu = cpu; + if (cur_ops->reader_blocked) + rtrsp[-1].rt_preempted = cur_ops->reader_blocked(); + } + } + /* * Next, remove old protection, in decreasing order of strength * to avoid unlock paths that aren't safe in the stronger @@ -1926,6 +2016,7 @@ static void rcutorture_one_extend(int *readstate, int newstate, WARN_ON_ONCE(*readstate < 0); if (WARN_ON_ONCE(*readstate & ~RCUTORTURE_RDR_ALLBITS)) pr_info("Unexpected readstate value of %#x\n", *readstate); + rcutorture_one_extend_check("after change", *readstate, statesnew, statesold, insoftirq); } /* Return the biggest extendables mask given current RCU and boot parameters. */ @@ -1992,7 +2083,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) * critical section. */ static struct rt_read_seg * -rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp, +rcutorture_loop_extend(int *readstate, bool insoftirq, struct torture_random_state *trsp, struct rt_read_seg *rtrsp) { int i; @@ -2007,7 +2098,7 @@ rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp, i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1; for (j = 0; j < i; j++) { mask = rcutorture_extend_mask(*readstate, trsp); - rcutorture_one_extend(readstate, mask, trsp, &rtrsp[j]); + rcutorture_one_extend(readstate, mask, insoftirq, trsp, &rtrsp[j]); } return &rtrsp[j]; } @@ -2028,6 +2119,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) int newstate; struct rcu_torture *p; int pipe_count; + bool preempted = false; int readstate = 0; struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS] = { { 0 } }; struct rt_read_seg *rtrsp = &rtseg[0]; @@ -2036,7 +2128,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) WARN_ON_ONCE(!rcu_is_watching()); newstate = rcutorture_extend_mask(readstate, trsp); - rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++); + rcutorture_one_extend(&readstate, newstate, myid < 0, trsp, rtrsp++); if (checkpolling) { if (cur_ops->get_gp_state && cur_ops->poll_gp_state) cookie = cur_ops->get_gp_state(); @@ -2049,13 +2141,13 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) !cur_ops->readlock_held || cur_ops->readlock_held()); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ - rcutorture_one_extend(&readstate, 0, trsp, rtrsp); + rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp); return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); rcu_torture_reader_do_mbchk(myid, p, trsp); - rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp); + rtrsp = rcutorture_loop_extend(&readstate, myid < 0, trsp, rtrsp); preempt_disable(); pipe_count = READ_ONCE(p->rtort_pipe_count); if (pipe_count > RCU_TORTURE_PIPE_LEN) { @@ -2093,7 +2185,9 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) rcu_torture_writer_state, cpumask_pr_args(cpu_online_mask)); } - rcutorture_one_extend(&readstate, 0, trsp, rtrsp); + if (cur_ops->reader_blocked) + preempted = cur_ops->reader_blocked(); + rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp); WARN_ON_ONCE(readstate); // This next splat is expected behavior if leakpointer, especially // for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels. @@ -2105,6 +2199,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) for (rtrsp1 = &rtseg[0]; rtrsp1 < rtrsp; rtrsp1++) err_segs[i++] = *rtrsp1; rt_read_nsegs = i; + rt_read_preempted = preempted; } return true; @@ -2425,7 +2520,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "read_exit_delay=%d read_exit_burst=%d " "reader_flavor=%x " "nocbs_nthreads=%d nocbs_toggle=%d " - "test_nmis=%d\n", + "test_nmis=%d " + "preempt_duration=%d preempt_interval=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, @@ -2438,7 +2534,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) read_exit_delay, read_exit_burst, reader_flavor, nocbs_nthreads, nocbs_toggle, - test_nmis); + test_nmis, + preempt_duration, preempt_interval); } static int rcutorture_booster_cleanup(unsigned int cpu) @@ -3068,12 +3165,12 @@ static int __init rcu_torture_fwd_prog_init(void) fwd_progress = 0; return 0; } - if (stall_cpu > 0) { - VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing"); + if (stall_cpu > 0 || (preempt_duration > 0 && IS_ENABLED(CONFIG_RCU_NOCB_CPU))) { + VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall and/or preemption testing"); fwd_progress = 0; if (IS_MODULE(CONFIG_RCU_TORTURE_TEST)) return -EINVAL; /* In module, can fail back to user. */ - WARN_ON(1); /* Make sure rcutorture notices conflict. */ + WARN_ON(1); /* Make sure rcutorture scripting notices conflict. */ return 0; } if (fwd_progress_holdoff <= 0) @@ -3418,6 +3515,35 @@ static void rcutorture_test_nmis(int n) #endif // #else // #if IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) } +// Randomly preempt online CPUs. +static int rcu_torture_preempt(void *unused) +{ + int cpu = -1; + DEFINE_TORTURE_RANDOM(rand); + + schedule_timeout_idle(stall_cpu_holdoff); + do { + // Wait for preempt_interval ms with up to 100us fuzz. + torture_hrtimeout_ms(preempt_interval, 100, &rand); + // Select online CPU. + cpu = cpumask_next(cpu, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_next(-1, cpu_online_mask); + WARN_ON_ONCE(cpu >= nr_cpu_ids); + // Move to that CPU, if can't do so, retry later. + if (torture_sched_setaffinity(current->pid, cpumask_of(cpu), false)) + continue; + // Preempt at high-ish priority, then reset to normal. + sched_set_fifo(current); + torture_sched_setaffinity(current->pid, cpu_present_mask, true); + mdelay(preempt_duration); + sched_set_normal(current, 0); + stutter_wait("rcu_torture_preempt"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_preempt"); + return 0; +} + static enum cpuhp_state rcutor_hp; static void @@ -3446,6 +3572,7 @@ rcu_torture_cleanup(void) if (cur_ops->gp_kthread_dbg) cur_ops->gp_kthread_dbg(); + torture_stop_kthread(rcu_torture_preempt, preempt_task); rcu_torture_read_exit_cleanup(); rcu_torture_barrier_cleanup(); rcu_torture_fwd_prog_cleanup(); @@ -3508,26 +3635,49 @@ rcu_torture_cleanup(void) pr_alert("\t: No segments recorded!!!\n"); firsttime = 1; for (i = 0; i < rt_read_nsegs; i++) { - pr_alert("\t%d: %#x ", i, err_segs[i].rt_readstate); + pr_alert("\t%d: %#4x", i, err_segs[i].rt_readstate); if (err_segs[i].rt_delay_jiffies != 0) { pr_cont("%s%ldjiffies", firsttime ? "" : "+", err_segs[i].rt_delay_jiffies); firsttime = 0; } + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_LOG_CPU)) { + pr_cont(" CPU %2d", err_segs[i].rt_cpu); + if (err_segs[i].rt_cpu != err_segs[i].rt_end_cpu) + pr_cont("->%-2d", err_segs[i].rt_end_cpu); + else + pr_cont(" ..."); + } if (err_segs[i].rt_delay_ms != 0) { - pr_cont("%s%ldms", firsttime ? "" : "+", + pr_cont(" %s%ldms", firsttime ? "" : "+", err_segs[i].rt_delay_ms); firsttime = 0; } if (err_segs[i].rt_delay_us != 0) { - pr_cont("%s%ldus", firsttime ? "" : "+", + pr_cont(" %s%ldus", firsttime ? "" : "+", err_segs[i].rt_delay_us); firsttime = 0; } - pr_cont("%s\n", - err_segs[i].rt_preempted ? "preempted" : ""); + pr_cont("%s", err_segs[i].rt_preempted ? " preempted" : ""); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_BH) + pr_cont(" BH"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_IRQ) + pr_cont(" IRQ"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_PREEMPT) + pr_cont(" PREEMPT"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RBH) + pr_cont(" RBH"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_SCHED) + pr_cont(" SCHED"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RCU_1) + pr_cont(" RCU_1"); + if (err_segs[i].rt_readstate & RCUTORTURE_RDR_RCU_2) + pr_cont(" RCU_2"); + pr_cont("\n"); } + if (rt_read_preempted) + pr_alert("\tReader was preempted.\n"); } if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); @@ -4019,6 +4169,11 @@ rcu_torture_init(void) firsterr = rcu_torture_read_exit_init(); if (torture_init_error(firsterr)) goto unwind; + if (preempt_duration > 0) { + firsterr = torture_create_kthread(rcu_torture_preempt, NULL, preempt_task); + if (torture_init_error(firsterr)) + goto unwind; + } if (object_debug) rcu_test_debug_objects(); torture_init_end(); diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index aacfcc9838b3..1b47376acdc4 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/torture.h> #include <linux/types.h> +#include <linux/sched/clock.h> #include "rcu.h" @@ -531,6 +532,39 @@ static const struct ref_scale_ops acqrel_ops = { static volatile u64 stopopts; +static void ref_sched_clock_section(const int nloops) +{ + u64 x = 0; + int i; + + preempt_disable(); + for (i = nloops; i >= 0; i--) + x += sched_clock(); + preempt_enable(); + stopopts = x; +} + +static void ref_sched_clock_delay_section(const int nloops, const int udl, const int ndl) +{ + u64 x = 0; + int i; + + preempt_disable(); + for (i = nloops; i >= 0; i--) { + x += sched_clock(); + un_delay(udl, ndl); + } + preempt_enable(); + stopopts = x; +} + +static const struct ref_scale_ops sched_clock_ops = { + .readsection = ref_sched_clock_section, + .delaysection = ref_sched_clock_delay_section, + .name = "sched-clock" +}; + + static void ref_clock_section(const int nloops) { u64 x = 0; @@ -1130,9 +1164,9 @@ ref_scale_init(void) int firsterr = 0; static const struct ref_scale_ops *scale_ops[] = { &rcu_ops, &srcu_ops, &srcu_lite_ops, RCU_TRACE_OPS RCU_TASKS_OPS - &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, - &clock_ops, &jiffies_ops, &typesafe_ref_ops, &typesafe_lock_ops, - &typesafe_seqlock_ops, + &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, + &acqrel_ops, &sched_clock_ops, &clock_ops, &jiffies_ops, + &typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops, }; if (!torture_init_begin(scale_type, verbose)) diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 5e2e53464794..b83c74c4dcc0 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -738,7 +738,8 @@ EXPORT_SYMBOL_GPL(__srcu_check_read_flavor); /* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. - * Returns an index that must be passed to the matching srcu_read_unlock(). + * Returns a guaranteed non-negative index that must be passed to the + * matching __srcu_read_unlock(). */ int __srcu_read_lock(struct srcu_struct *ssp) { @@ -1076,7 +1077,6 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, /* If grace period not already in progress, start it. */ if (!WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) && rcu_seq_state(sup->srcu_gp_seq) == SRCU_STATE_IDLE) { - WARN_ON_ONCE(ULONG_CMP_GE(sup->srcu_gp_seq, sup->srcu_gp_seq_needed)); srcu_gp_start(ssp); // And how can that list_add() in the "else" clause diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ff98233d4aa5..f81df3923f37 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -186,26 +186,6 @@ static int rcu_unlock_delay; module_param(rcu_unlock_delay, int, 0444); #endif -/* - * This rcu parameter is runtime-read-only. It reflects - * a minimum allowed number of objects which can be cached - * per-CPU. Object size is equal to one page. This value - * can be changed at boot time. - */ -static int rcu_min_cached_objs = 5; -module_param(rcu_min_cached_objs, int, 0444); - -// A page shrinker can ask for pages to be freed to make them -// available for other parts of the system. This usually happens -// under low memory conditions, and in that case we should also -// defer page-cache filling for a short time period. -// -// The default value is 5 seconds, which is long enough to reduce -// interference with the shrinker while it asks other systems to -// drain their caches. -static int rcu_delay_page_cache_fill_msec = 5000; -module_param(rcu_delay_page_cache_fill_msec, int, 0444); - /* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { @@ -3084,8 +3064,11 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) head->func = func; head->next = NULL; kasan_record_aux_stack_noalloc(head); + local_irq_save(flags); rdp = this_cpu_ptr(&rcu_data); + RCU_LOCKDEP_WARN(!rcu_rdp_cpu_online(rdp), "Callback enqueued on offline CPU!"); + lazy = lazy_in && !rcu_async_should_hurry(); /* Add the callback to our list. */ @@ -3191,812 +3174,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func) } EXPORT_SYMBOL_GPL(call_rcu); -/* Maximum number of jiffies to wait before draining a batch. */ -#define KFREE_DRAIN_JIFFIES (5 * HZ) -#define KFREE_N_BATCHES 2 -#define FREE_N_CHANNELS 2 - -/** - * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers - * @list: List node. All blocks are linked between each other - * @gp_snap: Snapshot of RCU state for objects placed to this bulk - * @nr_records: Number of active pointers in the array - * @records: Array of the kvfree_rcu() pointers - */ -struct kvfree_rcu_bulk_data { - struct list_head list; - struct rcu_gp_oldstate gp_snap; - unsigned long nr_records; - void *records[] __counted_by(nr_records); -}; - -/* - * This macro defines how many entries the "records" array - * will contain. It is based on the fact that the size of - * kvfree_rcu_bulk_data structure becomes exactly one page. - */ -#define KVFREE_BULK_MAX_ENTR \ - ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) - -/** - * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests - * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period - * @head_free: List of kfree_rcu() objects waiting for a grace period - * @head_free_gp_snap: Grace-period snapshot to check for attempted premature frees. - * @bulk_head_free: Bulk-List of kvfree_rcu() objects waiting for a grace period - * @krcp: Pointer to @kfree_rcu_cpu structure - */ - -struct kfree_rcu_cpu_work { - struct rcu_work rcu_work; - struct rcu_head *head_free; - struct rcu_gp_oldstate head_free_gp_snap; - struct list_head bulk_head_free[FREE_N_CHANNELS]; - struct kfree_rcu_cpu *krcp; -}; - -/** - * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period - * @head: List of kfree_rcu() objects not yet waiting for a grace period - * @head_gp_snap: Snapshot of RCU state for objects placed to "@head" - * @bulk_head: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period - * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period - * @lock: Synchronize access to this structure - * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES - * @initialized: The @rcu_work fields have been initialized - * @head_count: Number of objects in rcu_head singular list - * @bulk_count: Number of objects in bulk-list - * @bkvcache: - * A simple cache list that contains objects for reuse purpose. - * In order to save some per-cpu space the list is singular. - * Even though it is lockless an access has to be protected by the - * per-cpu lock. - * @page_cache_work: A work to refill the cache when it is empty - * @backoff_page_cache_fill: Delay cache refills - * @work_in_progress: Indicates that page_cache_work is running - * @hrtimer: A hrtimer for scheduling a page_cache_work - * @nr_bkv_objs: number of allocated objects at @bkvcache. - * - * This is a per-CPU structure. The reason that it is not included in - * the rcu_data structure is to permit this code to be extracted from - * the RCU files. Such extraction could allow further optimization of - * the interactions with the slab allocators. - */ -struct kfree_rcu_cpu { - // Objects queued on a linked list - // through their rcu_head structures. - struct rcu_head *head; - unsigned long head_gp_snap; - atomic_t head_count; - - // Objects queued on a bulk-list. - struct list_head bulk_head[FREE_N_CHANNELS]; - atomic_t bulk_count[FREE_N_CHANNELS]; - - struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - raw_spinlock_t lock; - struct delayed_work monitor_work; - bool initialized; - - struct delayed_work page_cache_work; - atomic_t backoff_page_cache_fill; - atomic_t work_in_progress; - struct hrtimer hrtimer; - - struct llist_head bkvcache; - int nr_bkv_objs; -}; - -static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), -}; - -static __always_inline void -debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) -{ -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - int i; - - for (i = 0; i < bhead->nr_records; i++) - debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); -#endif -} - -static inline struct kfree_rcu_cpu * -krc_this_cpu_lock(unsigned long *flags) -{ - struct kfree_rcu_cpu *krcp; - - local_irq_save(*flags); // For safely calling this_cpu_ptr(). - krcp = this_cpu_ptr(&krc); - raw_spin_lock(&krcp->lock); - - return krcp; -} - -static inline void -krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) -{ - raw_spin_unlock_irqrestore(&krcp->lock, flags); -} - -static inline struct kvfree_rcu_bulk_data * -get_cached_bnode(struct kfree_rcu_cpu *krcp) -{ - if (!krcp->nr_bkv_objs) - return NULL; - - WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1); - return (struct kvfree_rcu_bulk_data *) - llist_del_first(&krcp->bkvcache); -} - -static inline bool -put_cached_bnode(struct kfree_rcu_cpu *krcp, - struct kvfree_rcu_bulk_data *bnode) -{ - // Check the limit. - if (krcp->nr_bkv_objs >= rcu_min_cached_objs) - return false; - - llist_add((struct llist_node *) bnode, &krcp->bkvcache); - WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1); - return true; -} - -static int -drain_page_cache(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - struct llist_node *page_list, *pos, *n; - int freed = 0; - - if (!rcu_min_cached_objs) - return 0; - - raw_spin_lock_irqsave(&krcp->lock, flags); - page_list = llist_del_all(&krcp->bkvcache); - WRITE_ONCE(krcp->nr_bkv_objs, 0); - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - llist_for_each_safe(pos, n, page_list) { - free_page((unsigned long)pos); - freed++; - } - - return freed; -} - -static void -kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp, - struct kvfree_rcu_bulk_data *bnode, int idx) -{ - unsigned long flags; - int i; - - if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) { - debug_rcu_bhead_unqueue(bnode); - rcu_lock_acquire(&rcu_callback_map); - if (idx == 0) { // kmalloc() / kfree(). - trace_rcu_invoke_kfree_bulk_callback( - rcu_state.name, bnode->nr_records, - bnode->records); - - kfree_bulk(bnode->nr_records, bnode->records); - } else { // vmalloc() / vfree(). - for (i = 0; i < bnode->nr_records; i++) { - trace_rcu_invoke_kvfree_callback( - rcu_state.name, bnode->records[i], 0); - - vfree(bnode->records[i]); - } - } - rcu_lock_release(&rcu_callback_map); - } - - raw_spin_lock_irqsave(&krcp->lock, flags); - if (put_cached_bnode(krcp, bnode)) - bnode = NULL; - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - if (bnode) - free_page((unsigned long) bnode); - - cond_resched_tasks_rcu_qs(); -} - -static void -kvfree_rcu_list(struct rcu_head *head) -{ - struct rcu_head *next; - - for (; head; head = next) { - void *ptr = (void *) head->func; - unsigned long offset = (void *) head - ptr; - - next = head->next; - debug_rcu_head_unqueue((struct rcu_head *)ptr); - rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - - if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) - kvfree(ptr); - - rcu_lock_release(&rcu_callback_map); - cond_resched_tasks_rcu_qs(); - } -} - -/* - * This function is invoked in workqueue context after a grace period. - * It frees all the objects queued on ->bulk_head_free or ->head_free. - */ -static void kfree_rcu_work(struct work_struct *work) -{ - unsigned long flags; - struct kvfree_rcu_bulk_data *bnode, *n; - struct list_head bulk_head[FREE_N_CHANNELS]; - struct rcu_head *head; - struct kfree_rcu_cpu *krcp; - struct kfree_rcu_cpu_work *krwp; - struct rcu_gp_oldstate head_gp_snap; - int i; - - krwp = container_of(to_rcu_work(work), - struct kfree_rcu_cpu_work, rcu_work); - krcp = krwp->krcp; - - raw_spin_lock_irqsave(&krcp->lock, flags); - // Channels 1 and 2. - for (i = 0; i < FREE_N_CHANNELS; i++) - list_replace_init(&krwp->bulk_head_free[i], &bulk_head[i]); - - // Channel 3. - head = krwp->head_free; - krwp->head_free = NULL; - head_gp_snap = krwp->head_free_gp_snap; - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - // Handle the first two channels. - for (i = 0; i < FREE_N_CHANNELS; i++) { - // Start from the tail page, so a GP is likely passed for it. - list_for_each_entry_safe(bnode, n, &bulk_head[i], list) - kvfree_rcu_bulk(krcp, bnode, i); - } - - /* - * This is used when the "bulk" path can not be used for the - * double-argument of kvfree_rcu(). This happens when the - * page-cache is empty, which means that objects are instead - * queued on a linked list through their rcu_head structures. - * This list is named "Channel 3". - */ - if (head && !WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&head_gp_snap))) - kvfree_rcu_list(head); -} - -static bool -need_offload_krc(struct kfree_rcu_cpu *krcp) -{ - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - if (!list_empty(&krcp->bulk_head[i])) - return true; - - return !!READ_ONCE(krcp->head); -} - -static bool -need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) -{ - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - if (!list_empty(&krwp->bulk_head_free[i])) - return true; - - return !!krwp->head_free; -} - -static int krc_count(struct kfree_rcu_cpu *krcp) -{ - int sum = atomic_read(&krcp->head_count); - int i; - - for (i = 0; i < FREE_N_CHANNELS; i++) - sum += atomic_read(&krcp->bulk_count[i]); - - return sum; -} - -static void -__schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) -{ - long delay, delay_left; - - delay = krc_count(krcp) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; - if (delayed_work_pending(&krcp->monitor_work)) { - delay_left = krcp->monitor_work.timer.expires - jiffies; - if (delay < delay_left) - mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); - return; - } - queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); -} - -static void -schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&krcp->lock, flags); - __schedule_delayed_monitor_work(krcp); - raw_spin_unlock_irqrestore(&krcp->lock, flags); -} - -static void -kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) -{ - struct list_head bulk_ready[FREE_N_CHANNELS]; - struct kvfree_rcu_bulk_data *bnode, *n; - struct rcu_head *head_ready = NULL; - unsigned long flags; - int i; - - raw_spin_lock_irqsave(&krcp->lock, flags); - for (i = 0; i < FREE_N_CHANNELS; i++) { - INIT_LIST_HEAD(&bulk_ready[i]); - - list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) { - if (!poll_state_synchronize_rcu_full(&bnode->gp_snap)) - break; - - atomic_sub(bnode->nr_records, &krcp->bulk_count[i]); - list_move(&bnode->list, &bulk_ready[i]); - } - } - - if (krcp->head && poll_state_synchronize_rcu(krcp->head_gp_snap)) { - head_ready = krcp->head; - atomic_set(&krcp->head_count, 0); - WRITE_ONCE(krcp->head, NULL); - } - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - for (i = 0; i < FREE_N_CHANNELS; i++) { - list_for_each_entry_safe(bnode, n, &bulk_ready[i], list) - kvfree_rcu_bulk(krcp, bnode, i); - } - - if (head_ready) - kvfree_rcu_list(head_ready); -} - -/* - * Return: %true if a work is queued, %false otherwise. - */ -static bool -kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) -{ - unsigned long flags; - bool queued = false; - int i, j; - - raw_spin_lock_irqsave(&krcp->lock, flags); - - // Attempt to start a new batch. - for (i = 0; i < KFREE_N_BATCHES; i++) { - struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); - - // Try to detach bulk_head or head and attach it, only when - // all channels are free. Any channel is not free means at krwp - // there is on-going rcu work to handle krwp's free business. - if (need_wait_for_krwp_work(krwp)) - continue; - - // kvfree_rcu_drain_ready() might handle this krcp, if so give up. - if (need_offload_krc(krcp)) { - // Channel 1 corresponds to the SLAB-pointer bulk path. - // Channel 2 corresponds to vmalloc-pointer bulk path. - for (j = 0; j < FREE_N_CHANNELS; j++) { - if (list_empty(&krwp->bulk_head_free[j])) { - atomic_set(&krcp->bulk_count[j], 0); - list_replace_init(&krcp->bulk_head[j], - &krwp->bulk_head_free[j]); - } - } - - // Channel 3 corresponds to both SLAB and vmalloc - // objects queued on the linked list. - if (!krwp->head_free) { - krwp->head_free = krcp->head; - get_state_synchronize_rcu_full(&krwp->head_free_gp_snap); - atomic_set(&krcp->head_count, 0); - WRITE_ONCE(krcp->head, NULL); - } - - // One work is per one batch, so there are three - // "free channels", the batch can handle. Break - // the loop since it is done with this CPU thus - // queuing an RCU work is _always_ success here. - queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); - WARN_ON_ONCE(!queued); - break; - } - } - - raw_spin_unlock_irqrestore(&krcp->lock, flags); - return queued; -} - -/* - * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. - */ -static void kfree_rcu_monitor(struct work_struct *work) -{ - struct kfree_rcu_cpu *krcp = container_of(work, - struct kfree_rcu_cpu, monitor_work.work); - - // Drain ready for reclaim. - kvfree_rcu_drain_ready(krcp); - - // Queue a batch for a rest. - kvfree_rcu_queue_batch(krcp); - - // If there is nothing to detach, it means that our job is - // successfully done here. In case of having at least one - // of the channels that is still busy we should rearm the - // work to repeat an attempt. Because previous batches are - // still in progress. - if (need_offload_krc(krcp)) - schedule_delayed_monitor_work(krcp); -} - -static enum hrtimer_restart -schedule_page_work_fn(struct hrtimer *t) -{ - struct kfree_rcu_cpu *krcp = - container_of(t, struct kfree_rcu_cpu, hrtimer); - - queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0); - return HRTIMER_NORESTART; -} - -static void fill_page_cache_func(struct work_struct *work) -{ - struct kvfree_rcu_bulk_data *bnode; - struct kfree_rcu_cpu *krcp = - container_of(work, struct kfree_rcu_cpu, - page_cache_work.work); - unsigned long flags; - int nr_pages; - bool pushed; - int i; - - nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ? - 1 : rcu_min_cached_objs; - - for (i = READ_ONCE(krcp->nr_bkv_objs); i < nr_pages; i++) { - bnode = (struct kvfree_rcu_bulk_data *) - __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - - if (!bnode) - break; - - raw_spin_lock_irqsave(&krcp->lock, flags); - pushed = put_cached_bnode(krcp, bnode); - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - if (!pushed) { - free_page((unsigned long) bnode); - break; - } - } - - atomic_set(&krcp->work_in_progress, 0); - atomic_set(&krcp->backoff_page_cache_fill, 0); -} - -static void -run_page_cache_worker(struct kfree_rcu_cpu *krcp) -{ - // If cache disabled, bail out. - if (!rcu_min_cached_objs) - return; - - if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && - !atomic_xchg(&krcp->work_in_progress, 1)) { - if (atomic_read(&krcp->backoff_page_cache_fill)) { - queue_delayed_work(system_unbound_wq, - &krcp->page_cache_work, - msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); - } else { - hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - krcp->hrtimer.function = schedule_page_work_fn; - hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL); - } - } -} - -// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock() -// state specified by flags. If can_alloc is true, the caller must -// be schedulable and not be holding any locks or mutexes that might be -// acquired by the memory allocator or anything that it might invoke. -// Returns true if ptr was successfully recorded, else the caller must -// use a fallback. -static inline bool -add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, - unsigned long *flags, void *ptr, bool can_alloc) -{ - struct kvfree_rcu_bulk_data *bnode; - int idx; - - *krcp = krc_this_cpu_lock(flags); - if (unlikely(!(*krcp)->initialized)) - return false; - - idx = !!is_vmalloc_addr(ptr); - bnode = list_first_entry_or_null(&(*krcp)->bulk_head[idx], - struct kvfree_rcu_bulk_data, list); - - /* Check if a new block is required. */ - if (!bnode || bnode->nr_records == KVFREE_BULK_MAX_ENTR) { - bnode = get_cached_bnode(*krcp); - if (!bnode && can_alloc) { - krc_this_cpu_unlock(*krcp, *flags); - - // __GFP_NORETRY - allows a light-weight direct reclaim - // what is OK from minimizing of fallback hitting point of - // view. Apart of that it forbids any OOM invoking what is - // also beneficial since we are about to release memory soon. - // - // __GFP_NOMEMALLOC - prevents from consuming of all the - // memory reserves. Please note we have a fallback path. - // - // __GFP_NOWARN - it is supposed that an allocation can - // be failed under low memory or high memory pressure - // scenarios. - bnode = (struct kvfree_rcu_bulk_data *) - __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - raw_spin_lock_irqsave(&(*krcp)->lock, *flags); - } - - if (!bnode) - return false; - - // Initialize the new block and attach it. - bnode->nr_records = 0; - list_add(&bnode->list, &(*krcp)->bulk_head[idx]); - } - - // Finally insert and update the GP for this page. - bnode->nr_records++; - bnode->records[bnode->nr_records - 1] = ptr; - get_state_synchronize_rcu_full(&bnode->gp_snap); - atomic_inc(&(*krcp)->bulk_count[idx]); - - return true; -} - -/* - * Queue a request for lazy invocation of the appropriate free routine - * after a grace period. Please note that three paths are maintained, - * two for the common case using arrays of pointers and a third one that - * is used only when the main paths cannot be used, for example, due to - * memory pressure. - * - * Each kvfree_call_rcu() request is added to a batch. The batch will be drained - * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will - * be free'd in workqueue context. This allows us to: batch requests together to - * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. - */ -void kvfree_call_rcu(struct rcu_head *head, void *ptr) -{ - unsigned long flags; - struct kfree_rcu_cpu *krcp; - bool success; - - /* - * Please note there is a limitation for the head-less - * variant, that is why there is a clear rule for such - * objects: it can be used from might_sleep() context - * only. For other places please embed an rcu_head to - * your data. - */ - if (!head) - might_sleep(); - - // Queue the object but don't yet schedule the batch. - if (debug_rcu_head_queue(ptr)) { - // Probable double kfree_rcu(), just leak. - WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", - __func__, head); - - // Mark as success and leave. - return; - } - - kasan_record_aux_stack_noalloc(ptr); - success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head); - if (!success) { - run_page_cache_worker(krcp); - - if (head == NULL) - // Inline if kvfree_rcu(one_arg) call. - goto unlock_return; - - head->func = ptr; - head->next = krcp->head; - WRITE_ONCE(krcp->head, head); - atomic_inc(&krcp->head_count); - - // Take a snapshot for this krcp. - krcp->head_gp_snap = get_state_synchronize_rcu(); - success = true; - } - - /* - * The kvfree_rcu() caller considers the pointer freed at this point - * and likely removes any references to it. Since the actual slab - * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore - * this object (no scanning or false positives reporting). - */ - kmemleak_ignore(ptr); - - // Set timer to drain after KFREE_DRAIN_JIFFIES. - if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) - __schedule_delayed_monitor_work(krcp); - -unlock_return: - krc_this_cpu_unlock(krcp, flags); - - /* - * Inline kvfree() after synchronize_rcu(). We can do - * it from might_sleep() context only, so the current - * CPU can pass the QS state. - */ - if (!success) { - debug_rcu_head_unqueue((struct rcu_head *) ptr); - synchronize_rcu(); - kvfree(ptr); - } -} -EXPORT_SYMBOL_GPL(kvfree_call_rcu); - -/** - * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. - * - * Note that a single argument of kvfree_rcu() call has a slow path that - * triggers synchronize_rcu() following by freeing a pointer. It is done - * before the return from the function. Therefore for any single-argument - * call that will result in a kfree() to a cache that is to be destroyed - * during module exit, it is developer's responsibility to ensure that all - * such calls have returned before the call to kmem_cache_destroy(). - */ -void kvfree_rcu_barrier(void) -{ - struct kfree_rcu_cpu_work *krwp; - struct kfree_rcu_cpu *krcp; - bool queued; - int i, cpu; - - /* - * Firstly we detach objects and queue them over an RCU-batch - * for all CPUs. Finally queued works are flushed for each CPU. - * - * Please note. If there are outstanding batches for a particular - * CPU, those have to be finished first following by queuing a new. - */ - for_each_possible_cpu(cpu) { - krcp = per_cpu_ptr(&krc, cpu); - - /* - * Check if this CPU has any objects which have been queued for a - * new GP completion. If not(means nothing to detach), we are done - * with it. If any batch is pending/running for this "krcp", below - * per-cpu flush_rcu_work() waits its completion(see last step). - */ - if (!need_offload_krc(krcp)) - continue; - - while (1) { - /* - * If we are not able to queue a new RCU work it means: - * - batches for this CPU are still in flight which should - * be flushed first and then repeat; - * - no objects to detach, because of concurrency. - */ - queued = kvfree_rcu_queue_batch(krcp); - - /* - * Bail out, if there is no need to offload this "krcp" - * anymore. As noted earlier it can run concurrently. - */ - if (queued || !need_offload_krc(krcp)) - break; - - /* There are ongoing batches. */ - for (i = 0; i < KFREE_N_BATCHES; i++) { - krwp = &(krcp->krw_arr[i]); - flush_rcu_work(&krwp->rcu_work); - } - } - } - - /* - * Now we guarantee that all objects are flushed. - */ - for_each_possible_cpu(cpu) { - krcp = per_cpu_ptr(&krc, cpu); - - /* - * A monitor work can drain ready to reclaim objects - * directly. Wait its completion if running or pending. - */ - cancel_delayed_work_sync(&krcp->monitor_work); - - for (i = 0; i < KFREE_N_BATCHES; i++) { - krwp = &(krcp->krw_arr[i]); - flush_rcu_work(&krwp->rcu_work); - } - } -} -EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); - -static unsigned long -kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) -{ - int cpu; - unsigned long count = 0; - - /* Snapshot count of all CPUs */ - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - count += krc_count(krcp); - count += READ_ONCE(krcp->nr_bkv_objs); - atomic_set(&krcp->backoff_page_cache_fill, 1); - } - - return count == 0 ? SHRINK_EMPTY : count; -} - -static unsigned long -kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) -{ - int cpu, freed = 0; - - for_each_possible_cpu(cpu) { - int count; - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - count = krc_count(krcp); - count += drain_page_cache(krcp); - kfree_rcu_monitor(&krcp->monitor_work.work); - - sc->nr_to_scan -= count; - freed += count; - - if (sc->nr_to_scan <= 0) - break; - } - - return freed == 0 ? SHRINK_STOP : freed; -} - -void __init kfree_rcu_scheduler_running(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - if (need_offload_krc(krcp)) - schedule_delayed_monitor_work(krcp); - } -} - /* * During early boot, any blocking grace-period wait automatically * implies a grace period. @@ -5648,62 +4825,12 @@ static void __init rcu_dump_rcu_node_tree(void) struct workqueue_struct *rcu_gp_wq; -static void __init kfree_rcu_batch_init(void) -{ - int cpu; - int i, j; - struct shrinker *kfree_rcu_shrinker; - - /* Clamp it to [0:100] seconds interval. */ - if (rcu_delay_page_cache_fill_msec < 0 || - rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { - - rcu_delay_page_cache_fill_msec = - clamp(rcu_delay_page_cache_fill_msec, 0, - (int) (100 * MSEC_PER_SEC)); - - pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n", - rcu_delay_page_cache_fill_msec); - } - - for_each_possible_cpu(cpu) { - struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - - for (i = 0; i < KFREE_N_BATCHES; i++) { - INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); - krcp->krw_arr[i].krcp = krcp; - - for (j = 0; j < FREE_N_CHANNELS; j++) - INIT_LIST_HEAD(&krcp->krw_arr[i].bulk_head_free[j]); - } - - for (i = 0; i < FREE_N_CHANNELS; i++) - INIT_LIST_HEAD(&krcp->bulk_head[i]); - - INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); - INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); - krcp->initialized = true; - } - - kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree"); - if (!kfree_rcu_shrinker) { - pr_err("Failed to allocate kfree_rcu() shrinker!\n"); - return; - } - - kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count; - kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan; - - shrinker_register(kfree_rcu_shrinker); -} - void __init rcu_init(void) { int cpu = smp_processor_id(); rcu_early_boot_tests(); - kfree_rcu_batch_init(); rcu_bootup_announce(); sanitize_kthread_prio(); rcu_init_geometry(); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index fb664d3a01c9..77efed89c79e 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -227,16 +227,16 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake) /* * Report expedited quiescent state for multiple CPUs, all covered by the - * specified leaf rcu_node structure. + * specified leaf rcu_node structure, which is acquired by the caller. */ -static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, +static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, unsigned long flags, unsigned long mask, bool wake) + __releases(rnp->lock) { int cpu; - unsigned long flags; struct rcu_data *rdp; - raw_spin_lock_irqsave_rcu_node(rnp, flags); + raw_lockdep_assert_held_rcu_node(rnp); if (!(rnp->expmask & mask)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; @@ -257,8 +257,13 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, */ static void rcu_report_exp_rdp(struct rcu_data *rdp) { + unsigned long flags; + struct rcu_node *rnp = rdp->mynode; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rdp->cpu_no_qs.b.exp, false); - rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true); + ASSERT_EXCLUSIVE_WRITER(rdp->cpu_no_qs.b.exp); + rcu_report_exp_cpu_mult(rnp, flags, rdp->grpmask, true); } /* Common code for work-done checking. */ @@ -432,8 +437,10 @@ retry_ipi: raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ - if (mask_ofl_test) - rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); + if (mask_ofl_test) { + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_report_exp_cpu_mult(rnp, flags, mask_ofl_test, false); + } } static void rcu_exp_sel_wait_wake(unsigned long s); @@ -712,6 +719,18 @@ static void rcu_exp_sel_wait_wake(unsigned long s) rcu_exp_wait_wake(s); } +/* Request an expedited quiescent state. */ +static void rcu_exp_need_qs(void) +{ + lockdep_assert_irqs_disabled(); + ASSERT_EXCLUSIVE_WRITER_SCOPED(*this_cpu_ptr(&rcu_data.cpu_no_qs.b.exp)); + __this_cpu_write(rcu_data.cpu_no_qs.b.exp, true); + /* Store .exp before .rcu_urgent_qs. */ + smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + #ifdef CONFIG_PREEMPT_RCU /* @@ -730,24 +749,34 @@ static void rcu_exp_handler(void *unused) struct task_struct *t = current; /* - * First, the common case of not being in an RCU read-side + * First, is there no need for a quiescent state from this CPU, + * or is this CPU already looking for a quiescent state for the + * current grace period? If either is the case, just leave. + * However, this should not happen due to the preemptible + * sync_sched_exp_online_cleanup() implementation being a no-op, + * so warn if this does happen. + */ + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); + if (WARN_ON_ONCE(!(READ_ONCE(rnp->expmask) & rdp->grpmask) || + READ_ONCE(rdp->cpu_no_qs.b.exp))) + return; + + /* + * Second, the common case of not being in an RCU read-side * critical section. If also enabled or idle, immediately * report the quiescent state, otherwise defer. */ if (!depth) { if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || - rcu_is_cpu_rrupt_from_idle()) { + rcu_is_cpu_rrupt_from_idle()) rcu_report_exp_rdp(rdp); - } else { - WRITE_ONCE(rdp->cpu_no_qs.b.exp, true); - set_tsk_need_resched(t); - set_preempt_need_resched(); - } + else + rcu_exp_need_qs(); return; } /* - * Second, the less-common case of being in an RCU read-side + * Third, the less-common case of being in an RCU read-side * critical section. In this case we can count on a future * rcu_read_unlock(). However, this rcu_read_unlock() might * execute on some other CPU, but in that case there will be @@ -768,7 +797,7 @@ static void rcu_exp_handler(void *unused) return; } - // Finally, negative nesting depth should not happen. + // Fourth and finally, negative nesting depth should not happen. WARN_ON_ONCE(1); } @@ -835,16 +864,6 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) #else /* #ifdef CONFIG_PREEMPT_RCU */ -/* Request an expedited quiescent state. */ -static void rcu_exp_need_qs(void) -{ - __this_cpu_write(rcu_data.cpu_no_qs.b.exp, true); - /* Store .exp before .rcu_urgent_qs. */ - smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true); - set_tsk_need_resched(current); - set_preempt_need_resched(); -} - /* Invoked on each online non-idle CPU for expedited quiescent state. */ static void rcu_exp_handler(void *unused) { @@ -852,6 +871,7 @@ static void rcu_exp_handler(void *unused) struct rcu_node *rnp = rdp->mynode; bool preempt_bh_enabled = !(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)); + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) return; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3927ea5f7955..bb7ca6eb9ef0 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -275,6 +275,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) rcu_report_exp_rdp(rdp); else WARN_ON_ONCE(rdp->cpu_no_qs.b.exp); + ASSERT_EXCLUSIVE_WRITER_SCOPED(rdp->cpu_no_qs.b.exp); } /* diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f8436969e0c8..c912b594ba98 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -527,12 +527,12 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) /* Get rcutorture access to sched_setaffinity(). */ -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn) { int ret; ret = sched_setaffinity(pid, in_mask); - WARN_ONCE(ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret); + WARN_ONCE(dowarn && ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret); return ret; } EXPORT_SYMBOL_GPL(torture_sched_setaffinity); diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c index 62e73444ffe4..38dae590b29f 100644 --- a/kernel/time/clocksource-wdtest.c +++ b/kernel/time/clocksource-wdtest.c @@ -137,7 +137,8 @@ static int wdtest_func(void *arg) udelay(1); j2 = clocksource_wdtest_ktime.read(&clocksource_wdtest_ktime); pr_info("--- tsc-like times: %lu - %lu = %lu.\n", j2, j1, j2 - j1); - WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); + WARN_ONCE(time_before(j2, j1 + NSEC_PER_USEC), + "Expected at least 1000ns, got %lu.\n", j2 - j1); /* Verify tsc-like stability with various numbers of errors injected. */ max_retries = clocksource_get_max_watchdog_retry(); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 030426c8c944..f6d8df94045c 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1067,11 +1067,10 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * - * Returns 1 when the new timer is the leftmost timer in the tree. + * Returns true when the new timer is the leftmost timer in the tree. */ -static int enqueue_hrtimer(struct hrtimer *timer, - struct hrtimer_clock_base *base, - enum hrtimer_mode mode) +static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, + enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 881a9ce96af7..1b675aee99a9 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -538,7 +538,7 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * When the reference count reaches zero, the timer is scheduled * for RCU removal after the grace period. * - * Holding rcu_read_lock() accross the lookup ensures that + * Holding rcu_read_lock() across the lookup ensures that * the timer cannot be freed. * * The lookup validates locklessly that timr::it_signal == diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index ed58eebb4e8f..0207868c8b4d 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -1020,6 +1020,8 @@ static inline ktime_t tick_get_next_period(void) /** * tick_broadcast_setup_oneshot - setup the broadcast device + * @bc: the broadcast device + * @from_periodic: true if called from periodic mode */ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3d128825d343..1e67d076f195 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -485,91 +485,30 @@ u64 notrace ktime_get_tai_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); -static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) +/** + * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. + * + * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. + */ +u64 ktime_get_real_fast_ns(void) { + struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; - u64 basem, baser, delta; + u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); - basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); - if (mono) - *mono = basem + delta; return baser + delta; } - -/** - * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. - * - * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. - */ -u64 ktime_get_real_fast_ns(void) -{ - return __ktime_get_real_fast(&tk_fast_mono, NULL); -} EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** - * ktime_get_fast_timestamps: - NMI safe timestamps - * @snapshot: Pointer to timestamp storage - * - * Stores clock monotonic, boottime and realtime timestamps. - * - * Boot time is a racy access on 32bit systems if the sleep time injection - * happens late during resume and not in timekeeping_resume(). That could - * be avoided by expanding struct tk_read_base with boot offset for 32bit - * and adding more overhead to the update. As this is a hard to observe - * once per resume event which can be filtered with reasonable effort using - * the accurate mono/real timestamps, it's probably not worth the trouble. - * - * Aside of that it might be possible on 32 and 64 bit to observe the - * following when the sleep time injection happens late: - * - * CPU 0 CPU 1 - * timekeeping_resume() - * ktime_get_fast_timestamps() - * mono, real = __ktime_get_real_fast() - * inject_sleep_time() - * update boot offset - * boot = mono + bootoffset; - * - * That means that boot time already has the sleep time adjustment, but - * real time does not. On the next readout both are in sync again. - * - * Preventing this for 64bit is not really feasible without destroying the - * careful cache layout of the timekeeper because the sequence count and - * struct tk_read_base would then need two cache lines instead of one. - * - * Access to the time keeper clock source is disabled across the innermost - * steps of suspend/resume. The accessors still work, but the timestamps - * are frozen until time keeping is resumed which happens very early. - * - * For regular suspend/resume there is no observable difference vs. sched - * clock, but it might affect some of the nasty low level debug printks. - * - * OTOH, access to sched clock is not guaranteed across suspend/resume on - * all systems either so it depends on the hardware in use. - * - * If that turns out to be a real problem then this could be mitigated by - * using sched clock in a similar way as during early boot. But it's not as - * trivial as on early boot because it needs some careful protection - * against the clock monotonic timestamp jumping backwards on resume. - */ -void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); - snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); -} - -/** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * diff --git a/kernel/time/timer.c b/kernel/time/timer.c index a5860bf6d16f..40706cb36920 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -956,33 +956,29 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base, static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; - struct timer_base *base; - - base = per_cpu_ptr(&timer_bases[index], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) - base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); - return base; + index = BASE_DEF; + + return per_cpu_ptr(&timer_bases[index], cpu); } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; - struct timer_base *base; - - base = this_cpu_ptr(&timer_bases[index]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) - base = this_cpu_ptr(&timer_bases[BASE_DEF]); - return base; + index = BASE_DEF; + + return this_cpu_ptr(&timer_bases[index]); } static inline struct timer_base *get_timer_base(u32 tflags) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 066c9ddca4ec..9cb9b6584ea1 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1670,9 +1670,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) * be different from tmigr_hierarchy_levels, contains only a * single group. */ - if (group->parent || i == tmigr_hierarchy_levels || - (list_empty(&tmigr_level_list[i]) && - list_is_singular(&tmigr_level_list[i - 1]))) + if (group->parent || list_is_singular(&tmigr_level_list[i - 1])) break; } while (i < tmigr_hierarchy_levels); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 154accc7a543..ae19f70f8170 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -110,22 +110,19 @@ struct tmigr_cpu { * union tmigr_state - state of tmigr_group * @state: Combined version of the state - only used for atomic * read/cmpxchg function - * @struct: Split version of the state - only use the struct members to + * &anon struct: Split version of the state - only use the struct members to * update information to stay independent of endianness + * @active: Contains each mask bit of the active children + * @migrator: Contains mask of the child which is migrator + * @seq: Sequence counter needs to be increased when an update + * to the tmigr_state is done. It prevents a race when + * updates in the child groups are propagated in changed + * order. Detailed information about the scenario is + * given in the documentation at the begin of + * timer_migration.c. */ union tmigr_state { u32 state; - /** - * struct - split state of tmigr_group - * @active: Contains each mask bit of the active children - * @migrator: Contains mask of the child which is migrator - * @seq: Sequence counter needs to be increased when an update - * to the tmigr_state is done. It prevents a race when - * updates in the child groups are propagated in changed - * order. Detailed information about the scenario is - * given in the documentation at the begin of - * timer_migration.c. - */ struct { u8 active; u8 migrator; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 74c2b1d43bb9..d570b8b9c0a9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -31,9 +31,14 @@ config HAVE_FUNCTION_GRAPH_TRACER help See Documentation/trace/ftrace-design.rst -config HAVE_FUNCTION_GRAPH_RETVAL +config HAVE_FUNCTION_GRAPH_FREGS bool +config HAVE_FTRACE_GRAPH_FUNC + bool + help + True if ftrace_graph_func() is defined. + config HAVE_DYNAMIC_FTRACE bool help @@ -57,6 +62,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS This allows for use of ftrace_regs_get_argument() and ftrace_regs_get_stack_pointer(). +config HAVE_FTRACE_REGS_HAVING_PT_REGS + bool + help + If this is set, ftrace_regs has pt_regs, thus it can convert to + pt_regs without allocating memory. + config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE bool help @@ -232,7 +243,7 @@ config FUNCTION_GRAPH_TRACER config FUNCTION_GRAPH_RETVAL bool "Kernel Function Graph Return Value" - depends on HAVE_FUNCTION_GRAPH_RETVAL + depends on HAVE_FUNCTION_GRAPH_FREGS depends on FUNCTION_GRAPH_TRACER default n help @@ -296,10 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" - depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS - depends on HAVE_RETHOOK - select RETHOOK + depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC + depends on DYNAMIC_FTRACE_WITH_ARGS + select FUNCTION_GRAPH_TRACER default n help This option enables kernel function probe (fprobe) based on ftrace. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9f2f65767639..c462aca8b7e6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2585,6 +2585,20 @@ struct user_syms { char *buf; }; +#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS +static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); +#define bpf_kprobe_multi_pt_regs_ptr() this_cpu_ptr(&bpf_kprobe_multi_pt_regs) +#else +#define bpf_kprobe_multi_pt_regs_ptr() (NULL) +#endif + +static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip) +{ + unsigned long ip = ftrace_get_symaddr(fentry_ip); + + return ip ? : fentry_ip; +} + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2779,7 +2793,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs, + unsigned long entry_ip, struct ftrace_regs *fregs, bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { @@ -2791,6 +2805,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; + struct pt_regs *regs; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { @@ -2801,6 +2816,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); + regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr()); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); @@ -2814,26 +2830,28 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } static void kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); + kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 30e3ddc8a8a8..9e6b5a71555b 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -292,13 +292,15 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset) } /* ftrace_graph_entry set to this to tell some archs to run function graph */ -static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops) +static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { return 0; } /* ftrace_graph_return set to this to tell some archs to run function graph */ -static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops) +static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { } @@ -520,13 +522,15 @@ int __weak ftrace_disable_ftrace_graph_caller(void) #endif int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { return 0; } static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { } @@ -644,14 +648,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, #endif /* If the caller does not use ftrace, call this function. */ -int function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp) +int function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs) { struct ftrace_graph_ent trace; unsigned long bitmap = 0; int offset; + int bit; int i; + bit = ftrace_test_recursion_trylock(func, ret); + if (bit < 0) + return -EBUSY; + trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -663,7 +673,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (static_branch_likely(&fgraph_do_direct)) { int save_curr_ret_stack = current->curr_ret_stack; - if (static_call(fgraph_func)(&trace, fgraph_direct_gops)) + if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs)) bitmap |= BIT(fgraph_direct_gops->idx); else /* Clear out any saved storage */ @@ -681,7 +691,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, save_curr_ret_stack = current->curr_ret_stack; if (ftrace_ops_test(&gops->ops, func, NULL) && - gops->entryfunc(&trace, gops)) + gops->entryfunc(&trace, gops, fregs)) bitmap |= BIT(i); else /* Clear out any saved storage */ @@ -697,12 +707,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, * flag, set that bit always. */ set_bitmap(current, offset, bitmap | BIT(0)); - + ftrace_test_recursion_unlock(bit); return 0; out_ret: current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1; out: current->curr_ret_depth--; + ftrace_test_recursion_unlock(bit); return -EBUSY; } @@ -792,15 +803,12 @@ static struct notifier_block ftrace_suspend_notifier = { .notifier_call = ftrace_suspend_notifier_call, }; -/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */ -struct fgraph_ret_regs; - /* * Send the trace to the ring-buffer. * @return the original return address. */ -static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs, - unsigned long frame_pointer) +static inline unsigned long +__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer) { struct ftrace_ret_stack *ret_stack; struct ftrace_graph_ret trace; @@ -819,8 +827,11 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs } trace.rettime = trace_clock_local(); + if (fregs) + ftrace_regs_set_instruction_pointer(fregs, ret); + #ifdef CONFIG_FUNCTION_GRAPH_RETVAL - trace.retval = fgraph_ret_regs_return_value(ret_regs); + trace.retval = ftrace_regs_get_return_value(fregs); #endif bitmap = get_bitmap_bits(current, offset); @@ -828,7 +839,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs #ifdef CONFIG_HAVE_STATIC_CALL if (static_branch_likely(&fgraph_do_direct)) { if (test_bit(fgraph_direct_gops->idx, &bitmap)) - static_call(fgraph_retfunc)(&trace, fgraph_direct_gops); + static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs); } else #endif { @@ -838,7 +849,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs if (gops == &fgraph_stub) continue; - gops->retfunc(&trace, gops); + gops->retfunc(&trace, gops, fregs); } } @@ -855,14 +866,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs } /* - * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can - * leave only ftrace_return_to_handler(ret_regs). + * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can + * leave only ftrace_return_to_handler(fregs). */ -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs) +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs) { - return __ftrace_return_to_handler(ret_regs, - fgraph_ret_regs_frame_pointer(ret_regs)); + return __ftrace_return_to_handler(fregs, + ftrace_regs_get_frame_pointer(fregs)); } #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer) @@ -1010,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable) * Simply points to ftrace_stub, but with the proper protocol. * Defined by the linker script in linux/vmlinux.lds.h */ -void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); /* The callbacks that hook a function */ trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph; @@ -1174,7 +1186,8 @@ void ftrace_graph_exit_task(struct task_struct *t) #ifdef CONFIG_DYNAMIC_FTRACE static int fgraph_pid_func(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = gops->ops.private; int pid; @@ -1188,7 +1201,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace, return 0; } - return gops->saved_func(trace, gops); + return gops->saved_func(trace, gops, fregs); } void fgraph_update_pid_func(void) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9ff018245840..2560b312ad57 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -8,98 +8,224 @@ #include <linux/fprobe.h> #include <linux/kallsyms.h> #include <linux/kprobes.h> -#include <linux/rethook.h> +#include <linux/list.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <linux/sort.h> +#include <asm/fprobe.h> + #include "trace.h" -struct fprobe_rethook_node { - struct rethook_node node; - unsigned long entry_ip; - unsigned long entry_parent_ip; - char data[]; -}; +#define FPROBE_IP_HASH_BITS 8 +#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS) -static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) -{ - struct fprobe_rethook_node *fpr; - struct rethook_node *rh = NULL; - struct fprobe *fp; - void *entry_data = NULL; - int ret = 0; +#define FPROBE_HASH_BITS 6 +#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS) - fp = container_of(ops, struct fprobe, ops); +#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2)) - if (fp->exit_handler) { - rh = rethook_try_get(fp->rethook); - if (!rh) { - fp->nmissed++; - return; - } - fpr = container_of(rh, struct fprobe_rethook_node, node); - fpr->entry_ip = ip; - fpr->entry_parent_ip = parent_ip; - if (fp->entry_data_size) - entry_data = fpr->data; +/* + * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still + * exists. The key is the address of fprobe instance. + * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe + * instance related to the funciton address. The key is the ftrace IP + * address. + * + * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp + * are set NULL and delete those from both hash tables (by hlist_del_rcu). + * After an RCU grace period, the fprobe_hlist itself will be released. + * + * fprobe_table and fprobe_ip_table can be accessed from either + * - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held. + * - RCU hlist traversal under disabling preempt + */ +static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; +static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE]; +static DEFINE_MUTEX(fprobe_mutex); + +/* + * Find first fprobe in the hlist. It will be iterated twice in the entry + * probe, once for correcting the total required size, the second time is + * calling back the user handlers. + * Thus the hlist in the fprobe_table must be sorted and new probe needs to + * be added *before* the first fprobe. + */ +static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip) +{ + struct fprobe_hlist_node *node; + struct hlist_head *head; + + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (node->addr == ip) + return node; } + return NULL; +} +NOKPROBE_SYMBOL(find_first_fprobe_node); - if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data); +/* Node insertion and deletion requires the fprobe_mutex */ +static void insert_fprobe_node(struct fprobe_hlist_node *node) +{ + unsigned long ip = node->addr; + struct fprobe_hlist_node *next; + struct hlist_head *head; - /* If entry_handler returns !0, nmissed is not counted. */ - if (rh) { - if (ret) - rethook_recycle(rh); - else - rethook_hook(rh, ftrace_get_regs(fregs), true); + lockdep_assert_held(&fprobe_mutex); + + next = find_first_fprobe_node(ip); + if (next) { + hlist_add_before_rcu(&node->hlist, &next->hlist); + return; } + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_add_head_rcu(&node->hlist, head); } -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +/* Return true if there are synonims */ +static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - struct fprobe *fp; - int bit; + lockdep_assert_held(&fprobe_mutex); - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; + WRITE_ONCE(node->fp, NULL); + hlist_del_rcu(&node->hlist); + return !!find_first_fprobe_node(node->addr); +} - /* recursion detection has to go before any traceable function and - * all functions before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; +/* Check existence of the fprobe */ +static bool is_fprobe_still_exist(struct fprobe *fp) +{ + struct hlist_head *head; + struct fprobe_hlist *fph; + + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_for_each_entry_rcu(fph, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (fph->fp == fp) + return true; } - __fprobe_handler(ip, parent_ip, ops, fregs); - ftrace_test_recursion_unlock(bit); + return false; +} +NOKPROBE_SYMBOL(is_fprobe_still_exist); + +static int add_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + struct hlist_head *head; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (is_fprobe_still_exist(fp)) + return -EEXIST; + + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_add_head_rcu(&fp->hlist_array->hlist, head); + return 0; +} + +static int del_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (!is_fprobe_still_exist(fp)) + return -ENOENT; + + fph->fp = NULL; + hlist_del_rcu(&fph->hlist); + return 0; } -NOKPROBE_SYMBOL(fprobe_handler); -static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +/* The arch should encode fprobe_header info into one unsigned long */ +#define FPROBE_HEADER_SIZE_IN_LONG 1 + +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) { + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD || + !arch_fprobe_header_encodable(fp))) + return false; + + *stack = arch_encode_fprobe_header(fp, size_words); + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + *fp = arch_decode_fprobe_header_fp(*stack); + *size_words = arch_decode_fprobe_header_size(*stack); +} + +#else + +/* Generic fprobe_header */ +struct __fprobe_header { struct fprobe *fp; - int bit; + unsigned long size_words; +} __packed; - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; +#define FPROBE_HEADER_SIZE_IN_LONG SIZE_IN_LONG(sizeof(struct __fprobe_header)) - /* recursion detection has to go before any traceable function and - * all functions called before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD)) + return false; + + fph->fp = fp; + fph->size_words = size_words; + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + *fp = fph->fp; + *size_words = fph->size_words; +} + +#endif + +/* + * fprobe shadow stack management: + * Since fprobe shares a single fgraph_ops, it needs to share the stack entry + * among the probes on the same function exit. Note that a new probe can be + * registered before a target function is returning, we can not use the hash + * table to find the corresponding probes. Thus the probe address is stored on + * the shadow stack with its entry data size. + * + */ +static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + if (!fp->entry_handler) + return 0; + + return fp->entry_handler(fp, ip, parent_ip, fregs, data); +} +static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + int ret; /* * This user handler is shared with other kprobes and is not expected to be * called recursively. So if any other kprobe handler is running, this will @@ -108,44 +234,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, */ if (unlikely(kprobe_running())) { fp->nmissed++; - goto recursion_unlock; + return 0; } kprobe_busy_begin(); - __fprobe_handler(ip, parent_ip, ops, fregs); + ret = __fprobe_handler(ip, parent_ip, fp, fregs, data); kprobe_busy_end(); - -recursion_unlock: - ftrace_test_recursion_unlock(bit); + return ret; } -static void fprobe_exit_handler(struct rethook_node *rh, void *data, - unsigned long ret_ip, struct pt_regs *regs) +static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs) { - struct fprobe *fp = (struct fprobe *)data; - struct fprobe_rethook_node *fpr; - int bit; + struct fprobe_hlist_node *node, *first; + unsigned long *fgraph_data = NULL; + unsigned long func = trace->func; + unsigned long ret_ip; + int reserved_words; + struct fprobe *fp; + int used, ret; - if (!fp || fprobe_disabled(fp)) - return; + if (WARN_ON_ONCE(!fregs)) + return 0; - fpr = container_of(rh, struct fprobe_rethook_node, node); + first = node = find_first_fprobe_node(func); + if (unlikely(!first)) + return 0; + + reserved_words = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || !fp->exit_handler) + continue; + /* + * Since fprobe can be enabled until the next loop, we ignore the + * fprobe's disabled flag in this loop. + */ + reserved_words += + FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size); + } + node = first; + if (reserved_words) { + fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long)); + if (unlikely(!fgraph_data)) { + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (fp && !fprobe_disabled(fp)) + fp->nmissed++; + } + return 0; + } + } /* - * we need to assure no calls to traceable functions in-between the - * end of fprobe_handler and the beginning of fprobe_exit_handler. + * TODO: recursion detection has been done in the fgraph. Thus we need + * to add a callback to increment missed counter. */ - bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); - if (bit < 0) { - fp->nmissed++; + ret_ip = ftrace_regs_get_return_address(fregs); + used = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + int data_size; + void *data; + + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || fprobe_disabled(fp)) + continue; + + data_size = fp->entry_data_size; + if (data_size && fp->exit_handler) + data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG; + else + data = NULL; + + if (fprobe_shared_with_kprobes(fp)) + ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data); + else + ret = __fprobe_handler(func, ret_ip, fp, fregs, data); + + /* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */ + if (!ret && fp->exit_handler) { + int size_words = SIZE_IN_LONG(data_size); + + if (write_fprobe_header(&fgraph_data[used], fp, size_words)) + used += FPROBE_HEADER_SIZE_IN_LONG + size_words; + } + } + if (used < reserved_words) + memset(fgraph_data + used, 0, reserved_words - used); + + /* If any exit_handler is set, data must be used. */ + return used != 0; +} +NOKPROBE_SYMBOL(fprobe_entry); + +static void fprobe_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs) +{ + unsigned long *fgraph_data = NULL; + unsigned long ret_ip; + struct fprobe *fp; + int size, curr; + int size_words; + + fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size); + if (WARN_ON_ONCE(!fgraph_data)) return; + size_words = SIZE_IN_LONG(size); + ret_ip = ftrace_regs_get_instruction_pointer(fregs); + + preempt_disable(); + + curr = 0; + while (size_words > curr) { + read_fprobe_header(&fgraph_data[curr], &fp, &size); + if (!fp) + break; + curr += FPROBE_HEADER_SIZE_IN_LONG; + if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) { + if (WARN_ON_ONCE(curr + size > size_words)) + break; + fp->exit_handler(fp, trace->func, ret_ip, fregs, + size ? fgraph_data + curr : NULL); + } + curr += size; } + preempt_enable(); +} +NOKPROBE_SYMBOL(fprobe_return); + +static struct fgraph_ops fprobe_graph_ops = { + .entryfunc = fprobe_entry, + .retfunc = fprobe_return, +}; +static int fprobe_graph_active; - fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs, - fp->entry_data_size ? (void *)fpr->data : NULL); - ftrace_test_recursion_unlock(bit); +/* Add @addrs to the ftrace filter and register fgraph if needed. */ +static int fprobe_graph_add_ips(unsigned long *addrs, int num) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_graph_active) { + ret = register_ftrace_graph(&fprobe_graph_ops); + if (WARN_ON_ONCE(ret)) { + ftrace_free_filter(&fprobe_graph_ops.ops); + return ret; + } + } + fprobe_graph_active++; + return 0; +} + +/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ +static void fprobe_graph_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + fprobe_graph_active--; + if (!fprobe_graph_active) { + /* Q: should we unregister it ? */ + unregister_ftrace_graph(&fprobe_graph_ops); + return; + } + + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -NOKPROBE_SYMBOL(fprobe_exit_handler); static int symbols_cmp(const void *a, const void *b) { @@ -175,53 +440,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num) return ERR_PTR(-ENOENT); } -static void fprobe_init(struct fprobe *fp) -{ - fp->nmissed = 0; - if (fprobe_shared_with_kprobes(fp)) - fp->ops.func = fprobe_kprobe_handler; - else - fp->ops.func = fprobe_handler; - fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; -} +struct filter_match_data { + const char *filter; + const char *notfilter; + size_t index; + size_t size; + unsigned long *addrs; +}; -static int fprobe_init_rethook(struct fprobe *fp, int num) +static int filter_match_callback(void *data, const char *name, unsigned long addr) { - int size; + struct filter_match_data *match = data; - if (!fp->exit_handler) { - fp->rethook = NULL; + if (!glob_match(match->filter, name) || + (match->notfilter && glob_match(match->notfilter, name))) return 0; - } - /* Initialize rethook if needed */ - if (fp->nr_maxactive) - num = fp->nr_maxactive; - else - num *= num_possible_cpus() * 2; - if (num <= 0) - return -EINVAL; + if (!ftrace_location(addr)) + return 0; + + if (match->addrs) + match->addrs[match->index] = addr; - size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + match->index++; + return match->index == match->size; +} - /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); - if (IS_ERR(fp->rethook)) - return PTR_ERR(fp->rethook); +/* + * Make IP list from the filter/no-filter glob patterns. + * Return the number of matched symbols, or -ENOENT. + */ +static int ip_list_from_filter(const char *filter, const char *notfilter, + unsigned long *addrs, size_t size) +{ + struct filter_match_data match = { .filter = filter, .notfilter = notfilter, + .index = 0, .size = size, .addrs = addrs}; + int ret; - return 0; + ret = kallsyms_on_each_symbol(filter_match_callback, &match); + if (ret < 0) + return ret; + ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match); + if (ret < 0) + return ret; + + return match.index ?: -ENOENT; } static void fprobe_fail_cleanup(struct fprobe *fp) { - if (!IS_ERR_OR_NULL(fp->rethook)) { - /* Don't need to cleanup rethook->handler because this is not used. */ - rethook_free(fp->rethook); - fp->rethook = NULL; + kfree(fp->hlist_array); + fp->hlist_array = NULL; +} + +/* Initialize the fprobe data structure. */ +static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) +{ + struct fprobe_hlist *hlist_array; + unsigned long addr; + int size, i; + + if (!fp || !addrs || num <= 0) + return -EINVAL; + + size = ALIGN(fp->entry_data_size, sizeof(long)); + if (size > MAX_FPROBE_DATA_SIZE) + return -E2BIG; + fp->entry_data_size = size; + + hlist_array = kzalloc(struct_size(hlist_array, array, num), GFP_KERNEL); + if (!hlist_array) + return -ENOMEM; + + fp->nmissed = 0; + + hlist_array->size = num; + fp->hlist_array = hlist_array; + hlist_array->fp = fp; + for (i = 0; i < num; i++) { + hlist_array->array[i].fp = fp; + addr = ftrace_location(addrs[i]); + if (!addr) { + fprobe_fail_cleanup(fp); + return -ENOENT; + } + hlist_array->array[i].addr = addr; } - ftrace_free_filter(&fp->ops); + return 0; } +#define FPROBE_IPS_MAX INT_MAX + /** * register_fprobe() - Register fprobe to ftrace by pattern. * @fp: A fprobe data structure to be registered. @@ -235,46 +544,24 @@ static void fprobe_fail_cleanup(struct fprobe *fp) */ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) { - struct ftrace_hash *hash; - unsigned char *str; - int ret, len; + unsigned long *addrs; + int ret; if (!fp || !filter) return -EINVAL; - fprobe_init(fp); - - len = strlen(filter); - str = kstrdup(filter, GFP_KERNEL); - ret = ftrace_set_filter(&fp->ops, str, len, 0); - kfree(str); - if (ret) + ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX); + if (ret < 0) return ret; - if (notfilter) { - len = strlen(notfilter); - str = kstrdup(notfilter, GFP_KERNEL); - ret = ftrace_set_notrace(&fp->ops, str, len, 0); - kfree(str); - if (ret) - goto out; - } - - /* TODO: - * correctly calculate the total number of filtered symbols - * from both filter and notfilter. - */ - hash = rcu_access_pointer(fp->ops.local_hash.filter_hash); - if (WARN_ON_ONCE(!hash)) - goto out; - - ret = fprobe_init_rethook(fp, (int)hash->count); - if (!ret) - ret = register_ftrace_function(&fp->ops); + addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + ret = ip_list_from_filter(filter, notfilter, addrs, ret); + if (ret > 0) + ret = register_fprobe_ips(fp, addrs, ret); -out: - if (ret) - fprobe_fail_cleanup(fp); + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(register_fprobe); @@ -282,7 +569,7 @@ EXPORT_SYMBOL_GPL(register_fprobe); /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. - * @addrs: An array of target ftrace location addresses. + * @addrs: An array of target function address. * @num: The number of entries of @addrs. * * Register @fp to ftrace for enabling the probe on the address given by @addrs. @@ -294,23 +581,27 @@ EXPORT_SYMBOL_GPL(register_fprobe); */ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) { - int ret; - - if (!fp || !addrs || num <= 0) - return -EINVAL; - - fprobe_init(fp); + struct fprobe_hlist *hlist_array; + int ret, i; - ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0); + ret = fprobe_init(fp, addrs, num); if (ret) return ret; - ret = fprobe_init_rethook(fp, num); - if (!ret) - ret = register_ftrace_function(&fp->ops); + mutex_lock(&fprobe_mutex); + + hlist_array = fp->hlist_array; + ret = fprobe_graph_add_ips(addrs, num); + if (!ret) { + add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size; i++) + insert_fprobe_node(&hlist_array->array[i]); + } + mutex_unlock(&fprobe_mutex); if (ret) fprobe_fail_cleanup(fp); + return ret; } EXPORT_SYMBOL_GPL(register_fprobe_ips); @@ -348,14 +639,13 @@ EXPORT_SYMBOL_GPL(register_fprobe_syms); bool fprobe_is_registered(struct fprobe *fp) { - if (!fp || (fp->ops.saved_func != fprobe_handler && - fp->ops.saved_func != fprobe_kprobe_handler)) + if (!fp || !fp->hlist_array) return false; return true; } /** - * unregister_fprobe() - Unregister fprobe from ftrace + * unregister_fprobe() - Unregister fprobe. * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). @@ -364,23 +654,41 @@ bool fprobe_is_registered(struct fprobe *fp) */ int unregister_fprobe(struct fprobe *fp) { - int ret; + struct fprobe_hlist *hlist_array; + unsigned long *addrs = NULL; + int ret = 0, i, count; - if (!fprobe_is_registered(fp)) - return -EINVAL; + mutex_lock(&fprobe_mutex); + if (!fp || !is_fprobe_still_exist(fp)) { + ret = -EINVAL; + goto out; + } + + hlist_array = fp->hlist_array; + addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) { + ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ + goto out; + } - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_stop(fp->rethook); + /* Remove non-synonim ips from table and hash */ + count = 0; + for (i = 0; i < hlist_array->size; i++) { + if (!delete_fprobe_node(&hlist_array->array[i])) + addrs[count++] = hlist_array->array[i].addr; + } + del_fprobe_hash(fp); - ret = unregister_ftrace_function(&fp->ops); - if (ret < 0) - return ret; + if (count) + fprobe_graph_remove_ips(addrs, count); - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_free(fp->rethook); + kfree_rcu(hlist_array, rcu); + fp->hlist_array = NULL; - ftrace_free_filter(&fp->ops); +out: + mutex_unlock(&fprobe_mutex); + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(unregister_fprobe); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2e113f8b13a2..b2955e504193 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; - int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); /* we raced with function_profile_reset() */ - if (unlikely(rec->counter == 0)) { - ret = -EBUSY; - goto out; - } + if (unlikely(rec->counter == 0)) + return -EBUSY; #ifdef CONFIG_FUNCTION_GRAPH_TRACER avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) - goto out; + return 0; #endif kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); @@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v) trace_print_seq(m, &s); #endif seq_putc(m, '\n'); -out: - mutex_unlock(&ftrace_profile_lock); - return ret; + return 0; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -789,27 +784,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; - unsigned long flags; if (!ftrace_profile_enabled) return; - local_irq_save(flags); + guard(preempt_notrace)(); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; rec = ftrace_find_profiled_func(stat, ip); if (!rec) { rec = ftrace_profile_alloc(stat, ip); if (!rec) - goto out; + return; } rec->counter++; - out: - local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -827,7 +819,8 @@ struct profile_fgraph_data { }; static int profile_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; @@ -849,26 +842,27 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace, } static void profile_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; struct ftrace_profile_stat *stat; unsigned long long calltime; unsigned long long rettime = trace_clock_local(); struct ftrace_profile *rec; - unsigned long flags; int size; - local_irq_save(flags); + guard(preempt_notrace)(); + stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; profile_data = fgraph_retrieve_data(gops->idx, &size); /* If the calltime was zero'd ignore it */ if (!profile_data || !profile_data->calltime) - goto out; + return; calltime = rettime - profile_data->calltime; @@ -896,9 +890,6 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, rec->time += calltime; rec->time_squared += calltime * calltime; } - - out: - local_irq_restore(flags); } static struct fgraph_ops fprofiler_ops = { @@ -946,20 +937,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, val = !!val; - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); if (ftrace_profile_enabled ^ val) { if (val) { ret = ftrace_profile_init(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ret = register_ftrace_profiler(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ftrace_profile_enabled = 1; } else { ftrace_profile_enabled = 0; @@ -970,8 +957,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, unregister_ftrace_profiler(); } } - out: - mutex_unlock(&ftrace_profile_lock); *ppos += cnt; @@ -1671,14 +1656,12 @@ unsigned long ftrace_location(unsigned long ip) loc = ftrace_location_range(ip, ip); if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) - goto out; + return 0; /* map sym+0 to __fentry__ */ if (!offset) loc = ftrace_location_range(ip, ip + size - 1); } - -out: return loc; } @@ -2073,7 +2056,7 @@ rollback: continue; if (rec == end) - goto err_out; + return -EBUSY; in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -2086,7 +2069,6 @@ rollback: rec->flags |= FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); -err_out: return -EBUSY; } @@ -4982,10 +4964,6 @@ static int cache_mod(struct trace_array *tr, return ftrace_add_mod(tr, func, module, enable); } -static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable); - #ifdef CONFIG_MODULES static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, char *mod, bool enable) @@ -5615,20 +5593,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex); __init int register_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p; - int ret = 0; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &ftrace_commands); - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return 0; } /* @@ -5638,20 +5611,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd) __init int unregister_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p, *n; - int ret = -ENODEV; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -ENODEV; } static int ftrace_process_regex(struct ftrace_iterator *iter, @@ -5661,7 +5631,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, struct trace_array *tr = iter->ops->private; char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); @@ -5678,17 +5648,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, command = strsep(&next, ":"); - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->func(tr, hash, func, command, next, enable); - goto out_unlock; - } + if (strcmp(p->name, command) == 0) + return p->func(tr, hash, func, command, next, enable); } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -EINVAL; } static ssize_t @@ -5722,12 +5689,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser->idx, enable); trace_parser_clear(parser); if (ret < 0) - goto out; + return ret; } - ret = read; - out: - return ret; + return read; } ssize_t @@ -5788,7 +5753,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips, static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long *ips, unsigned int cnt, - int remove, int reset, int enable) + int remove, int reset, int enable, char *mod) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -5814,7 +5779,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, goto out_regex_unlock; } - if (buf && !ftrace_match_records(hash, buf, len)) { + if (buf && !match_records(hash, buf, len, mod)) { + /* If this was for a module and nothing was enabled, flag it */ + if (mod) + (*orig_hash)->flags |= FTRACE_HASH_FL_MOD; + + /* + * Even if it is a mod, return error to let caller know + * nothing was added + */ ret = -EINVAL; goto out_regex_unlock; } @@ -5839,7 +5812,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset, int enable) { - return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL); } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -6217,7 +6190,38 @@ static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable) { - return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable); + char *mod = NULL, *func, *command, *next = buf; + char *tmp __free(kfree) = NULL; + struct trace_array *tr = ops->private; + int ret; + + func = strsep(&next, ":"); + + /* This can also handle :mod: parsing */ + if (next) { + if (!tr) + return -EINVAL; + + command = strsep(&next, ":"); + if (strcmp(command, "mod") != 0) + return -EINVAL; + + mod = next; + len = command - func; + /* Save the original func as ftrace_set_hash() can modify it */ + tmp = kstrdup(func, GFP_KERNEL); + } + + ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod); + + if (tr && mod && ret < 0) { + /* Did tmp fail to allocate? */ + if (!tmp) + return -ENOMEM; + ret = cache_mod(tr, tmp, mod, enable); + } + + return ret; } /** @@ -6381,6 +6385,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) ftrace_ops_init(ops); + /* The trace_array is needed for caching module function filters */ + if (!ops->private) { + struct trace_array *tr = trace_get_global_array(); + + ops->private = tr; + ftrace_init_trace_array(tr); + } + while (buf) { func = strsep(&buf, ","); ftrace_set_regex(ops, func, strlen(func), 0, enable); @@ -7814,9 +7826,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) void ftrace_init_trace_array(struct trace_array *tr) { + if (tr->flags & TRACE_ARRAY_FL_MOD_INIT) + return; + INIT_LIST_HEAD(&tr->func_probes); INIT_LIST_HEAD(&tr->mod_trace); INIT_LIST_HEAD(&tr->mod_notrace); + + tr->flags |= TRACE_ARRAY_FL_MOD_INIT; } #else @@ -7845,7 +7862,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) __init void ftrace_init_global_array_ops(struct trace_array *tr) { tr->ops = &global_ops; - tr->ops->private = tr; + if (!global_ops.private) + global_ops.private = tr; ftrace_init_trace_array(tr); init_array_fgraph_ops(tr, tr->ops); } @@ -8287,7 +8305,7 @@ pid_write(struct file *filp, const char __user *ubuf, if (!cnt) return 0; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); switch (type) { case TRACE_PIDS: @@ -8303,14 +8321,13 @@ pid_write(struct file *filp, const char __user *ubuf, lockdep_is_held(&ftrace_lock)); break; default: - ret = -EINVAL; WARN_ON_ONCE(1); - goto out; + return -EINVAL; } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; switch (type) { case TRACE_PIDS: @@ -8339,11 +8356,8 @@ pid_write(struct file *filp, const char __user *ubuf, ftrace_update_pid_func(); ftrace_startup_all(0); - out: - mutex_unlock(&ftrace_lock); - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -8746,17 +8760,17 @@ static int ftrace_enable_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret = -ENODEV; + int ret; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); if (unlikely(ftrace_disabled)) - goto out; + return -ENODEV; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) - goto out; + return ret; if (ftrace_enabled) { @@ -8770,8 +8784,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } else { if (is_permanent_ops_registered()) { ftrace_enabled = true; - ret = -EBUSY; - goto out; + return -EBUSY; } /* stopping ftrace calls (just send to ftrace_stub) */ @@ -8781,9 +8794,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } last_ftrace_enabled = !!ftrace_enabled; - out: - mutex_unlock(&ftrace_lock); - return ret; + return 0; } static struct ctl_table ftrace_sysctls[] = { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 60210fb5b211..6d61ff78926b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4682,40 +4682,22 @@ int ring_buffer_write(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_write); -static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +/* + * The total entries in the ring buffer is the running counter + * of entries entered into the ring buffer, minus the sum of + * the entries read from the ring buffer and the number of + * entries that were overwritten. + */ +static inline unsigned long +rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) { - struct buffer_page *reader = cpu_buffer->reader_page; - struct buffer_page *head = rb_set_head_page(cpu_buffer); - struct buffer_page *commit = cpu_buffer->commit_page; - - /* In case of error, head will be NULL */ - if (unlikely(!head)) - return true; - - /* Reader should exhaust content in reader page */ - if (reader->read != rb_page_size(reader)) - return false; - - /* - * If writers are committing on the reader page, knowing all - * committed content has been read, the ring buffer is empty. - */ - if (commit == reader) - return true; - - /* - * If writers are committing on a page other than reader page - * and head page, there should always be content to read. - */ - if (commit != head) - return false; + return local_read(&cpu_buffer->entries) - + (local_read(&cpu_buffer->overrun) + cpu_buffer->read); +} - /* - * Writers are committing on the head page, we just need - * to care about there're committed data, and the reader will - * swap reader page with head page when it is to read data. - */ - return rb_page_commit(commit) == 0; +static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +{ + return !rb_num_of_entries(cpu_buffer); } /** @@ -4861,19 +4843,6 @@ void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); -/* - * The total entries in the ring buffer is the running counter - * of entries entered into the ring buffer, minus the sum of - * the entries read from the ring buffer and the number of - * entries that were overwritten. - */ -static inline unsigned long -rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) -{ - return local_read(&cpu_buffer->entries) - - (local_read(&cpu_buffer->overrun) + cpu_buffer->read); -} - /** * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer * @buffer: The ring buffer @@ -7059,7 +7028,7 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, } while (p < nr_pages) { - struct page *page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + struct page *page; int off = 0; if (WARN_ON_ONCE(s >= nr_subbufs)) { @@ -7067,6 +7036,8 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, goto out; } + page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + for (; off < (1 << (subbuf_order)); off++, page++) { if (p >= nr_pages) break; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b6e40e8791fa..2542ec398b5d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10661,6 +10661,14 @@ out: return ret; } +#ifdef CONFIG_FUNCTION_TRACER +/* Used to set module cached ftrace filtering at boot up */ +__init struct trace_array *trace_get_global_array(void) +{ + return &global_trace; +} +#endif + void __init ftrace_boot_snapshot(void) { #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 179676db622e..04058a9889b7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -432,6 +432,7 @@ struct trace_array { enum { TRACE_ARRAY_FL_GLOBAL = BIT(0), TRACE_ARRAY_FL_BOOT = BIT(1), + TRACE_ARRAY_FL_MOD_INIT = BIT(2), }; extern struct list_head ftrace_trace_arrays; @@ -693,8 +694,10 @@ void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); -void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); -int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); +void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); +int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -1112,6 +1115,7 @@ void ftrace_destroy_function_files(struct trace_array *tr); int ftrace_allocate_ftrace_ops(struct trace_array *tr); void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); +struct trace_array *trace_get_global_array(void); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index c62d1629cffe..b8f3c4ba309b 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -134,7 +134,7 @@ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base) { - struct pt_regs *regs = rec; + struct ftrace_regs *fregs = rec; unsigned long val; int ret; @@ -142,17 +142,17 @@ retry: /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_STACK: - val = regs_get_kernel_stack_nth(regs, code->param); + val = ftrace_regs_get_kernel_stack_nth(fregs, code->param); break; case FETCH_OP_STACKP: - val = kernel_stack_pointer(regs); + val = ftrace_regs_get_stack_pointer(fregs); break; case FETCH_OP_RETVAL: - val = regs_return_value(regs); + val = ftrace_regs_get_return_value(fregs); break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: - val = regs_get_kernel_argument(regs, code->param); + val = ftrace_regs_get_argument(fregs, code->param); break; case FETCH_OP_EDATA: val = *(unsigned long *)((unsigned long)edata + code->offset); @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(process_fetch_insn) /* function entry handler */ static nokprobe_inline void __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs, + struct ftrace_regs *fregs, struct trace_event_file *trace_file) { struct fentry_trace_entry_head *entry; @@ -189,41 +189,71 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fentry_trace_func(tf, entry_ip, regs, link->file); + __fentry_trace_func(tf, entry_ip, fregs, link->file); } NOKPROBE_SYMBOL(fentry_trace_func); +static nokprobe_inline +void store_fprobe_entry_data(void *edata, struct trace_probe *tp, struct ftrace_regs *fregs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val = 0; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = ftrace_regs_get_argument(fregs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} + /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (tf->tp.entry_arg) - store_trace_entry_data(entry_data, &tf->tp, regs); + store_fprobe_entry_data(entry_data, &tf->tp, fregs); return 0; } @@ -231,7 +261,7 @@ NOKPROBE_SYMBOL(trace_fprobe_entry_handler) static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; @@ -245,60 +275,63 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, void *entry_data) + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); #ifdef CONFIG_PERF_EVENTS static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fentry_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return 0; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -307,31 +340,34 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -339,33 +375,34 @@ NOKPROBE_SYMBOL(fexit_perf_func); #endif /* CONFIG_PERF_EVENTS */ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); int ret = 0; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fentry_trace_func(tf, entry_ip, regs); + fentry_trace_func(tf, entry_ip, fregs); + #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - ret = fentry_perf_func(tf, entry_ip, regs); + ret = fentry_perf_func(tf, entry_ip, fregs); #endif return ret; } NOKPROBE_SYMBOL(fentry_dispatcher); static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); @@ -379,6 +416,9 @@ static void free_trace_fprobe(struct trace_fprobe *tf) } } +/* Since alloc_trace_fprobe() can return error, check the pointer is ERR too. */ +DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) free_trace_fprobe(_T)) + /* * Allocate new trace_probe and initialize it (including fprobe). */ @@ -387,10 +427,9 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, const char *symbol, struct tracepoint *tpoint, struct module *mod, - int maxactive, int nargs, bool is_return) { - struct trace_fprobe *tf; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int ret = -ENOMEM; tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL); @@ -399,7 +438,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->symbol = kstrdup(symbol, GFP_KERNEL); if (!tf->symbol) - goto error; + return ERR_PTR(-ENOMEM); if (is_return) tf->fp.exit_handler = fexit_dispatcher; @@ -408,17 +447,13 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->mod = mod; - tf->fp.nr_maxactive = maxactive; ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tf->devent, &trace_fprobe_ops); - return tf; -error: - free_trace_fprobe(tf); - return ERR_PTR(ret); + return_ptr(tf); } static struct trace_fprobe *find_trace_fprobe(const char *event, @@ -845,14 +880,12 @@ static int register_trace_fprobe(struct trace_fprobe *tf) struct trace_fprobe *old_tf; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tf = find_trace_fprobe(trace_probe_name(&tf->tp), trace_probe_group_name(&tf->tp)); - if (old_tf) { - ret = append_trace_fprobe(tf, old_tf); - goto end; - } + if (old_tf) + return append_trace_fprobe(tf, old_tf); /* Register new event */ ret = register_fprobe_event(tf); @@ -862,7 +895,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register fprobe */ @@ -872,8 +905,6 @@ static int register_trace_fprobe(struct trace_fprobe *tf) else dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -1034,7 +1065,10 @@ static int parse_symbol_and_return(int argc, const char *argv[], return 0; } -static int __trace_fprobe_create(int argc, const char *argv[]) +DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T)) + +static int trace_fprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -1060,24 +1094,20 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_fprobe *tf = NULL; - int i, len, new_argc = 0, ret = 0; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; + int i, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL; + char *symbol __free(kfree) = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; - const char **new_argv = NULL; - int maxactive = 0; + const char **new_argv __free(kfree) = NULL; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; + char *dbuf __free(kfree) = NULL; bool is_tracepoint = false; - struct module *tp_mod = NULL; + struct module *tp_mod __free(module_put) = NULL; struct tracepoint *tpoint = NULL; - struct traceprobe_parse_context ctx = { - .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, - }; if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2) return -ECANCELED; @@ -1087,35 +1117,13 @@ static int __trace_fprobe_create(int argc, const char *argv[]) group = TRACEPOINT_EVENT_SYSTEM; } - trace_probe_log_init("trace_fprobe", argc, argv); - - event = strchr(&argv[0][1], ':'); - if (event) - event++; - - if (isdigit(argv[0][1])) { - if (event) - len = event - &argv[0][1] - 1; - else - len = strlen(&argv[0][1]); - if (len > MAX_EVENT_NAME_LEN - 1) { - trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - memcpy(buf, &argv[0][1], len); - buf[len] = '\0'; - ret = kstrtouint(buf, 0, &maxactive); - if (ret || !maxactive) { + if (argv[0][1] != '\0') { + if (argv[0][1] != ':') { + trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - /* fprobe rethook instances are iterated over via a list. The - * maximum should stay reasonable. - */ - if (maxactive > RETHOOK_MAXACTIVE_MAX) { - trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; + return -EINVAL; } + event = &argv[0][2]; } trace_probe_log_set_index(1); @@ -1123,20 +1131,14 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* a symbol(or tracepoint) must be specified */ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint); if (ret < 0) - goto parse_error; - - if (!is_return && maxactive) { - trace_probe_log_set_index(0); - trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; - } + return -EINVAL; trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return -EINVAL; } if (!event) { @@ -1152,67 +1154,62 @@ static int __trace_fprobe_create(int argc, const char *argv[]) } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; else - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; if (is_tracepoint) { - ctx.flags |= TPARG_FL_TPOINT; + ctx->flags |= TPARG_FL_TPOINT; tpoint = find_tracepoint(symbol, &tp_mod); if (tpoint) { - ctx.funcname = kallsyms_lookup( + ctx->funcname = kallsyms_lookup( (unsigned long)tpoint->probestub, NULL, NULL, NULL, sbuf); } else if (IS_ENABLED(CONFIG_MODULES)) { /* This *may* be loaded afterwards */ tpoint = TRACEPOINT_STUB; - ctx.funcname = symbol; + ctx->funcname = symbol; } else { trace_probe_log_set_index(1); trace_probe_log_err(0, NO_TRACEPOINT); - goto parse_error; + return -EINVAL; } } else - ctx.funcname = symbol; + ctx->funcname = symbol; argc -= 2; argv += 2; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); - if (IS_ERR(new_argv)) { - ret = PTR_ERR(new_argv); - new_argv = NULL; - goto out; - } + abuf, MAX_BTF_ARGS_LEN, ctx); + if (IS_ERR(new_argv)) + return PTR_ERR(new_argv); if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, - maxactive, argc, is_return); + argc, is_return); if (IS_ERR(tf)) { ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tf is not allocated */ + return ret; } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], ctx); if (ret) - goto error; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } if (is_return && tf->tp.entry_arg) { @@ -1223,7 +1220,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) - goto error; + return ret; ret = register_trace_fprobe(tf); if (ret) { @@ -1234,29 +1231,32 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; + return -EINVAL; } -out: - if (tp_mod) - module_put(tp_mod); + /* 'tf' is successfully registered. To avoid freeing, assign NULL. */ + tf = NULL; + + return 0; +} + +static int trace_fprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { + .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, + }; + int ret; + + trace_probe_log_init("trace_fprobe", argc, argv); + ret = trace_fprobe_create_internal(argc, argv, &ctx); traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; - -parse_error: - ret = -EINVAL; -error: - free_trace_fprobe(tf); - goto out; } static int trace_fprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_fprobe_create); + return trace_probe_create(raw_command, trace_fprobe_create_cb); } static int trace_fprobe_release(struct dyn_event *ev) @@ -1278,8 +1278,6 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev) seq_putc(m, 't'); else seq_putc(m, 'f'); - if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive) - seq_printf(m, "%d", tf->fp.nr_maxactive); seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp), trace_probe_name(&tf->tp)); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 5504b5e4e7b4..dc62eb93837a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -175,16 +175,16 @@ struct fgraph_times { }; int trace_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; - int ret; + int ret = 0; int cpu; if (*task_var & TRACE_GRAPH_NOTRACE) @@ -235,25 +235,21 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, if (tracing_thresh) return 1; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); - if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && - tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) { + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); + if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && + tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) { unsigned long retaddr = ftrace_graph_top_ret_addr(current); - ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr); - } else + } else { ret = __trace_graph_entry(tr, trace, trace_ctx); - } else { - ret = 0; + } } - - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); return ret; } @@ -314,13 +310,12 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace, } void trace_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; int size; @@ -341,20 +336,20 @@ void trace_graph_return(struct ftrace_graph_ret *trace, trace->calltime = ftimes->calltime; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); __trace_graph_return(tr, trace, trace_ctx); } - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_times *ftimes; int size; @@ -378,7 +373,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, (trace->rettime - ftimes->calltime < tracing_thresh)) return; else - trace_graph_return(trace, gops); + trace_graph_return(trace, gops, fregs); } static struct fgraph_ops funcgraph_ops = { diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index a4e799c1e767..08786c59d397 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set) } static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; @@ -214,7 +215,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, } static void irqsoff_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 2caf0d2afb32..f39b37fcdb3b 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) +__get_data_size(struct trace_probe *tp, void *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index c58292e424d5..f372252dc8bb 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set) } static int wakeup_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; @@ -150,7 +151,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, } static void wakeup_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 38b5754790c9..d88c44f1dfa5 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -774,7 +774,8 @@ struct fgraph_fixture { }; static __init int store_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -807,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace, } static __init void store_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -1025,7 +1027,8 @@ static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { /* This is harmlessly racy, we want to approximately detect a hang */ if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { @@ -1039,7 +1042,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, return 0; } - return trace_graph_entry(trace, gops); + return trace_graph_entry(trace, gops, fregs); } static struct fgraph_ops fgraph_ops __initdata = { |