diff options
Diffstat (limited to 'kernel')
34 files changed, 989 insertions, 741 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 4df609be42d0..0e119c52a2cd 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -113,7 +113,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/audit.h b/kernel/audit.h index d6a2c899a8db..b2ef4c0d3ec0 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -194,6 +194,10 @@ struct audit_context { struct { char *name; } module; + struct { + struct audit_ntp_data ntp_data; + struct timespec64 tk_injoffset; + } time; }; int fds[2]; struct audit_proctitle proctitle; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b1cb1dbf7417..2f036bab3c28 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1219,6 +1219,53 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) from_kuid(&init_user_ns, name->fcap.rootid)); } +static void audit_log_time(struct audit_context *context, struct audit_buffer **ab) +{ + const struct audit_ntp_data *ntp = &context->time.ntp_data; + const struct timespec64 *tk = &context->time.tk_injoffset; + static const char * const ntp_name[] = { + "offset", + "freq", + "status", + "tai", + "tick", + "adjust", + }; + int type; + + if (context->type == AUDIT_TIME_ADJNTPVAL) { + for (type = 0; type < AUDIT_NTP_NVALS; type++) { + if (ntp->vals[type].newval != ntp->vals[type].oldval) { + if (!*ab) { + *ab = audit_log_start(context, + GFP_KERNEL, + AUDIT_TIME_ADJNTPVAL); + if (!*ab) + return; + } + audit_log_format(*ab, "op=%s old=%lli new=%lli", + ntp_name[type], + ntp->vals[type].oldval, + ntp->vals[type].newval); + audit_log_end(*ab); + *ab = NULL; + } + } + } + if (tk->tv_sec != 0 || tk->tv_nsec != 0) { + if (!*ab) { + *ab = audit_log_start(context, GFP_KERNEL, + AUDIT_TIME_INJOFFSET); + if (!*ab) + return; + } + audit_log_format(*ab, "sec=%lli nsec=%li", + (long long)tk->tv_sec, tk->tv_nsec); + audit_log_end(*ab); + *ab = NULL; + } +} + static void show_special(struct audit_context *context, int *call_panic) { struct audit_buffer *ab; @@ -1327,6 +1374,11 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "(null)"); break; + case AUDIT_TIME_ADJNTPVAL: + case AUDIT_TIME_INJOFFSET: + /* this call deviates from the rest, eating the buffer */ + audit_log_time(context, &ab); + break; } audit_log_end(ab); } @@ -2564,31 +2616,26 @@ void __audit_fanotify(unsigned int response) void __audit_tk_injoffset(struct timespec64 offset) { - audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_INJOFFSET, - "sec=%lli nsec=%li", - (long long)offset.tv_sec, offset.tv_nsec); -} - -static void audit_log_ntp_val(const struct audit_ntp_data *ad, - const char *op, enum audit_ntp_type type) -{ - const struct audit_ntp_val *val = &ad->vals[type]; - - if (val->newval == val->oldval) - return; + struct audit_context *context = audit_context(); - audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_ADJNTPVAL, - "op=%s old=%lli new=%lli", op, val->oldval, val->newval); + /* only set type if not already set by NTP */ + if (!context->type) + context->type = AUDIT_TIME_INJOFFSET; + memcpy(&context->time.tk_injoffset, &offset, sizeof(offset)); } void __audit_ntp_log(const struct audit_ntp_data *ad) { - audit_log_ntp_val(ad, "offset", AUDIT_NTP_OFFSET); - audit_log_ntp_val(ad, "freq", AUDIT_NTP_FREQ); - audit_log_ntp_val(ad, "status", AUDIT_NTP_STATUS); - audit_log_ntp_val(ad, "tai", AUDIT_NTP_TAI); - audit_log_ntp_val(ad, "tick", AUDIT_NTP_TICK); - audit_log_ntp_val(ad, "adjust", AUDIT_NTP_ADJUST); + struct audit_context *context = audit_context(); + int type; + + for (type = 0; type < AUDIT_NTP_NVALS; type++) + if (ad->vals[type].newval != ad->vals[type].oldval) { + /* unconditionally set type, overwriting TK */ + context->type = AUDIT_TIME_ADJNTPVAL; + memcpy(&context->time.ntp_data, ad, sizeof(*ad)); + break; + } } void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b8ed4da63bc8..09406b0e215e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6006,12 +6006,17 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id) return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; } +enum { + BTF_MODULE_F_LIVE = (1 << 0), +}; + #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module { struct list_head list; struct module *module; struct btf *btf; struct bin_attribute *sysfs_attr; + int flags; }; static LIST_HEAD(btf_modules); @@ -6037,7 +6042,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, int err = 0; if (mod->btf_data_size == 0 || - (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) + (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && + op != MODULE_STATE_GOING)) goto out; switch (op) { @@ -6095,6 +6101,17 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, } break; + case MODULE_STATE_LIVE: + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_mod->flags |= BTF_MODULE_F_LIVE; + break; + } + mutex_unlock(&btf_module_mutex); + break; case MODULE_STATE_GOING: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { @@ -6140,7 +6157,12 @@ struct module *btf_try_get_module(const struct btf *btf) if (btf_mod->btf != btf) continue; - if (try_module_get(btf_mod->module)) + /* We must only consider module whose __init routine has + * finished, hence we must check for BTF_MODULE_F_LIVE flag, + * which is set from the notifier callback for + * MODULE_STATE_LIVE. + */ + if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) res = btf_mod->module; break; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 0dcaed4d3f4c..fc0f77f91224 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -219,7 +219,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } static struct perf_callchain_entry * -get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) +get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; @@ -230,9 +230,8 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) if (!entry) return NULL; - entry->nr = init_nr + - stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr), - sysctl_perf_event_max_stack - init_nr, 0); + entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, + max_depth, 0); /* stack_trace_save_tsk() works on unsigned long array, while * perf_callchain_entry uses u64 array. For 32-bit systems, it is @@ -244,7 +243,7 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr) int i; /* copy data from the end to avoid using extra buffer */ - for (i = entry->nr - 1; i >= (int)init_nr; i--) + for (i = entry->nr - 1; i >= 0; i--) to[i] = (u64)(from[i]); } @@ -261,27 +260,19 @@ static long __bpf_get_stackid(struct bpf_map *map, { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; - u32 max_depth = map->value_size / stack_map_data_size(map); - /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ - u32 init_nr = sysctl_perf_event_max_stack - max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 hash, id, trace_nr, trace_len; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; - /* get_perf_callchain() guarantees that trace->nr >= init_nr - * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth - */ - trace_nr = trace->nr - init_nr; - - if (trace_nr <= skip) + if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; - trace_nr -= skip; + trace_nr = trace->nr - skip; trace_len = trace_nr * sizeof(u64); - ips = trace->ip + skip + init_nr; + ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); @@ -338,8 +329,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { u32 max_depth = map->value_size / stack_map_data_size(map); - /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */ - u32 init_nr = sysctl_perf_event_max_stack - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; @@ -348,8 +338,12 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, false, false); + max_depth += skip; + if (max_depth > sysctl_perf_event_max_stack) + max_depth = sysctl_perf_event_max_stack; + + trace = get_perf_callchain(regs, 0, kernel, user, max_depth, + false, false); if (unlikely(!trace)) /* couldn't fetch the stack trace */ @@ -440,7 +434,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags) { - u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; @@ -465,30 +459,28 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, goto err_fault; num_elem = size / elem_size; - if (sysctl_perf_event_max_stack < num_elem) - init_nr = 0; - else - init_nr = sysctl_perf_event_max_stack - num_elem; + max_depth = num_elem + skip; + if (sysctl_perf_event_max_stack < max_depth) + max_depth = sysctl_perf_event_max_stack; if (trace_in) trace = trace_in; else if (kernel && task) - trace = get_callchain_entry_for_task(task, init_nr); + trace = get_callchain_entry_for_task(task, max_depth); else - trace = get_perf_callchain(regs, init_nr, kernel, user, - sysctl_perf_event_max_stack, + trace = get_perf_callchain(regs, 0, kernel, user, max_depth, false, false); if (unlikely(!trace)) goto err_fault; - trace_nr = trace->nr - init_nr; - if (trace_nr < skip) + if (trace->nr < skip) goto err_fault; - trace_nr -= skip; + trace_nr = trace->nr - skip; trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; - ips = trace->ip + skip + init_nr; + + ips = trace->ip + skip; if (user && user_build_id) stack_map_get_build_id_offset(buf, ips, trace_nr, user); else diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index df2bface866e..85cb51c4a17e 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -291,7 +291,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size) */ int kdb_putarea_size(unsigned long addr, void *res, size_t size) { - int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size); + int ret = copy_to_kernel_nofault((char *)addr, (char *)res, size); if (ret) { if (!KDB_STATE(SUPPRESS)) { kdb_func_printf("Bad address 0x%lx\n", addr); diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 7a14ca29c377..f8ff598596b8 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -927,7 +927,7 @@ static __init int dma_debug_cmdline(char *str) global_disable = true; } - return 0; + return 1; } static __init int dma_debug_entries_cmdline(char *str) @@ -936,7 +936,7 @@ static __init int dma_debug_entries_cmdline(char *str) return -EINVAL; if (!get_option(&str, &nr_prealloc_entries)) nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; - return 0; + return 1; } __setup("dma_debug=", dma_debug_cmdline); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index e58dce93c661..2ee5419649ed 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -459,7 +459,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) * allocate a buffer from that IO TLB pool. */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, - size_t alloc_size) + size_t alloc_size, unsigned int alloc_align_mask) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); @@ -483,6 +483,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; if (alloc_size >= PAGE_SIZE) stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT)); + stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1); spin_lock_irqsave(&mem->lock, flags); if (unlikely(nslots > mem->nslabs - mem->used)) @@ -541,7 +542,8 @@ found: phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs) + unsigned int alloc_align_mask, enum dma_data_direction dir, + unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); @@ -561,7 +563,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return (phys_addr_t)DMA_MAPPING_ERROR; } - index = swiotlb_find_slots(dev, orig_addr, alloc_size + offset); + index = swiotlb_find_slots(dev, orig_addr, + alloc_size + offset, alloc_align_mask); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, @@ -652,13 +655,10 @@ void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - /* - * Unconditional bounce is necessary to avoid corruption on - * sync_*_for_cpu or dma_ummap_* when the device didn't overwrite - * the whole lengt of the bounce buffer. - */ - swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); - BUG_ON(!valid_dma_direction(dir)); + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) + swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); + else + BUG_ON(dir != DMA_FROM_DEVICE); } void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, @@ -683,7 +683,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; @@ -767,7 +767,7 @@ struct page *swiotlb_alloc(struct device *dev, size_t size) if (!mem) return NULL; - index = swiotlb_find_slots(dev, 0, size); + index = swiotlb_find_slots(dev, 0, size, 0); if (index == -1) return NULL; diff --git a/kernel/events/core.c b/kernel/events/core.c index b81652fc2cdd..699446d60b6b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10530,8 +10530,11 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, } /* ready to consume more filters */ + kfree(filename); + filename = NULL; state = IF_STATE_ACTION; filter = NULL; + kernel = 0; } } @@ -11593,6 +11596,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 335d988bd811..c0789383807b 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -190,7 +190,7 @@ static int klp_find_object_symbol(const char *objname, const char *name, return -EINVAL; } -static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab, +static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, unsigned int symndx, Elf_Shdr *relasec, const char *sec_objname) { @@ -218,7 +218,7 @@ static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab, relas = (Elf_Rela *) relasec->sh_addr; /* For each rela in this klp relocation section */ for (i = 0; i < relasec->sh_size / sizeof(Elf_Rela); i++) { - sym = (Elf64_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info); + sym = (Elf_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info); if (sym->st_shndx != SHN_LIVEPATCH) { pr_err("symbol %s is not marked as a livepatch symbol\n", strtab + sym->st_name); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 92127296cf2b..a30702b847ba 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -183,11 +183,9 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES); static struct hlist_head lock_keys_hash[KEYHASH_SIZE]; unsigned long nr_lock_classes; unsigned long nr_zapped_classes; -#ifndef CONFIG_DEBUG_LOCKDEP -static -#endif +unsigned long max_lock_class_idx; struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; -static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS); +DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS); static inline struct lock_class *hlock_class(struct held_lock *hlock) { @@ -338,7 +336,7 @@ static inline void lock_release_holdtime(struct held_lock *hlock) * elements. These elements are linked together by the lock_entry member in * struct lock_class. */ -LIST_HEAD(all_lock_classes); +static LIST_HEAD(all_lock_classes); static LIST_HEAD(free_lock_classes); /** @@ -1240,6 +1238,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) struct lockdep_subclass_key *key; struct hlist_head *hash_head; struct lock_class *class; + int idx; DEBUG_LOCKS_WARN_ON(!irqs_disabled()); @@ -1305,6 +1304,9 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * of classes. */ list_move_tail(&class->lock_entry, &all_lock_classes); + idx = class - lock_classes; + if (idx > max_lock_class_idx) + max_lock_class_idx = idx; if (verbose(class)) { graph_unlock(); @@ -5986,6 +5988,8 @@ static void zap_class(struct pending_free *pf, struct lock_class *class) WRITE_ONCE(class->name, NULL); nr_lock_classes--; __clear_bit(class - lock_classes, lock_classes_in_use); + if (class - lock_classes == max_lock_class_idx) + max_lock_class_idx--; } else { WARN_ONCE(true, "%s() failed for class %s\n", __func__, class->name); @@ -6276,7 +6280,13 @@ void lockdep_reset_lock(struct lockdep_map *lock) lockdep_reset_lock_reg(lock); } -/* Unregister a dynamically allocated key. */ +/* + * Unregister a dynamically allocated key. + * + * Unlike lockdep_register_key(), a search is always done to find a matching + * key irrespective of debug_locks to avoid potential invalid access to freed + * memory in lock_class entry. + */ void lockdep_unregister_key(struct lock_class_key *key) { struct hlist_head *hash_head = keyhashentry(key); @@ -6291,10 +6301,8 @@ void lockdep_unregister_key(struct lock_class_key *key) return; raw_local_irq_save(flags); - if (!graph_lock()) - goto out_irq; + lockdep_lock(); - pf = get_pending_free(); hlist_for_each_entry_rcu(k, hash_head, hash_entry) { if (k == key) { hlist_del_rcu(&k->hash_entry); @@ -6302,11 +6310,13 @@ void lockdep_unregister_key(struct lock_class_key *key) break; } } - WARN_ON_ONCE(!found); - __lockdep_free_key_range(pf, key, 1); - call_rcu_zapped(pf); - graph_unlock(); -out_irq: + WARN_ON_ONCE(!found && debug_locks); + if (found) { + pf = get_pending_free(); + __lockdep_free_key_range(pf, key, 1); + call_rcu_zapped(pf); + } + lockdep_unlock(); raw_local_irq_restore(flags); /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */ diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index ecb8662e7a4e..bbe9000260d0 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -121,7 +121,6 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) -extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; #define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1) @@ -151,6 +150,10 @@ extern unsigned int nr_large_chain_blocks; extern unsigned int max_lockdep_depth; extern unsigned int max_bfs_queue_depth; +extern unsigned long max_lock_class_idx; + +extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; +extern unsigned long lock_classes_in_use[]; #ifdef CONFIG_PROVE_LOCKING extern unsigned long lockdep_count_forward_deps(struct lock_class *); @@ -205,7 +208,6 @@ struct lockdep_stats { }; DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats); -extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; #define __debug_atomic_inc(ptr) \ this_cpu_inc(lockdep_stats.ptr); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index b8d9a050c337..15fdc7fa5c68 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -24,14 +24,33 @@ #include "lockdep_internals.h" +/* + * Since iteration of lock_classes is done without holding the lockdep lock, + * it is not safe to iterate all_lock_classes list directly as the iteration + * may branch off to free_lock_classes or the zapped list. Iteration is done + * directly on the lock_classes array by checking the lock_classes_in_use + * bitmap and max_lock_class_idx. + */ +#define iterate_lock_classes(idx, class) \ + for (idx = 0, class = lock_classes; idx <= max_lock_class_idx; \ + idx++, class++) + static void *l_next(struct seq_file *m, void *v, loff_t *pos) { - return seq_list_next(v, &all_lock_classes, pos); + struct lock_class *class = v; + + ++class; + *pos = class - lock_classes; + return (*pos > max_lock_class_idx) ? NULL : class; } static void *l_start(struct seq_file *m, loff_t *pos) { - return seq_list_start_head(&all_lock_classes, *pos); + unsigned long idx = *pos; + + if (idx > max_lock_class_idx) + return NULL; + return lock_classes + idx; } static void l_stop(struct seq_file *m, void *v) @@ -57,14 +76,16 @@ static void print_name(struct seq_file *m, struct lock_class *class) static int l_show(struct seq_file *m, void *v) { - struct lock_class *class = list_entry(v, struct lock_class, lock_entry); + struct lock_class *class = v; struct lock_list *entry; char usage[LOCK_USAGE_CHARS]; + int idx = class - lock_classes; - if (v == &all_lock_classes) { + if (v == lock_classes) seq_printf(m, "all lock classes:\n"); + + if (!test_bit(idx, lock_classes_in_use)) return 0; - } seq_printf(m, "%p", class->key); #ifdef CONFIG_DEBUG_LOCKDEP @@ -220,8 +241,11 @@ static int lockdep_stats_show(struct seq_file *m, void *v) #ifdef CONFIG_PROVE_LOCKING struct lock_class *class; + unsigned long idx; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; if (class->usage_mask == 0) nr_unused++; @@ -254,6 +278,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v) sum_forward_deps += lockdep_count_forward_deps(class); } + #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); #endif @@ -345,6 +370,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v) seq_printf(m, " max bfs queue depth: %11u\n", max_bfs_queue_depth); #endif + seq_printf(m, " max lock class index: %11lu\n", + max_lock_class_idx); lockdep_stats_debug_show(m); seq_printf(m, " debug_locks: %11u\n", debug_locks); @@ -622,12 +649,16 @@ static int lock_stat_open(struct inode *inode, struct file *file) if (!res) { struct lock_stat_data *iter = data->stats; struct seq_file *m = file->private_data; + unsigned long idx; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; iter->class = class; iter->stats = lock_stats(class); iter++; } + data->iter_end = iter; sort(data->stats, data->iter_end - data->stats, @@ -645,6 +676,7 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct lock_class *class; + unsigned long idx; char c; if (count) { @@ -654,8 +686,11 @@ static ssize_t lock_stat_write(struct file *file, const char __user *buf, if (c != '0') return count; - list_for_each_entry(class, &all_lock_classes, lock_entry) + iterate_lock_classes(idx, class) { + if (!test_bit(idx, lock_classes_in_use)) + continue; clear_lock_stats(class); + } } return count; } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b0888e9224da..d926852f8119 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1326,7 +1326,7 @@ static int __init resumedelay_setup(char *str) int rc = kstrtouint(str, 0, &resume_delay); if (rc) - return rc; + pr_warn("resumedelay: bad option string '%s'\n", str); return 1; } diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index d20526c5be15..b663a97f5867 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -157,22 +157,22 @@ static int __init setup_test_suspend(char *value) value++; suspend_type = strsep(&value, ","); if (!suspend_type) - return 0; + return 1; repeat = strsep(&value, ","); if (repeat) { if (kstrtou32(repeat, 0, &test_repeat_count_max)) - return 0; + return 1; } for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) if (!strcmp(pm_labels[i], suspend_type)) { test_state_label = pm_labels[i]; - return 0; + return 1; } printk(warn_bad_state, suspend_type); - return 0; + return 1; } __setup("test_suspend", setup_test_suspend); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 99221b016c68..7aeb13542ce7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -146,8 +146,10 @@ static int __control_devkmsg(char *str) static int __init control_devkmsg(char *str) { - if (__control_devkmsg(str) < 0) + if (__control_devkmsg(str) < 0) { + pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; + } /* * Set sysctl string accordingly: @@ -166,7 +168,7 @@ static int __init control_devkmsg(char *str) */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; - return 0; + return 1; } __setup("printk.devkmsg=", control_devkmsg); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f8589bf8d7dc..516ad5e65849 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -371,6 +371,26 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) return !err; } +static int check_ptrace_options(unsigned long data) +{ + if (data & ~(unsigned long)PTRACE_O_MASK) + return -EINVAL; + + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { + if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || + !IS_ENABLED(CONFIG_SECCOMP)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || + current->ptrace & PT_SUSPEND_SECCOMP) + return -EPERM; + } + return 0; +} + static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) @@ -382,8 +402,16 @@ static int ptrace_attach(struct task_struct *task, long request, if (seize) { if (addr != 0) goto out; + /* + * This duplicates the check in check_ptrace_options() because + * ptrace_attach() and ptrace_setoptions() have historically + * used different error codes for unknown ptrace options. + */ if (flags & ~(unsigned long)PTRACE_O_MASK) goto out; + retval = check_ptrace_options(flags); + if (retval) + return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; @@ -656,22 +684,11 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; + int ret; - if (data & ~(unsigned long)PTRACE_O_MASK) - return -EINVAL; - - if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { - if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || - !IS_ENABLED(CONFIG_SECCOMP)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || - current->ptrace & PT_SUSPEND_SECCOMP) - return -EPERM; - } + ret = check_ptrace_options(data); + if (ret) + return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 9a19328ff251..5d405943823e 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -56,13 +56,13 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp, int flags) { - rsclp->flags |= flags; + WRITE_ONCE(rsclp->flags, rsclp->flags | flags); } static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp, int flags) { - rsclp->flags &= ~flags; + WRITE_ONCE(rsclp->flags, rsclp->flags & ~flags); } static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 0d21a5cdc724..ef2dd131e955 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -554,16 +554,16 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - /* Unboost if we were boosted. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); - /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) rcu_report_exp_rnp(rnp, true); + + /* Unboost if we were boosted. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) + rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); } else { local_irq_restore(flags); } diff --git a/kernel/resource.c b/kernel/resource.c index ca9f5198a01f..20e10e48f052 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -56,14 +56,6 @@ struct resource_constraint { static DEFINE_RWLOCK(resource_lock); -/* - * For memory hotplug, there is no way to free resource entries allocated - * by boot mem after the system is up. So for reusing the resource entry - * we need to remember the resource. - */ -static struct resource *bootmem_resource_free; -static DEFINE_SPINLOCK(bootmem_resource_lock); - static struct resource *next_resource(struct resource *p) { if (p->child) @@ -148,36 +140,19 @@ __initcall(ioresources_init); static void free_resource(struct resource *res) { - if (!res) - return; - - if (!PageSlab(virt_to_head_page(res))) { - spin_lock(&bootmem_resource_lock); - res->sibling = bootmem_resource_free; - bootmem_resource_free = res; - spin_unlock(&bootmem_resource_lock); - } else { + /** + * If the resource was allocated using memblock early during boot + * we'll leak it here: we can only return full pages back to the + * buddy and trying to be smart and reusing them eventually in + * alloc_resource() overcomplicates resource handling. + */ + if (res && PageSlab(virt_to_head_page(res))) kfree(res); - } } static struct resource *alloc_resource(gfp_t flags) { - struct resource *res = NULL; - - spin_lock(&bootmem_resource_lock); - if (bootmem_resource_free) { - res = bootmem_resource_free; - bootmem_resource_free = res->sibling; - } - spin_unlock(&bootmem_resource_lock); - - if (res) - memset(res, 0, sizeof(struct resource)); - else - res = kzalloc(sizeof(struct resource), flags); - - return res; + return kzalloc(sizeof(struct resource), flags); } /* Return the conflict entry if you can't request it */ diff --git a/kernel/rseq.c b/kernel/rseq.c index 6d45ac3dae7f..97ac20b4f738 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -128,10 +128,10 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) int ret; #ifdef CONFIG_64BIT - if (get_user(ptr, &t->rseq->rseq_cs.ptr64)) + if (get_user(ptr, &t->rseq->rseq_cs)) return -EFAULT; #else - if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr))) + if (copy_from_user(&ptr, &t->rseq->rseq_cs, sizeof(ptr))) return -EFAULT; #endif if (!ptr) { @@ -217,9 +217,9 @@ static int clear_rseq_cs(struct task_struct *t) * Set rseq_cs to NULL. */ #ifdef CONFIG_64BIT - return put_user(0UL, &t->rseq->rseq_cs.ptr64); + return put_user(0UL, &t->rseq->rseq_cs); #else - if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64))) + if (clear_user(&t->rseq->rseq_cs, sizeof(t->rseq->rseq_cs))) return -EFAULT; return 0; #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a0747eaa2dba..779f3198b17d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -36,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); @@ -5926,7 +5927,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index ab67d97a8442..cacc2076ad21 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -328,12 +328,13 @@ static struct cftype files[] = { */ void cpuacct_charge(struct task_struct *tsk, u64 cputime) { + unsigned int cpu = task_cpu(tsk); struct cpuacct *ca; rcu_read_lock(); for (ca = task_ca(tsk); ca; ca = parent_ca(ca)) - __this_cpu_add(*ca->cpuusage, cputime); + *per_cpu_ptr(ca->cpuusage, cpu) += cputime; rcu_read_unlock(); } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index e7af18857371..7f6bb37d3a2f 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -289,6 +289,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * into the same scale so we can compare. */ boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; + boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e94314633b39..1f811b375bf0 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2145,12 +2145,6 @@ static int push_dl_task(struct rq *rq) return 0; retry: - if (is_migration_disabled(next_task)) - return 0; - - if (WARN_ON(next_task == rq->curr)) - return 0; - /* * If next_task preempts rq->curr, and rq->curr * can move away, it makes sense to just reschedule @@ -2163,6 +2157,12 @@ retry: return 0; } + if (is_migration_disabled(next_task)) + return 0; + + if (WARN_ON(next_task == rq->curr)) + return 0; + /* We might release rq lock */ get_task_struct(next_task); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 17a653b67006..7a2d32d2025f 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -921,25 +921,15 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, static void sched_show_numa(struct task_struct *p, struct seq_file *m) { #ifdef CONFIG_NUMA_BALANCING - struct mempolicy *pol; - if (p->mm) P(mm->numa_scan_seq); - task_lock(p); - pol = p->mempolicy; - if (pol && !(pol->flags & MPOL_F_MORON)) - pol = NULL; - mpol_get(pol); - task_unlock(p); - P(numa_pages_migrated); P(numa_preferred_nid); P(total_numa_faults); SEQ_printf(m, "current_node=%d, numa_group_id=%d\n", task_node(p), task_numa_group_id(p)); show_numa_stats(p, m); - mpol_put(pol); #endif } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6420580f2730..02766f3fe206 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9005,9 +9005,10 @@ static bool update_pick_idlest(struct sched_group *idlest, * This is an approximation as the number of running tasks may not be * related to the number of busy CPUs due to sched_setaffinity. */ -static inline bool allow_numa_imbalance(int dst_running, int dst_weight) +static inline bool +allow_numa_imbalance(unsigned int running, unsigned int weight) { - return (dst_running < (dst_weight >> 2)); + return (running < (weight >> 2)); } /* @@ -9141,12 +9142,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) return idlest; #endif /* - * Otherwise, keep the task on this node to stay close - * its wakeup source and improve locality. If there is - * a real need of migration, periodic load balance will - * take care of it. + * Otherwise, keep the task close to the wakeup source + * and improve locality if the number of running tasks + * would remain below threshold where an imbalance is + * allowed. If there is a real need of migration, + * periodic load balance will take care of it. */ - if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight)) + if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, local_sgs.group_weight)) return NULL; } @@ -9352,7 +9354,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { env->imbalance = adjust_numa_imbalance(env->imbalance, - busiest->sum_nr_running, busiest->group_weight); + local->sum_nr_running + 1, local->group_weight); } return; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 54f9bb3f1560..2758cf5f7987 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1900,6 +1900,16 @@ static int push_rt_task(struct rq *rq, bool pull) return 0; retry: + /* + * It's possible that the next_task slipped in of + * higher priority than current. If that's the case + * just reschedule current. + */ + if (unlikely(next_task->prio < rq->curr->prio)) { + resched_curr(rq); + return 0; + } + if (is_migration_disabled(next_task)) { struct task_struct *push_task = NULL; int cpu; @@ -1907,6 +1917,18 @@ retry: if (!pull || rq->push_busy) return 0; + /* + * Invoking find_lowest_rq() on anything but an RT task doesn't + * make sense. Per the above priority check, curr has to + * be of higher priority than next_task, so no need to + * reschedule when bailing out. + * + * Note that the stoppers are masqueraded as SCHED_FIFO + * (cf. sched_set_stop_task()), so we can't rely on rt_task(). + */ + if (rq->curr->sched_class != &rt_sched_class) + return 0; + cpu = find_lowest_rq(rq->curr); if (cpu == -1 || cpu == rq->cpu) return 0; @@ -1931,16 +1953,6 @@ retry: if (WARN_ON(next_task == rq->curr)) return 0; - /* - * It's possible that the next_task slipped in of - * higher priority than current. If that's the case - * just reschedule current. - */ - if (unlikely(next_task->prio < rq->curr->prio)) { - resched_curr(rq); - return 0; - } - /* We might release rq lock */ get_task_struct(next_task); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 9f8117c7cfdd..9c625257023d 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> +#include <linux/interrupt.h> /** * stack_trace_print - Print the entries in the stack trace @@ -373,3 +374,32 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) #endif /* CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* !CONFIG_ARCH_STACKWALK */ + +static inline bool in_irqentry_text(unsigned long ptr) +{ + return (ptr >= (unsigned long)&__irqentry_text_start && + ptr < (unsigned long)&__irqentry_text_end) || + (ptr >= (unsigned long)&__softirqentry_text_start && + ptr < (unsigned long)&__softirqentry_text_end); +} + +/** + * filter_irq_stacks - Find first IRQ stack entry in trace + * @entries: Pointer to stack trace array + * @nr_entries: Number of entries in the storage array + * + * Return: Number of trace entries until IRQ stack starts. + */ +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries) +{ + unsigned int i; + + for (i = 0; i < nr_entries; i++) { + if (in_irqentry_text(entries[i])) { + /* Include the irqentry function into the stack. */ + return i + 1; + } + } + return nr_entries; +} +EXPORT_SYMBOL_GPL(filter_irq_stacks); diff --git a/kernel/static_call.c b/kernel/static_call.c index 43ba0b1e0edb..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,548 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ +EXPORT_SYMBOL_GPL(__static_call_return0); diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 01002656f1ae..b49756608f83 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3678,12 +3678,17 @@ static char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str) +static bool trace_safe_str(struct trace_iterator *iter, const char *str, + bool star, int len) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; + /* Ignore strings with no length */ + if (star && !len) + return true; + /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3869,7 +3874,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!trace_safe_str(iter, str), + if (WARN_ONCE(!trace_safe_str(iter, str, star, len), "fmt: '%s' current_buffer: '%s'", fmt, show_buffer(&iter->seq))) { int ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 44d031ffe511..c072e8b9849c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -40,6 +40,14 @@ static LIST_HEAD(ftrace_generic_fields); static LIST_HEAD(ftrace_common_fields); static bool eventdir_initialized; +static LIST_HEAD(module_strings); + +struct module_string { + struct list_head next; + struct module *module; + char *str; +}; + #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) static struct kmem_cache *field_cachep; @@ -2633,6 +2641,76 @@ static void update_event_printk(struct trace_event_call *call, } } +static void add_str_to_module(struct module *module, char *str) +{ + struct module_string *modstr; + + modstr = kmalloc(sizeof(*modstr), GFP_KERNEL); + + /* + * If we failed to allocate memory here, then we'll just + * let the str memory leak when the module is removed. + * If this fails to allocate, there's worse problems than + * a leaked string on module removal. + */ + if (WARN_ON_ONCE(!modstr)) + return; + + modstr->module = module; + modstr->str = str; + + list_add(&modstr->next, &module_strings); +} + +static void update_event_fields(struct trace_event_call *call, + struct trace_eval_map *map) +{ + struct ftrace_event_field *field; + struct list_head *head; + char *ptr; + char *str; + int len = strlen(map->eval_string); + + /* Dynamic events should never have field maps */ + if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC)) + return; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + ptr = strchr(field->type, '['); + if (!ptr) + continue; + ptr++; + + if (!isalpha(*ptr) && *ptr != '_') + continue; + + if (strncmp(map->eval_string, ptr, len) != 0) + continue; + + str = kstrdup(field->type, GFP_KERNEL); + if (WARN_ON_ONCE(!str)) + return; + ptr = str + (ptr - field->type); + ptr = eval_replace(ptr, map, len); + /* enum/sizeof string smaller than value */ + if (WARN_ON_ONCE(!ptr)) { + kfree(str); + continue; + } + + /* + * If the event is part of a module, then we need to free the string + * when the module is removed. Otherwise, it will stay allocated + * until a reboot. + */ + if (call->module) + add_str_to_module(call->module, str); + + field->type = str; + } +} + void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; @@ -2668,6 +2746,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) first = false; } update_event_printk(call, map[i]); + update_event_fields(call, map[i]); } } } @@ -2851,6 +2930,7 @@ static void trace_module_add_events(struct module *mod) static void trace_module_remove_events(struct module *mod) { struct trace_event_call *call, *p; + struct module_string *modstr, *m; down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { @@ -2859,6 +2939,14 @@ static void trace_module_remove_events(struct module *mod) if (call->module == mod) __trace_remove_event_call(call); } + /* Check for any strings allocade for this module */ + list_for_each_entry_safe(modstr, m, &module_strings, next) { + if (modstr->module != mod) + continue; + list_del(&modstr->next); + kfree(modstr->str); + kfree(modstr); + } up_write(&trace_event_sem); /* diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 055bc20ecdda..b1ae7c9c3b47 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -274,7 +274,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) return 0; error_p: - for (i = 0; i < nr_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); error: @@ -373,6 +373,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + kfree(wqueue->notes); bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); @@ -398,6 +399,7 @@ static void free_watch(struct rcu_head *rcu) put_watch_queue(rcu_access_pointer(watch->queue)); atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); + kfree(watch); } static void __put_watch(struct kref *kref) |