From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- mm/kasan/common.c | 630 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 630 insertions(+) create mode 100644 mm/kasan/common.c (limited to 'mm/kasan/common.c') diff --git a/mm/kasan/common.c b/mm/kasan/common.c new file mode 100644 index 000000000..b7d05c2a6 --- /dev/null +++ b/mm/kasan/common.c @@ -0,0 +1,630 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common KASAN code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * Some code borrowed from https://github.com/xairy/kasan-prototype by + * Andrey Konovalov + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kasan.h" +#include "../slab.h" + +#if defined(CONFIG_ARCH_DEFER_KASAN) || defined(CONFIG_KASAN_HW_TAGS) +/* + * Definition of the unified static key declared in kasan-enabled.h. + * This provides consistent runtime enable/disable across KASAN modes. + */ +DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled); +EXPORT_SYMBOL_GPL(kasan_flag_enabled); +#endif + +struct slab *kasan_addr_to_slab(const void *addr) +{ + if (virt_addr_valid(addr)) + return virt_to_slab(addr); + return NULL; +} + +depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags) +{ + unsigned long entries[KASAN_STACK_DEPTH]; + unsigned int nr_entries; + + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); + return stack_depot_save_flags(entries, nr_entries, flags, depot_flags); +} + +void kasan_set_track(struct kasan_track *track, depot_stack_handle_t stack) +{ +#ifdef CONFIG_KASAN_EXTRA_INFO + u32 cpu = raw_smp_processor_id(); + u64 ts_nsec = local_clock(); + + track->cpu = cpu; + track->timestamp = ts_nsec >> 9; +#endif /* CONFIG_KASAN_EXTRA_INFO */ + track->pid = current->pid; + track->stack = stack; +} + +void kasan_save_track(struct kasan_track *track, gfp_t flags) +{ + depot_stack_handle_t stack; + + stack = kasan_save_stack(flags, STACK_DEPOT_FLAG_CAN_ALLOC); + kasan_set_track(track, stack); +} + +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +void kasan_enable_current(void) +{ + current->kasan_depth++; +} +EXPORT_SYMBOL(kasan_enable_current); + +void kasan_disable_current(void) +{ + current->kasan_depth--; +} +EXPORT_SYMBOL(kasan_disable_current); + +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +void __kasan_unpoison_range(const void *address, size_t size) +{ + if (is_kfence_address(address)) + return; + + kasan_unpoison(address, size, false); +} + +#ifdef CONFIG_KASAN_STACK +/* Unpoison the entire stack for a task. */ +void kasan_unpoison_task_stack(struct task_struct *task) +{ + void *base = task_stack_page(task); + + kasan_unpoison(base, THREAD_SIZE, false); +} + +/* Unpoison the stack for the current task beyond a watermark sp value. */ +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) +{ + /* + * Calculate the task stack base address. Avoid using 'current' + * because this function is called by early resume code which hasn't + * yet set up the percpu register (%gs). + */ + void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1)); + + kasan_unpoison(base, watermark - base, false); +} +#endif /* CONFIG_KASAN_STACK */ + +bool __kasan_unpoison_pages(struct page *page, unsigned int order, bool init) +{ + u8 tag; + unsigned long i; + + if (unlikely(PageHighMem(page))) + return false; + + if (!kasan_sample_page_alloc(order)) + return false; + + tag = kasan_random_tag(); + kasan_unpoison(set_tag(page_address(page), tag), + PAGE_SIZE << order, init); + for (i = 0; i < (1 << order); i++) + page_kasan_tag_set(page + i, tag); + + return true; +} + +void __kasan_poison_pages(struct page *page, unsigned int order, bool init) +{ + if (likely(!PageHighMem(page))) + kasan_poison(page_address(page), PAGE_SIZE << order, + KASAN_PAGE_FREE, init); +} + +void __kasan_poison_slab(struct slab *slab) +{ + struct page *page = slab_page(slab); + unsigned long i; + + for (i = 0; i < compound_nr(page); i++) + page_kasan_tag_reset(page + i); + kasan_poison(page_address(page), page_size(page), + KASAN_SLAB_REDZONE, false); +} + +void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object) +{ + kasan_unpoison(object, cache->object_size, false); +} + +void __kasan_poison_new_object(struct kmem_cache *cache, void *object) +{ + kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), + KASAN_SLAB_REDZONE, false); +} + +/* + * This function assigns a tag to an object considering the following: + * 1. A cache might have a constructor, which might save a pointer to a slab + * object somewhere (e.g. in the object itself). We preassign a tag for + * each object in caches with constructors during slab creation and reuse + * the same tag each time a particular object is allocated. + * 2. A cache might be SLAB_TYPESAFE_BY_RCU, which means objects can be + * accessed after being freed. We preassign tags for objects in these + * caches as well. + */ +static inline u8 assign_tag(struct kmem_cache *cache, + const void *object, bool init) +{ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + return 0xff; + + /* + * If the cache neither has a constructor nor has SLAB_TYPESAFE_BY_RCU + * set, assign a tag when the object is being allocated (init == false). + */ + if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU)) + return init ? KASAN_TAG_KERNEL : kasan_random_tag(); + + /* + * For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU, + * assign a random tag during slab creation, otherwise reuse + * the already assigned tag. + */ + return init ? kasan_random_tag() : get_tag(object); +} + +void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache, + const void *object) +{ + /* Initialize per-object metadata if it is present. */ + if (kasan_requires_meta()) + kasan_init_object_meta(cache, object); + + /* Tag is ignored in set_tag() without CONFIG_KASAN_SW/HW_TAGS */ + object = set_tag(object, assign_tag(cache, object, true)); + + return (void *)object; +} + +/* Returns true when freeing the object is not safe. */ +static bool check_slab_allocation(struct kmem_cache *cache, void *object, + unsigned long ip) +{ + void *tagged_object = object; + + object = kasan_reset_tag(object); + + if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) { + kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_INVALID_FREE); + return true; + } + + if (!kasan_byte_accessible(tagged_object)) { + kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_DOUBLE_FREE); + return true; + } + + return false; +} + +static inline void poison_slab_object(struct kmem_cache *cache, void *object, + bool init) +{ + void *tagged_object = object; + + object = kasan_reset_tag(object); + + kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), + KASAN_SLAB_FREE, init); + + if (kasan_stack_collection_enabled()) + kasan_save_free_info(cache, tagged_object); +} + +bool __kasan_slab_pre_free(struct kmem_cache *cache, void *object, + unsigned long ip) +{ + if (is_kfence_address(object)) + return false; + return check_slab_allocation(cache, object, ip); +} + +bool __kasan_slab_free(struct kmem_cache *cache, void *object, bool init, + bool still_accessible, bool no_quarantine) +{ + if (is_kfence_address(object)) + return false; + + /* + * If this point is reached with an object that must still be + * accessible under RCU, we can't poison it; in that case, also skip the + * quarantine. This should mostly only happen when CONFIG_SLUB_RCU_DEBUG + * has been disabled manually. + * + * Putting the object on the quarantine wouldn't help catch UAFs (since + * we can't poison it here), and it would mask bugs caused by + * SLAB_TYPESAFE_BY_RCU users not being careful enough about object + * reuse; so overall, putting the object into the quarantine here would + * be counterproductive. + */ + if (still_accessible) + return false; + + poison_slab_object(cache, object, init); + + if (no_quarantine) + return false; + + /* + * If the object is put into quarantine, do not let slab put the object + * onto the freelist for now. The object's metadata is kept until the + * object gets evicted from quarantine. + */ + if (kasan_quarantine_put(cache, object)) + return true; + + /* + * Note: Keep per-object metadata to allow KASAN print stack traces for + * use-after-free-before-realloc bugs. + */ + + /* Let slab put the object onto the freelist. */ + return false; +} + +static inline bool check_page_allocation(void *ptr, unsigned long ip) +{ + if (ptr != page_address(virt_to_head_page(ptr))) { + kasan_report_invalid_free(ptr, ip, KASAN_REPORT_INVALID_FREE); + return true; + } + + if (!kasan_byte_accessible(ptr)) { + kasan_report_invalid_free(ptr, ip, KASAN_REPORT_DOUBLE_FREE); + return true; + } + + return false; +} + +void __kasan_kfree_large(void *ptr, unsigned long ip) +{ + check_page_allocation(ptr, ip); + + /* The object will be poisoned by kasan_poison_pages(). */ +} + +static inline void unpoison_slab_object(struct kmem_cache *cache, void *object, + gfp_t flags, bool init) +{ + /* + * Unpoison the whole object. For kmalloc() allocations, + * poison_kmalloc_redzone() will do precise poisoning. + */ + kasan_unpoison(object, cache->object_size, init); + + /* Save alloc info (if possible) for non-kmalloc() allocations. */ + if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache)) + kasan_save_alloc_info(cache, object, flags); +} + +void * __must_check __kasan_slab_alloc(struct kmem_cache *cache, + void *object, gfp_t flags, bool init) +{ + u8 tag; + void *tagged_object; + + if (gfpflags_allow_blocking(flags)) + kasan_quarantine_reduce(); + + if (unlikely(object == NULL)) + return NULL; + + if (is_kfence_address(object)) + return (void *)object; + + /* + * Generate and assign random tag for tag-based modes. + * Tag is ignored in set_tag() for the generic mode. + */ + tag = assign_tag(cache, object, false); + tagged_object = set_tag(object, tag); + + /* Unpoison the object and save alloc info for non-kmalloc() allocations. */ + unpoison_slab_object(cache, tagged_object, flags, init); + + return tagged_object; +} + +static inline void poison_kmalloc_redzone(struct kmem_cache *cache, + const void *object, size_t size, gfp_t flags) +{ + unsigned long redzone_start; + unsigned long redzone_end; + + /* + * The redzone has byte-level precision for the generic mode. + * Partially poison the last object granule to cover the unaligned + * part of the redzone. + */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + kasan_poison_last_granule((void *)object, size); + + /* Poison the aligned part of the redzone. */ + redzone_start = round_up((unsigned long)(object + size), + KASAN_GRANULE_SIZE); + redzone_end = round_up((unsigned long)(object + cache->object_size), + KASAN_GRANULE_SIZE); + kasan_poison((void *)redzone_start, redzone_end - redzone_start, + KASAN_SLAB_REDZONE, false); + + /* + * Save alloc info (if possible) for kmalloc() allocations. + * This also rewrites the alloc info when called from kasan_krealloc(). + */ + if (kasan_stack_collection_enabled() && is_kmalloc_cache(cache)) + kasan_save_alloc_info(cache, (void *)object, flags); + +} + +void * __must_check __kasan_kmalloc(struct kmem_cache *cache, const void *object, + size_t size, gfp_t flags) +{ + if (gfpflags_allow_blocking(flags)) + kasan_quarantine_reduce(); + + if (unlikely(object == NULL)) + return NULL; + + if (is_kfence_address(object)) + return (void *)object; + + /* The object has already been unpoisoned by kasan_slab_alloc(). */ + poison_kmalloc_redzone(cache, object, size, flags); + + /* Keep the tag that was set by kasan_slab_alloc(). */ + return (void *)object; +} +EXPORT_SYMBOL(__kasan_kmalloc); + +static inline void poison_kmalloc_large_redzone(const void *ptr, size_t size, + gfp_t flags) +{ + unsigned long redzone_start; + unsigned long redzone_end; + + /* + * The redzone has byte-level precision for the generic mode. + * Partially poison the last object granule to cover the unaligned + * part of the redzone. + */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + kasan_poison_last_granule(ptr, size); + + /* Poison the aligned part of the redzone. */ + redzone_start = round_up((unsigned long)(ptr + size), KASAN_GRANULE_SIZE); + redzone_end = (unsigned long)ptr + page_size(virt_to_page(ptr)); + kasan_poison((void *)redzone_start, redzone_end - redzone_start, + KASAN_PAGE_REDZONE, false); +} + +void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ + if (gfpflags_allow_blocking(flags)) + kasan_quarantine_reduce(); + + if (unlikely(ptr == NULL)) + return NULL; + + /* The object has already been unpoisoned by kasan_unpoison_pages(). */ + poison_kmalloc_large_redzone(ptr, size, flags); + + /* Keep the tag that was set by alloc_pages(). */ + return (void *)ptr; +} + +void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flags) +{ + struct slab *slab; + + if (gfpflags_allow_blocking(flags)) + kasan_quarantine_reduce(); + + if (unlikely(object == ZERO_SIZE_PTR)) + return (void *)object; + + if (is_kfence_address(object)) + return (void *)object; + + /* + * Unpoison the object's data. + * Part of it might already have been unpoisoned, but it's unknown + * how big that part is. + */ + kasan_unpoison(object, size, false); + + slab = virt_to_slab(object); + + /* Piggy-back on kmalloc() instrumentation to poison the redzone. */ + if (unlikely(!slab)) + poison_kmalloc_large_redzone(object, size, flags); + else + poison_kmalloc_redzone(slab->slab_cache, object, size, flags); + + return (void *)object; +} + +bool __kasan_mempool_poison_pages(struct page *page, unsigned int order, + unsigned long ip) +{ + unsigned long *ptr; + + if (unlikely(PageHighMem(page))) + return true; + + /* Bail out if allocation was excluded due to sampling. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC) && + page_kasan_tag(page) == KASAN_TAG_KERNEL) + return true; + + ptr = page_address(page); + + if (check_page_allocation(ptr, ip)) + return false; + + kasan_poison(ptr, PAGE_SIZE << order, KASAN_PAGE_FREE, false); + + return true; +} + +void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order, + unsigned long ip) +{ + __kasan_unpoison_pages(page, order, false); +} + +bool __kasan_mempool_poison_object(void *ptr, unsigned long ip) +{ + struct page *page = virt_to_page(ptr); + struct slab *slab; + + if (unlikely(PageLargeKmalloc(page))) { + if (check_page_allocation(ptr, ip)) + return false; + kasan_poison(ptr, page_size(page), KASAN_PAGE_FREE, false); + return true; + } + + if (is_kfence_address(ptr)) + return true; + + slab = page_slab(page); + + if (check_slab_allocation(slab->slab_cache, ptr, ip)) + return false; + + poison_slab_object(slab->slab_cache, ptr, false); + return true; +} + +void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip) +{ + struct slab *slab; + gfp_t flags = 0; /* Might be executing under a lock. */ + + slab = virt_to_slab(ptr); + + /* + * This function can be called for large kmalloc allocation that get + * their memory from page_alloc. + */ + if (unlikely(!slab)) { + kasan_unpoison(ptr, size, false); + poison_kmalloc_large_redzone(ptr, size, flags); + return; + } + + if (is_kfence_address(ptr)) + return; + + /* Unpoison the object and save alloc info for non-kmalloc() allocations. */ + unpoison_slab_object(slab->slab_cache, ptr, flags, false); + + /* Poison the redzone and save alloc info for kmalloc() allocations. */ + if (is_kmalloc_cache(slab->slab_cache)) + poison_kmalloc_redzone(slab->slab_cache, ptr, size, flags); +} + +bool __kasan_check_byte(const void *address, unsigned long ip) +{ + if (!kasan_byte_accessible(address)) { + kasan_report(address, 1, false, ip); + return false; + } + return true; +} + +#ifdef CONFIG_KASAN_VMALLOC +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + unsigned long size; + void *addr; + int area; + u8 tag; + + /* + * If KASAN_VMALLOC_KEEP_TAG was set at this point, all vms[] pointers + * would be unpoisoned with the KASAN_TAG_KERNEL which would disable + * KASAN checks down the line. + */ + if (WARN_ON_ONCE(flags & KASAN_VMALLOC_KEEP_TAG)) + return; + + size = vms[0]->size; + addr = vms[0]->addr; + vms[0]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + tag = get_tag(vms[0]->addr); + + for (area = 1 ; area < nr_vms ; area++) { + size = vms[area]->size; + addr = set_tag(vms[area]->addr, tag); + vms[area]->addr = + __kasan_unpoison_vmalloc(addr, size, flags | KASAN_VMALLOC_KEEP_TAG); + } +} + +void __kasan_vrealloc(const void *addr, unsigned long old_size, + unsigned long new_size) +{ + if (new_size < old_size) { + kasan_poison_last_granule(addr, new_size); + + new_size = round_up(new_size, KASAN_GRANULE_SIZE); + old_size = round_up(old_size, KASAN_GRANULE_SIZE); + if (new_size < old_size) + __kasan_poison_vmalloc(addr + new_size, + old_size - new_size); + } else if (new_size > old_size) { + old_size = round_down(old_size, KASAN_GRANULE_SIZE); + __kasan_unpoison_vmalloc(addr + old_size, + new_size - old_size, + KASAN_VMALLOC_PROT_NORMAL | + KASAN_VMALLOC_VM_ALLOC | + KASAN_VMALLOC_KEEP_TAG); + } +} +#endif -- cgit v1.3.1