diff options
Diffstat (limited to 'kernel')
61 files changed, 882 insertions, 884 deletions
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index a4181234232b..2dfe66b9ed76 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -74,5 +74,6 @@ static void exitf(void) module_init(backtrace_regression_test); module_exit(exitf); +MODULE_DESCRIPTION("Simple stack backtrace regression test module"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index a546aba46d5d..dec892ded031 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -155,12 +155,9 @@ static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) { -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (c->objcg) return get_mem_cgroup_from_objcg(c->objcg); -#endif - -#ifdef CONFIG_MEMCG return root_mem_cgroup; #else return NULL; @@ -534,7 +531,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) size += LLIST_NODE_SZ; /* room for llist_node */ unit_size = size; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif @@ -556,7 +553,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 869265852d51..bf6c5f685ea2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -385,7 +385,7 @@ void bpf_map_free_id(struct bpf_map *map) spin_unlock_irqrestore(&map_idr_lock, flags); } -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root @@ -486,7 +486,7 @@ int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long i, j; struct page *pg; int ret = 0; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct mem_cgroup *memcg, *old_memcg; memcg = bpf_map_get_memcg(map); @@ -505,7 +505,7 @@ int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, break; } -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG set_active_memcg(old_memcg); mem_cgroup_put(memcg); #endif @@ -5983,7 +5983,7 @@ const struct bpf_prog_ops bpf_syscall_prog_ops = { }; #ifdef CONFIG_SYSCTL -static int bpf_stats_handler(struct ctl_table *table, int write, +static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; @@ -6018,7 +6018,7 @@ void __weak unpriv_ebpf_notify(int new_state) { } -static int bpf_unpriv_handler(struct ctl_table *table, int write, +static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8da132a1ef28..4cb5441ad75f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21132,8 +21132,12 @@ BTF_SET_START(btf_non_sleepable_error_inject) * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __filemap_add_folio) +#ifdef CONFIG_FAIL_PAGE_ALLOC BTF_ID(func, should_fail_alloc_page) +#endif +#ifdef CONFIG_FAILSLAB BTF_ID(func, should_failslab) +#endif BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index 5b2722a93a48..d3b4cd12bdd1 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -13,7 +13,6 @@ #include <linux/memory.h> #include <linux/cpuhotplug.h> #include <linux/memblock.h> -#include <linux/kexec.h> #include <linux/kmemleak.h> #include <asm/page.h> diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 10b454554ab0..137ba73f56fc 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -144,7 +144,7 @@ kdb_bt(int argc, const char **argv) kdb_ps_suppressed(); /* Run the active tasks first */ for_each_online_cpu(cpu) { - p = kdb_curr_task(cpu); + p = curr_task(cpu); if (kdb_bt1(p, mask, btaprompt)) return 0; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 3131334d7a81..6a77f1c779c4 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -206,7 +206,7 @@ char kdb_getchar(void) */ static void kdb_position_cursor(char *prompt, char *buffer, char *cp) { - kdb_printf("\r%s", kdb_prompt_str); + kdb_printf("\r%s", prompt); if (cp > buffer) kdb_printf("%.*s", (int)(cp - buffer), buffer); } @@ -362,7 +362,7 @@ poll_again: if (i >= dtab_count) kdb_printf("..."); kdb_printf("\n"); - kdb_printf(kdb_prompt_str); + kdb_printf("%s", kdb_prompt_str); kdb_printf("%s", buffer); if (cp != lastchar) kdb_position_cursor(kdb_prompt_str, buffer, cp); @@ -453,7 +453,7 @@ char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt) { if (prompt && kdb_prompt_str != prompt) strscpy(kdb_prompt_str, prompt, CMD_BUFLEN); - kdb_printf(kdb_prompt_str); + kdb_printf("%s", kdb_prompt_str); kdb_nextline = 1; /* Prompt and input resets line number */ return kdb_read(buffer, bufsize); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 664bae55f2c9..f5f7d7fb5936 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -155,16 +155,6 @@ static char *__env[31] = { static const int __nenv = ARRAY_SIZE(__env); -struct task_struct *kdb_curr_task(int cpu) -{ - struct task_struct *p = curr_task(cpu); -#ifdef _TIF_MCA_INIT - if ((task_thread_info(p)->flags & _TIF_MCA_INIT) && KDB_TSK(cpu)) - p = krp->p; -#endif - return p; -} - /* * Update the permissions flags (kdb_cmd_enabled) to match the * current lockdown state. @@ -1228,7 +1218,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, char *cmdbuf; int diag; struct task_struct *kdb_current = - kdb_curr_task(raw_smp_processor_id()); + curr_task(raw_smp_processor_id()); KDB_DEBUG_STATE("kdb_local 1", reason); @@ -2278,7 +2268,7 @@ void kdb_ps_suppressed(void) unsigned long cpu; const struct task_struct *p, *g; for_each_online_cpu(cpu) { - p = kdb_curr_task(cpu); + p = curr_task(cpu); if (kdb_task_state(p, "-")) ++idle; } @@ -2314,7 +2304,7 @@ void kdb_ps1(const struct task_struct *p) kdb_task_has_cpu(p), kdb_process_cpu(p), kdb_task_state_char(p), (void *)(&p->thread), - p == kdb_curr_task(raw_smp_processor_id()) ? '*' : ' ', + p == curr_task(raw_smp_processor_id()) ? '*' : ' ', p->comm); if (kdb_task_has_cpu(p)) { if (!KDB_TSK(cpu)) { @@ -2350,7 +2340,7 @@ static int kdb_ps(int argc, const char **argv) for_each_online_cpu(cpu) { if (KDB_FLAG(CMD_INTERRUPT)) return 0; - p = kdb_curr_task(cpu); + p = curr_task(cpu); if (kdb_task_state(p, mask)) kdb_ps1(p); } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 548fd4059bf9..d2520d72b1f5 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -210,8 +210,6 @@ extern void kdb_gdb_state_pass(char *buf); #define KDB_TSK(cpu) kgdb_info[cpu].task #define KDB_TSKREGS(cpu) kgdb_info[cpu].debuggerinfo -extern struct task_struct *kdb_curr_task(int); - #define kdb_task_has_cpu(p) (task_curr(p)) #define GFP_KDB (in_dbg_master() ? GFP_ATOMIC : GFP_KERNEL) diff --git a/kernel/delayacct.c b/kernel/delayacct.c index e039b0f99a0b..dead51de8eb5 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -44,7 +44,7 @@ void delayacct_init(void) } #ifdef CONFIG_PROC_SYSCTL -static int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, +static int sysctl_delayacct(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int state = delayacct_on; diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 81de84318ccc..b1c18058d55f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -67,8 +67,8 @@ void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, { struct dma_devres match_data = { size, vaddr, dma_handle }; - dma_free_coherent(dev, size, vaddr, dma_handle); WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data)); + dma_free_coherent(dev, size, vaddr, dma_handle); } EXPORT_SYMBOL(dmam_free_coherent); diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 8d57255e5b29..8a47e52a454f 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -270,7 +270,7 @@ exit_put: * Used for sysctl_perf_event_max_stack and * sysctl_perf_event_max_contexts_per_stack. */ -int perf_event_max_stack_handler(struct ctl_table *table, int write, +int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *value = table->data; diff --git a/kernel/events/core.c b/kernel/events/core.c index ab6c4c942f79..aa3450bdc227 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -450,7 +450,7 @@ static void update_perf_cpu_limits(void) static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc); -int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, +int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -474,7 +474,7 @@ int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT; -int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, +int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -534,7 +534,7 @@ void perf_sample_event_took(u64 sample_len_ns) __this_cpu_write(running_sample_length, running_len); /* - * Note: this will be biased artifically low until we have + * Note: this will be biased artificially low until we have * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us * from having to maintain a count. */ @@ -596,10 +596,10 @@ static inline u64 perf_event_clock(struct perf_event *event) * * Event groups make things a little more complicated, but not terribly so. The * rules for a group are that if the group leader is OFF the entire group is - * OFF, irrespecive of what the group member states are. This results in + * OFF, irrespective of what the group member states are. This results in * __perf_effective_state(). * - * A futher ramification is that when a group leader flips between OFF and + * A further ramification is that when a group leader flips between OFF and * !OFF, we need to update all group member times. * * @@ -891,7 +891,7 @@ static int perf_cgroup_ensure_storage(struct perf_event *event, int cpu, heap_size, ret = 0; /* - * Allow storage to have sufficent space for an iterator for each + * Allow storage to have sufficient space for an iterator for each * possibly nested cgroup plus an iterator for events with no cgroup. */ for (heap_size = 1; css; css = css->parent) @@ -3671,7 +3671,7 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_switch(next); } -static bool perf_less_group_idx(const void *l, const void *r) +static bool perf_less_group_idx(const void *l, const void *r, void __always_unused *args) { const struct perf_event *le = *(const struct perf_event **)l; const struct perf_event *re = *(const struct perf_event **)r; @@ -3679,20 +3679,21 @@ static bool perf_less_group_idx(const void *l, const void *r) return le->group_index < re->group_index; } -static void swap_ptr(void *l, void *r) +static void swap_ptr(void *l, void *r, void __always_unused *args) { void **lp = l, **rp = r; swap(*lp, *rp); } +DEFINE_MIN_HEAP(struct perf_event *, perf_event_min_heap); + static const struct min_heap_callbacks perf_min_heap = { - .elem_size = sizeof(struct perf_event *), .less = perf_less_group_idx, .swp = swap_ptr, }; -static void __heap_add(struct min_heap *heap, struct perf_event *event) +static void __heap_add(struct perf_event_min_heap *heap, struct perf_event *event) { struct perf_event **itrs = heap->data; @@ -3726,7 +3727,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx = NULL; /* Space for per CPU and/or any CPU event iterators. */ struct perf_event *itrs[2]; - struct min_heap event_heap; + struct perf_event_min_heap event_heap; struct perf_event **evt; int ret; @@ -3735,7 +3736,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, if (!ctx->task) { cpuctx = this_cpu_ptr(&perf_cpu_context); - event_heap = (struct min_heap){ + event_heap = (struct perf_event_min_heap){ .data = cpuctx->heap, .nr = 0, .size = cpuctx->heap_size, @@ -3748,7 +3749,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, css = &cpuctx->cgrp->css; #endif } else { - event_heap = (struct min_heap){ + event_heap = (struct perf_event_min_heap){ .data = itrs, .nr = 0, .size = ARRAY_SIZE(itrs), @@ -3770,7 +3771,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, perf_assert_pmu_disabled((*evt)->pmu_ctx->pmu); } - min_heapify_all(&event_heap, &perf_min_heap); + min_heapify_all(&event_heap, &perf_min_heap, NULL); while (event_heap.nr) { ret = func(*evt, data); @@ -3779,9 +3780,9 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx, *evt = perf_event_groups_next(*evt, pmu); if (*evt) - min_heapify(&event_heap, 0, &perf_min_heap); + min_heap_sift_down(&event_heap, 0, &perf_min_heap, NULL); else - min_heap_pop(&event_heap, &perf_min_heap); + min_heap_pop(&event_heap, &perf_min_heap, NULL); } return 0; @@ -7634,7 +7635,7 @@ again: pte = ptep_get_lockless(ptep); if (pte_present(pte)) - size = pte_leaf_size(pte); + size = __pte_leaf_size(pmd, pte); pte_unmap(ptep); #endif /* CONFIG_HAVE_GUP_FAST */ @@ -9327,21 +9328,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD; int i; - if (prog->aux->func_cnt == 0) { - perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, - (u64)(unsigned long)prog->bpf_func, - prog->jited_len, unregister, - prog->aux->ksym.name); - } else { - for (i = 0; i < prog->aux->func_cnt; i++) { - struct bpf_prog *subprog = prog->aux->func[i]; - - perf_event_ksymbol( - PERF_RECORD_KSYMBOL_TYPE_BPF, - (u64)(unsigned long)subprog->bpf_func, - subprog->jited_len, unregister, - subprog->aux->ksym.name); - } + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)prog->bpf_func, + prog->jited_len, unregister, + prog->aux->ksym.name); + + for (i = 1; i < prog->aux->func_cnt; i++) { + struct bpf_prog *subprog = prog->aux->func[i]; + + perf_event_ksymbol( + PERF_RECORD_KSYMBOL_TYPE_BPF, + (u64)(unsigned long)subprog->bpf_func, + subprog->jited_len, unregister, + subprog->aux->ksym.name); } } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 99be2adedbc0..73cc47708679 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { folio_get(new_folio); - folio_add_new_anon_rmap(new_folio, vma, addr); + folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/kernel/exit.c b/kernel/exit.c index be81342caf1b..7430852a8571 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -438,14 +438,46 @@ static void coredump_task_exit(struct task_struct *tsk) } #ifdef CONFIG_MEMCG +/* drops tasklist_lock if succeeds */ +static bool __try_to_set_owner(struct task_struct *tsk, struct mm_struct *mm) +{ + bool ret = false; + + task_lock(tsk); + if (likely(tsk->mm == mm)) { + /* tsk can't pass exit_mm/exec_mmap and exit */ + read_unlock(&tasklist_lock); + WRITE_ONCE(mm->owner, tsk); + lru_gen_migrate_mm(mm); + ret = true; + } + task_unlock(tsk); + return ret; +} + +static bool try_to_set_owner(struct task_struct *g, struct mm_struct *mm) +{ + struct task_struct *t; + + for_each_thread(g, t) { + struct mm_struct *t_mm = READ_ONCE(t->mm); + if (t_mm == mm) { + if (__try_to_set_owner(t, mm)) + return true; + } else if (t_mm) + break; + } + + return false; +} + /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { - struct task_struct *c, *g, *p = current; + struct task_struct *g, *p = current; -retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. @@ -466,19 +498,17 @@ retry: /* * Search in the children */ - list_for_each_entry(c, &p->children, sibling) { - if (c->mm == mm) - goto assign_new_owner; + list_for_each_entry(g, &p->children, sibling) { + if (try_to_set_owner(g, mm)) + goto ret; } - /* * Search in the siblings */ - list_for_each_entry(c, &p->real_parent->children, sibling) { - if (c->mm == mm) - goto assign_new_owner; + list_for_each_entry(g, &p->real_parent->children, sibling) { + if (try_to_set_owner(g, mm)) + goto ret; } - /* * Search through everything else, we should not get here often. */ @@ -487,12 +517,8 @@ retry: break; if (g->flags & PF_KTHREAD) continue; - for_each_thread(g, c) { - if (c->mm == mm) - goto assign_new_owner; - if (c->mm) - break; - } + if (try_to_set_owner(g, mm)) + goto ret; } read_unlock(&tasklist_lock); /* @@ -501,30 +527,9 @@ retry: * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); + ret: return; -assign_new_owner: - BUG_ON(c == p); - get_task_struct(c); - /* - * The task_lock protects c->mm from changing. - * We always want mm->owner->mm == mm - */ - task_lock(c); - /* - * Delay read_unlock() till we have the task_lock() - * to ensure that c does not slip away underneath us - */ - read_unlock(&tasklist_lock); - if (c->mm != mm) { - task_unlock(c); - put_task_struct(c); - goto retry; - } - WRITE_ONCE(mm->owner, c); - lru_gen_migrate_mm(mm); - task_unlock(c); - put_task_struct(c); } #endif /* CONFIG_MEMCG */ diff --git a/kernel/fork.c b/kernel/fork.c index 942e3d8617bf..cc760491f201 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -44,6 +44,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> +#include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -207,9 +208,10 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm) unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { - if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL) - continue; - return true; + struct vm_struct *tmp = NULL; + + if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm)) + return true; } return false; } @@ -992,10 +994,10 @@ void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ -static void set_max_threads(unsigned int max_threads_suggested) +static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; - unsigned long nr_pages = totalram_pages(); + unsigned long nr_pages = PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); /* * The number of threads shall be limited such that the thread @@ -1018,7 +1020,7 @@ static void set_max_threads(unsigned int max_threads_suggested) int arch_task_struct_size __read_mostly; #endif -static void task_struct_whitelist(unsigned long *offset, unsigned long *size) +static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); @@ -1519,14 +1521,13 @@ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; + if (task->flags & PF_KTHREAD) + return NULL; + task_lock(task); mm = task->mm; - if (mm) { - if (task->flags & PF_KTHREAD) - mm = NULL; - else - mmget(mm); - } + if (mm) + mmget(mm); task_unlock(task); return mm; } @@ -3403,7 +3404,7 @@ int unshare_files(void) return 0; } -int sysctl_max_threads(struct ctl_table *table, int write, +int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 1d92016b0b3c..959d99583d1c 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -127,7 +127,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * Ok, the task did not get scheduled for more than 2 minutes, * complain: */ - if (sysctl_hung_task_warnings) { + if (sysctl_hung_task_warnings || hung_task_call_panic) { if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -239,7 +239,7 @@ static long hung_timeout_jiffies(unsigned long last_checked, /* * Process updating of timeout sysctl */ -static int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, +static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index aae0402507ed..c6ffb97966be 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -9,14 +9,8 @@ static struct dentry *irq_dir; -struct irq_bit_descr { - unsigned int mask; - char *name; -}; -#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } - -static void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, - const struct irq_bit_descr *sd, int size) +void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, + const struct irq_bit_descr *sd, int size) { int i; diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index f6e5515ee077..b3e98668f4dd 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/irqdomain.h> #include <linux/device.h> #include <linux/gfp.h> #include <linux/irq.h> @@ -282,3 +283,43 @@ int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, } EXPORT_SYMBOL_GPL(devm_irq_setup_generic_chip); #endif /* CONFIG_GENERIC_IRQ_CHIP */ + +#ifdef CONFIG_IRQ_DOMAIN +static void devm_irq_domain_remove(struct device *dev, void *res) +{ + struct irq_domain **domain = res; + + irq_domain_remove(*domain); +} + +/** + * devm_irq_domain_instantiate() - Instantiate a new irq domain data for a + * managed device. + * @dev: Device to instantiate the domain for + * @info: Domain information pointer pointing to the information for this + * domain + * + * Return: A pointer to the instantiated irq domain or an ERR_PTR value. + */ +struct irq_domain *devm_irq_domain_instantiate(struct device *dev, + const struct irq_domain_info *info) +{ + struct irq_domain *domain; + struct irq_domain **dr; + + dr = devres_alloc(devm_irq_domain_remove, sizeof(*dr), GFP_KERNEL); + if (!dr) + return ERR_PTR(-ENOMEM); + + domain = irq_domain_instantiate(info); + if (!IS_ERR(domain)) { + *dr = domain; + devres_add(dev, dr); + } else { + devres_free(dr); + } + + return domain; +} +EXPORT_SYMBOL_GPL(devm_irq_domain_instantiate); +#endif /* CONFIG_IRQ_DOMAIN */ diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index d39a40bc542b..32ffcbb87fa1 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -276,21 +276,14 @@ irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags) } /** - * __irq_alloc_domain_generic_chips - Allocate generic chips for an irq domain - * @d: irq domain for which to allocate chips - * @irqs_per_chip: Number of interrupts each chip handles (max 32) - * @num_ct: Number of irq_chip_type instances associated with this - * @name: Name of the irq chip - * @handler: Default flow handler associated with these chips - * @clr: IRQ_* bits to clear in the mapping function - * @set: IRQ_* bits to set in the mapping function - * @gcflags: Generic chip specific setup flags + * irq_domain_alloc_generic_chips - Allocate generic chips for an irq domain + * @d: irq domain for which to allocate chips + * @info: Generic chip information + * + * Return: 0 on success, negative error code on failure */ -int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, - int num_ct, const char *name, - irq_flow_handler_t handler, - unsigned int clr, unsigned int set, - enum irq_gc_flags gcflags) +int irq_domain_alloc_generic_chips(struct irq_domain *d, + const struct irq_domain_chip_generic_info *info) { struct irq_domain_chip_generic *dgc; struct irq_chip_generic *gc; @@ -300,27 +293,29 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, size_t gc_sz; size_t sz; void *tmp; + int ret; if (d->gc) return -EBUSY; - numchips = DIV_ROUND_UP(d->revmap_size, irqs_per_chip); + numchips = DIV_ROUND_UP(d->revmap_size, info->irqs_per_chip); if (!numchips) return -EINVAL; /* Allocate a pointer, generic chip and chiptypes for each chip */ - gc_sz = struct_size(gc, chip_types, num_ct); + gc_sz = struct_size(gc, chip_types, info->num_ct); dgc_sz = struct_size(dgc, gc, numchips); sz = dgc_sz + numchips * gc_sz; tmp = dgc = kzalloc(sz, GFP_KERNEL); if (!dgc) return -ENOMEM; - dgc->irqs_per_chip = irqs_per_chip; + dgc->irqs_per_chip = info->irqs_per_chip; dgc->num_chips = numchips; - dgc->irq_flags_to_set = set; - dgc->irq_flags_to_clear = clr; - dgc->gc_flags = gcflags; + dgc->irq_flags_to_set = info->irq_flags_to_set; + dgc->irq_flags_to_clear = info->irq_flags_to_clear; + dgc->gc_flags = info->gc_flags; + dgc->exit = info->exit; d->gc = dgc; /* Calc pointer to the first generic chip */ @@ -328,15 +323,22 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, for (i = 0; i < numchips; i++) { /* Store the pointer to the generic chip */ dgc->gc[i] = gc = tmp; - irq_init_generic_chip(gc, name, num_ct, i * irqs_per_chip, - NULL, handler); + irq_init_generic_chip(gc, info->name, info->num_ct, + i * dgc->irqs_per_chip, NULL, + info->handler); gc->domain = d; - if (gcflags & IRQ_GC_BE_IO) { + if (dgc->gc_flags & IRQ_GC_BE_IO) { gc->reg_readl = &irq_readl_be; gc->reg_writel = &irq_writel_be; } + if (info->init) { + ret = info->init(gc); + if (ret) + goto err; + } + raw_spin_lock_irqsave(&gc_lock, flags); list_add_tail(&gc->list, &gc_list); raw_spin_unlock_irqrestore(&gc_lock, flags); @@ -344,6 +346,69 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, tmp += gc_sz; } return 0; + +err: + while (i--) { + if (dgc->exit) + dgc->exit(dgc->gc[i]); + irq_remove_generic_chip(dgc->gc[i], ~0U, 0, 0); + } + d->gc = NULL; + kfree(dgc); + return ret; +} +EXPORT_SYMBOL_GPL(irq_domain_alloc_generic_chips); + +/** + * irq_domain_remove_generic_chips - Remove generic chips from an irq domain + * @d: irq domain for which generic chips are to be removed + */ +void irq_domain_remove_generic_chips(struct irq_domain *d) +{ + struct irq_domain_chip_generic *dgc = d->gc; + unsigned int i; + + if (!dgc) + return; + + for (i = 0; i < dgc->num_chips; i++) { + if (dgc->exit) + dgc->exit(dgc->gc[i]); + irq_remove_generic_chip(dgc->gc[i], ~0U, 0, 0); + } + d->gc = NULL; + kfree(dgc); +} +EXPORT_SYMBOL_GPL(irq_domain_remove_generic_chips); + +/** + * __irq_alloc_domain_generic_chips - Allocate generic chips for an irq domain + * @d: irq domain for which to allocate chips + * @irqs_per_chip: Number of interrupts each chip handles (max 32) + * @num_ct: Number of irq_chip_type instances associated with this + * @name: Name of the irq chip + * @handler: Default flow handler associated with these chips + * @clr: IRQ_* bits to clear in the mapping function + * @set: IRQ_* bits to set in the mapping function + * @gcflags: Generic chip specific setup flags + */ +int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, + int num_ct, const char *name, + irq_flow_handler_t handler, + unsigned int clr, unsigned int set, + enum irq_gc_flags gcflags) +{ + struct irq_domain_chip_generic_info info = { + .irqs_per_chip = irqs_per_chip, + .num_ct = num_ct, + .name = name, + .handler = handler, + .irq_flags_to_clear = clr, + .irq_flags_to_set = set, + .gc_flags = gcflags, + }; + + return irq_domain_alloc_generic_chips(d, &info); } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ed28059e9849..fe0272cd84a5 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -501,6 +501,16 @@ static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd) #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include <linux/debugfs.h> +struct irq_bit_descr { + unsigned int mask; + char *name; +}; + +#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } + +void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, + const struct irq_bit_descr *sd, int size); + void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index aadc8891cc16..cea8f6874b1f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -111,6 +111,7 @@ EXPORT_SYMBOL_GPL(__irq_domain_alloc_fwnode); /** * irq_domain_free_fwnode - Free a non-OF-backed fwnode_handle + * @fwnode: fwnode_handle to free * * Free a fwnode_handle allocated with irq_domain_alloc_fwnode. */ @@ -127,27 +128,12 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); -static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode, - unsigned int size, - irq_hw_number_t hwirq_max, - int direct_max, - const struct irq_domain_ops *ops, - void *host_data) +static int irq_domain_set_name(struct irq_domain *domain, + const struct fwnode_handle *fwnode, + enum irq_domain_bus_token bus_token) { - struct irqchip_fwid *fwid; - struct irq_domain *domain; - static atomic_t unknown_domains; - - if (WARN_ON((size && direct_max) || - (!IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && direct_max) || - (direct_max && (direct_max != hwirq_max)))) - return NULL; - - domain = kzalloc_node(struct_size(domain, revmap, size), - GFP_KERNEL, of_node_to_nid(to_of_node(fwnode))); - if (!domain) - return NULL; + struct irqchip_fwid *fwid; if (is_fwnode_irqchip(fwnode)) { fwid = container_of(fwnode, struct irqchip_fwid, fwnode); @@ -155,17 +141,23 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode, switch (fwid->type) { case IRQCHIP_FWNODE_NAMED: case IRQCHIP_FWNODE_NAMED_ID: - domain->fwnode = fwnode; - domain->name = kstrdup(fwid->name, GFP_KERNEL); - if (!domain->name) { - kfree(domain); - return NULL; - } + domain->name = bus_token ? + kasprintf(GFP_KERNEL, "%s-%d", + fwid->name, bus_token) : + kstrdup(fwid->name, GFP_KERNEL); + if (!domain->name) + return -ENOMEM; domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; break; default: - domain->fwnode = fwnode; domain->name = fwid->name; + if (bus_token) { + domain->name = kasprintf(GFP_KERNEL, "%s-%d", + fwid->name, bus_token); + if (!domain->name) + return -ENOMEM; + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + } break; } } else if (is_of_node(fwnode) || is_acpi_device_node(fwnode) || @@ -177,42 +169,68 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode, * unhappy about. Replace them with ':', which does * the trick and is not as offensive as '\'... */ - name = kasprintf(GFP_KERNEL, "%pfw", fwnode); - if (!name) { - kfree(domain); - return NULL; - } + name = bus_token ? + kasprintf(GFP_KERNEL, "%pfw-%d", fwnode, bus_token) : + kasprintf(GFP_KERNEL, "%pfw", fwnode); + if (!name) + return -ENOMEM; domain->name = strreplace(name, '/', ':'); - domain->fwnode = fwnode; domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; } if (!domain->name) { if (fwnode) pr_err("Invalid fwnode type for irqdomain\n"); - domain->name = kasprintf(GFP_KERNEL, "unknown-%d", - atomic_inc_return(&unknown_domains)); - if (!domain->name) { - kfree(domain); - return NULL; - } + domain->name = bus_token ? + kasprintf(GFP_KERNEL, "unknown-%d-%d", + atomic_inc_return(&unknown_domains), + bus_token) : + kasprintf(GFP_KERNEL, "unknown-%d", + atomic_inc_return(&unknown_domains)); + if (!domain->name) + return -ENOMEM; domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; } - fwnode_handle_get(fwnode); - fwnode_dev_initialized(fwnode, true); + return 0; +} + +static struct irq_domain *__irq_domain_create(const struct irq_domain_info *info) +{ + struct irq_domain *domain; + int err; + + if (WARN_ON((info->size && info->direct_max) || + (!IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && info->direct_max) || + (info->direct_max && info->direct_max != info->hwirq_max))) + return ERR_PTR(-EINVAL); + + domain = kzalloc_node(struct_size(domain, revmap, info->size), + GFP_KERNEL, of_node_to_nid(to_of_node(info->fwnode))); + if (!domain) + return ERR_PTR(-ENOMEM); + + err = irq_domain_set_name(domain, info->fwnode, info->bus_token); + if (err) { + kfree(domain); + return ERR_PTR(err); + } + + domain->fwnode = fwnode_handle_get(info->fwnode); + fwnode_dev_initialized(domain->fwnode, true); /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); - domain->ops = ops; - domain->host_data = host_data; - domain->hwirq_max = hwirq_max; + domain->ops = info->ops; + domain->host_data = info->host_data; + domain->bus_token = info->bus_token; + domain->hwirq_max = info->hwirq_max; - if (direct_max) + if (info->direct_max) domain->flags |= IRQ_DOMAIN_FLAG_NO_MAP; - domain->revmap_size = size; + domain->revmap_size = info->size; /* * Hierarchical domains use the domain lock of the root domain @@ -240,34 +258,64 @@ static void __irq_domain_publish(struct irq_domain *domain) pr_debug("Added domain %s\n", domain->name); } +static void irq_domain_free(struct irq_domain *domain) +{ + fwnode_dev_initialized(domain->fwnode, false); + fwnode_handle_put(domain->fwnode); + if (domain->flags & IRQ_DOMAIN_NAME_ALLOCATED) + kfree(domain->name); + kfree(domain); +} + /** - * __irq_domain_add() - Allocate a new irq_domain data structure - * @fwnode: firmware node for the interrupt controller - * @size: Size of linear map; 0 for radix mapping only - * @hwirq_max: Maximum number of interrupts supported by controller - * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no - * direct mapping - * @ops: domain callbacks - * @host_data: Controller private data pointer + * irq_domain_instantiate() - Instantiate a new irq domain data structure + * @info: Domain information pointer pointing to the information for this domain * - * Allocates and initializes an irq_domain structure. - * Returns pointer to IRQ domain, or NULL on failure. + * Return: A pointer to the instantiated irq domain or an ERR_PTR value. */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, - irq_hw_number_t hwirq_max, int direct_max, - const struct irq_domain_ops *ops, - void *host_data) +struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info) { struct irq_domain *domain; + int err; + + domain = __irq_domain_create(info); + if (IS_ERR(domain)) + return domain; - domain = __irq_domain_create(fwnode, size, hwirq_max, direct_max, - ops, host_data); - if (domain) - __irq_domain_publish(domain); + domain->flags |= info->domain_flags; + domain->exit = info->exit; + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (info->parent) { + domain->root = info->parent->root; + domain->parent = info->parent; + } +#endif + + if (info->dgc_info) { + err = irq_domain_alloc_generic_chips(domain, info->dgc_info); + if (err) + goto err_domain_free; + } + + if (info->init) { + err = info->init(domain); + if (err) + goto err_domain_gc_remove; + } + + __irq_domain_publish(domain); return domain; + +err_domain_gc_remove: + if (info->dgc_info) + irq_domain_remove_generic_chips(domain); +err_domain_free: + irq_domain_free(domain); + return ERR_PTR(err); } -EXPORT_SYMBOL_GPL(__irq_domain_add); +EXPORT_SYMBOL_GPL(irq_domain_instantiate); /** * irq_domain_remove() - Remove an irq domain. @@ -279,6 +327,9 @@ EXPORT_SYMBOL_GPL(__irq_domain_add); */ void irq_domain_remove(struct irq_domain *domain) { + if (domain->exit) + domain->exit(domain); + mutex_lock(&irq_domain_mutex); debugfs_remove_domain_dir(domain); @@ -294,13 +345,11 @@ void irq_domain_remove(struct irq_domain *domain) mutex_unlock(&irq_domain_mutex); - pr_debug("Removed domain %s\n", domain->name); + if (domain->flags & IRQ_DOMAIN_FLAG_DESTROY_GC) + irq_domain_remove_generic_chips(domain); - fwnode_dev_initialized(domain->fwnode, false); - fwnode_handle_put(domain->fwnode); - if (domain->flags & IRQ_DOMAIN_NAME_ALLOCATED) - kfree(domain->name); - kfree(domain); + pr_debug("Removed domain %s\n", domain->name); + irq_domain_free(domain); } EXPORT_SYMBOL_GPL(irq_domain_remove); @@ -360,10 +409,17 @@ struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { + struct irq_domain_info info = { + .fwnode = fwnode, + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + }; struct irq_domain *domain; - domain = __irq_domain_add(fwnode, size, size, 0, ops, host_data); - if (!domain) + domain = irq_domain_instantiate(&info); + if (IS_ERR(domain)) return NULL; if (first_irq > 0) { @@ -416,11 +472,20 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { + struct irq_domain_info info = { + .fwnode = fwnode, + .size = first_hwirq + size, + .hwirq_max = first_hwirq + size, + .ops = ops, + .host_data = host_data, + }; struct irq_domain *domain; - domain = __irq_domain_add(fwnode, first_hwirq + size, first_hwirq + size, 0, ops, host_data); - if (domain) - irq_domain_associate_many(domain, first_irq, first_hwirq, size); + domain = irq_domain_instantiate(&info); + if (IS_ERR(domain)) + return NULL; + + irq_domain_associate_many(domain, first_irq, first_hwirq, size); return domain; } @@ -438,7 +503,8 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, struct fwnode_handle *fwnode = fwspec->fwnode; int rc; - /* We might want to match the legacy controller last since + /* + * We might want to match the legacy controller last since * it might potentially be set to match all interrupts in * the absence of a device node. This isn't a problem so far * yet though... @@ -982,6 +1048,12 @@ EXPORT_SYMBOL_GPL(__irq_resolve_mapping); /** * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings + * @d: Interrupt domain involved in the translation + * @ctrlr: The device tree node for the device whose interrupt is translated + * @intspec: The interrupt specifier data from the device tree + * @intsize: The number of entries in @intspec + * @out_hwirq: Pointer to storage for the hardware interrupt number + * @out_type: Pointer to storage for the interrupt type * * Device Tree IRQ specifier translation function which works with one cell * bindings where the cell value maps directly to the hwirq number. @@ -1000,6 +1072,12 @@ EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell); /** * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings + * @d: Interrupt domain involved in the translation + * @ctrlr: The device tree node for the device whose interrupt is translated + * @intspec: The interrupt specifier data from the device tree + * @intsize: The number of entries in @intspec + * @out_hwirq: Pointer to storage for the hardware interrupt number + * @out_type: Pointer to storage for the interrupt type * * Device Tree IRQ specifier translation function which works with two cell * bindings where the cell values map directly to the hwirq number @@ -1018,6 +1096,12 @@ EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell); /** * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings + * @d: Interrupt domain involved in the translation + * @ctrlr: The device tree node for the device whose interrupt is translated + * @intspec: The interrupt specifier data from the device tree + * @intsize: The number of entries in @intspec + * @out_hwirq: Pointer to storage for the hardware interrupt number + * @out_type: Pointer to storage for the interrupt type * * Device Tree IRQ specifier translation function which works with either one * or two cell bindings where the cell values map directly to the hwirq number @@ -1051,6 +1135,10 @@ EXPORT_SYMBOL_GPL(irq_domain_simple_ops); /** * irq_domain_translate_onecell() - Generic translate for direct one cell * bindings + * @d: Interrupt domain involved in the translation + * @fwspec: The firmware interrupt specifier to translate + * @out_hwirq: Pointer to storage for the hardware interrupt number + * @out_type: Pointer to storage for the interrupt type */ int irq_domain_translate_onecell(struct irq_domain *d, struct irq_fwspec *fwspec, @@ -1068,6 +1156,10 @@ EXPORT_SYMBOL_GPL(irq_domain_translate_onecell); /** * irq_domain_translate_twocell() - Generic translate for direct two cell * bindings + * @d: Interrupt domain involved in the translation + * @fwspec: The firmware interrupt specifier to translate + * @out_hwirq: Pointer to storage for the hardware interrupt number + * @out_type: Pointer to storage for the interrupt type * * Device Tree IRQ specifier translation function which works with two cell * bindings where the cell values map directly to the hwirq number @@ -1144,23 +1236,22 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, const struct irq_domain_ops *ops, void *host_data) { - struct irq_domain *domain; - - if (size) - domain = __irq_domain_create(fwnode, size, size, 0, ops, host_data); - else - domain = __irq_domain_create(fwnode, 0, ~0, 0, ops, host_data); - - if (domain) { - if (parent) - domain->root = parent->root; - domain->parent = parent; - domain->flags |= flags; + struct irq_domain_info info = { + .fwnode = fwnode, + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + .domain_flags = flags, + .parent = parent, + }; + struct irq_domain *d; - __irq_domain_publish(domain); - } + if (!info.size) + info.hwirq_max = ~0U; - return domain; + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } EXPORT_SYMBOL_GPL(irq_domain_create_hierarchy); @@ -1932,13 +2023,26 @@ static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq static struct dentry *domain_dir; -static void -irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) +static const struct irq_bit_descr irqdomain_flags[] = { + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_HIERARCHY), + BIT_MASK_DESCR(IRQ_DOMAIN_NAME_ALLOCATED), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_IPI_PER_CPU), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_IPI_SINGLE), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_MSI), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_ISOLATED_MSI), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_NO_MAP), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_MSI_PARENT), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_MSI_DEVICE), + BIT_MASK_DESCR(IRQ_DOMAIN_FLAG_NONCORE), +}; + +static void irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) { seq_printf(m, "%*sname: %s\n", ind, "", d->name); seq_printf(m, "%*ssize: %u\n", ind + 1, "", d->revmap_size); seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); + irq_debug_show_bits(m, ind, d->flags, irqdomain_flags, ARRAY_SIZE(irqdomain_flags)); if (d->ops && d->ops->debug_show) d->ops->debug_show(m, d, NULL, ind + 1); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2024f89baea4..5fa0547ece0c 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -8,18 +8,34 @@ * This file contains common code to support Message Signaled Interrupts for * PCI compatible and non PCI compatible devices. */ -#include <linux/types.h> #include <linux/device.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/msi.h> +#include <linux/mutex.h> +#include <linux/pci.h> #include <linux/slab.h> #include <linux/sysfs.h> -#include <linux/pci.h> +#include <linux/types.h> +#include <linux/xarray.h> #include "internals.h" /** + * struct msi_device_data - MSI per device data + * @properties: MSI properties which are interesting to drivers + * @mutex: Mutex protecting the MSI descriptor store + * @__domains: Internal data for per device MSI domains + * @__iter_idx: Index to search the next entry for iterators + */ +struct msi_device_data { + unsigned long properties; + struct mutex mutex; + struct msi_dev_domain __domains[MSI_MAX_DEVICE_IRQDOMAINS]; + unsigned long __iter_idx; +}; + +/** * struct msi_ctrl - MSI internal management control structure * @domid: ID of the domain on which management operations should be done * @first: First (hardware) slot index to operate on @@ -1088,8 +1104,8 @@ bool msi_match_device_irq_domain(struct device *dev, unsigned int domid, return ret; } -int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +static int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; @@ -1097,77 +1113,6 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, return ops->msi_prepare(domain, dev, nvec, arg); } -int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, - int virq_base, int nvec, msi_alloc_info_t *arg) -{ - struct msi_domain_info *info = domain->host_data; - struct msi_domain_ops *ops = info->ops; - struct msi_ctrl ctrl = { - .domid = MSI_DEFAULT_DOMAIN, - .first = virq_base, - .last = virq_base + nvec - 1, - }; - struct msi_desc *desc; - struct xarray *xa; - int ret, virq; - - msi_lock_descs(dev); - - if (!msi_ctrl_valid(dev, &ctrl)) { - ret = -EINVAL; - goto unlock; - } - - ret = msi_domain_add_simple_msi_descs(dev, &ctrl); - if (ret) - goto unlock; - - xa = &dev->msi.data->__domains[ctrl.domid].store; - - for (virq = virq_base; virq < virq_base + nvec; virq++) { - desc = xa_load(xa, virq); - desc->irq = virq; - - ops->set_desc(arg, desc); - ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg); - if (ret) - goto fail; - - irq_set_msi_desc(virq, desc); - } - msi_unlock_descs(dev); - return 0; - -fail: - for (--virq; virq >= virq_base; virq--) { - msi_domain_depopulate_descs(dev, virq, 1); - irq_domain_free_irqs_common(domain, virq, 1); - } - msi_domain_free_descs(dev, &ctrl); -unlock: - msi_unlock_descs(dev); - return ret; -} - -void msi_domain_depopulate_descs(struct device *dev, int virq_base, int nvec) -{ - struct msi_ctrl ctrl = { - .domid = MSI_DEFAULT_DOMAIN, - .first = virq_base, - .last = virq_base + nvec - 1, - }; - struct msi_desc *desc; - struct xarray *xa; - unsigned long idx; - - if (!msi_ctrl_valid(dev, &ctrl)) - return; - - xa = &dev->msi.data->__domains[ctrl.domid].store; - xa_for_each_range(xa, idx, desc, ctrl.first, ctrl.last) - desc->irq = 0; -} - /* * Carefully check whether the device can use reservation mode. If * reservation mode is enabled then the early activation will assign a diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 5c320c3f10a7..8cccdf40725a 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -461,10 +461,10 @@ int show_interrupts(struct seq_file *p, void *v) { static int prec; - unsigned long flags, any_count = 0; int i = *(loff_t *) v, j; struct irqaction *action; struct irq_desc *desc; + unsigned long flags; if (i > ACTUAL_NR_IRQS) return 0; @@ -488,10 +488,7 @@ int show_interrupts(struct seq_file *p, void *v) if (!desc || irq_settings_is_hidden(desc)) goto outsparse; - if (desc->kstat_irqs) - any_count = kstat_irqs_desc(desc, cpu_online_mask); - - if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) + if (!desc->action || irq_desc_is_chained(desc) || !desc->kstat_irqs) goto outsparse; seq_printf(p, "%*d: ", prec, i); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 98b9622d372e..fb2c77368d18 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -148,9 +148,6 @@ static unsigned int get_symbol_offset(unsigned long pos) unsigned long kallsyms_sym_address(int idx) { - if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) - return kallsyms_addresses[idx]; - /* values are unsigned offsets if --absolute-percpu is not in effect */ if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU)) return kallsyms_relative_base + (u32)kallsyms_offsets[idx]; @@ -325,7 +322,7 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; - /* Do a binary search on the sorted kallsyms_addresses array. */ + /* Do a binary search on the sorted kallsyms_offsets array. */ low = 0; high = kallsyms_num_syms; diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h index 85480274fc8f..9633782f8250 100644 --- a/kernel/kallsyms_internal.h +++ b/kernel/kallsyms_internal.h @@ -4,12 +4,6 @@ #include <linux/types.h> -/* - * These will be re-linked against their real values during the second link - * stage. Preliminary values must be provided in the linker script using the - * PROVIDE() directive so that the first link stage can complete successfully. - */ -extern const unsigned long kallsyms_addresses[]; extern const int kallsyms_offsets[]; extern const u8 kallsyms_names[]; diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 9112d69d68b0..c0caa14880c3 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -888,7 +888,7 @@ struct kimage *kexec_crash_image; static int kexec_load_disabled; #ifdef CONFIG_SYSCTL -static int kexec_limit_handler(struct ctl_table *table, int write, +static int kexec_limit_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct kexec_load_limit *limit = table->data; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6a76a8100073..e85de37d9e1e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -939,7 +939,7 @@ static void unoptimize_all_kprobes(void) static DEFINE_MUTEX(kprobe_sysctl_mutex); static int sysctl_kprobes_optimization; -static int proc_kprobes_optimization_handler(struct ctl_table *table, +static int proc_kprobes_optimization_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 07fb5987b42b..1bab21b4718f 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -92,7 +92,14 @@ static ssize_t profiling_store(struct kobject *kobj, const char *buf, size_t count) { int ret; + static DEFINE_MUTEX(lock); + /* + * We need serialization, for profile_setup() initializes prof_on + * value and profile_init() must not reallocate prof_buffer after + * once allocated. + */ + guard(mutex)(&lock); if (prof_on) return -EEXIST; /* diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 84c53285f499..7a75eab9c179 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -65,7 +65,7 @@ static struct latency_record latency_record[MAXLR]; int latencytop_enabled; #ifdef CONFIG_SYSCTL -static int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, +static int sysctl_latencytop(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 52426665eecc..3c21c31796db 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -346,6 +346,7 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, * /sys/kernel/livepatch/<patch>/enabled * /sys/kernel/livepatch/<patch>/transition * /sys/kernel/livepatch/<patch>/force + * /sys/kernel/livepatch/<patch>/replace * /sys/kernel/livepatch/<patch>/<object> * /sys/kernel/livepatch/<patch>/<object>/patched * /sys/kernel/livepatch/<patch>/<object>/<function,sympos> @@ -401,7 +402,7 @@ static ssize_t enabled_show(struct kobject *kobj, struct klp_patch *patch; patch = container_of(kobj, struct klp_patch, kobj); - return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->enabled); + return sysfs_emit(buf, "%d\n", patch->enabled); } static ssize_t transition_show(struct kobject *kobj, @@ -410,8 +411,7 @@ static ssize_t transition_show(struct kobject *kobj, struct klp_patch *patch; patch = container_of(kobj, struct klp_patch, kobj); - return snprintf(buf, PAGE_SIZE-1, "%d\n", - patch == klp_transition_patch); + return sysfs_emit(buf, "%d\n", patch == klp_transition_patch); } static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -443,13 +443,24 @@ static ssize_t force_store(struct kobject *kobj, struct kobj_attribute *attr, return count; } +static ssize_t replace_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch; + + patch = container_of(kobj, struct klp_patch, kobj); + return sysfs_emit(buf, "%d\n", patch->replace); +} + 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 attribute *klp_patch_attrs[] = { &enabled_kobj_attr.attr, &transition_kobj_attr.attr, &force_kobj_attr.attr, + &replace_kobj_attr.attr, NULL }; ATTRIBUTE_GROUPS(klp_patch); diff --git a/kernel/panic.c b/kernel/panic.c index 8bff183d6180..f861bedc1925 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -35,6 +35,7 @@ #include <linux/debugfs.h> #include <linux/sysfs.h> #include <linux/context_tracking.h> +#include <linux/seq_buf.h> #include <trace/events/error_report.h> #include <asm/sections.h> @@ -470,32 +471,83 @@ void panic(const char *fmt, ...) EXPORT_SYMBOL(panic); +#define TAINT_FLAG(taint, _c_true, _c_false, _module) \ + [ TAINT_##taint ] = { \ + .c_true = _c_true, .c_false = _c_false, \ + .module = _module, \ + .desc = #taint, \ + } + /* * TAINT_FORCED_RMMOD could be a per-module flag but the module * is being removed anyway. */ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { - [ TAINT_PROPRIETARY_MODULE ] = { 'P', 'G', true }, - [ TAINT_FORCED_MODULE ] = { 'F', ' ', true }, - [ TAINT_CPU_OUT_OF_SPEC ] = { 'S', ' ', false }, - [ TAINT_FORCED_RMMOD ] = { 'R', ' ', false }, - [ TAINT_MACHINE_CHECK ] = { 'M', ' ', false }, - [ TAINT_BAD_PAGE ] = { 'B', ' ', false }, - [ TAINT_USER ] = { 'U', ' ', false }, - [ TAINT_DIE ] = { 'D', ' ', false }, - [ TAINT_OVERRIDDEN_ACPI_TABLE ] = { 'A', ' ', false }, - [ TAINT_WARN ] = { 'W', ' ', false }, - [ TAINT_CRAP ] = { 'C', ' ', true }, - [ TAINT_FIRMWARE_WORKAROUND ] = { 'I', ' ', false }, - [ TAINT_OOT_MODULE ] = { 'O', ' ', true }, - [ TAINT_UNSIGNED_MODULE ] = { 'E', ' ', true }, - [ TAINT_SOFTLOCKUP ] = { 'L', ' ', false }, - [ TAINT_LIVEPATCH ] = { 'K', ' ', true }, - [ TAINT_AUX ] = { 'X', ' ', true }, - [ TAINT_RANDSTRUCT ] = { 'T', ' ', true }, - [ TAINT_TEST ] = { 'N', ' ', true }, + TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G', true), + TAINT_FLAG(FORCED_MODULE, 'F', ' ', true), + TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' ', false), + TAINT_FLAG(FORCED_RMMOD, 'R', ' ', false), + TAINT_FLAG(MACHINE_CHECK, 'M', ' ', false), + TAINT_FLAG(BAD_PAGE, 'B', ' ', false), + TAINT_FLAG(USER, 'U', ' ', false), + TAINT_FLAG(DIE, 'D', ' ', false), + TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' ', false), + TAINT_FLAG(WARN, 'W', ' ', false), + TAINT_FLAG(CRAP, 'C', ' ', true), + TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' ', false), + TAINT_FLAG(OOT_MODULE, 'O', ' ', true), + TAINT_FLAG(UNSIGNED_MODULE, 'E', ' ', true), + TAINT_FLAG(SOFTLOCKUP, 'L', ' ', false), + TAINT_FLAG(LIVEPATCH, 'K', ' ', true), + TAINT_FLAG(AUX, 'X', ' ', true), + TAINT_FLAG(RANDSTRUCT, 'T', ' ', true), + TAINT_FLAG(TEST, 'N', ' ', true), }; +#undef TAINT_FLAG + +static void print_tainted_seq(struct seq_buf *s, bool verbose) +{ + const char *sep = ""; + int i; + + if (!tainted_mask) { + seq_buf_puts(s, "Not tainted"); + return; + } + + seq_buf_printf(s, "Tainted: "); + for (i = 0; i < TAINT_FLAGS_COUNT; i++) { + const struct taint_flag *t = &taint_flags[i]; + bool is_set = test_bit(i, &tainted_mask); + char c = is_set ? t->c_true : t->c_false; + + if (verbose) { + if (is_set) { + seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc); + sep = ", "; + } + } else { + seq_buf_putc(s, c); + } + } +} + +static const char *_print_tainted(bool verbose) +{ + /* FIXME: what should the size be? */ + static char buf[sizeof(taint_flags)]; + struct seq_buf s; + + BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); + + seq_buf_init(&s, buf, sizeof(buf)); + + print_tainted_seq(&s, verbose); + + return seq_buf_str(&s); +} + /** * print_tainted - return a string to represent the kernel taint state. * @@ -506,25 +558,15 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { */ const char *print_tainted(void) { - static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")]; - - BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); - - if (tainted_mask) { - char *s; - int i; - - s = buf + sprintf(buf, "Tainted: "); - for (i = 0; i < TAINT_FLAGS_COUNT; i++) { - const struct taint_flag *t = &taint_flags[i]; - *s++ = test_bit(i, &tainted_mask) ? - t->c_true : t->c_false; - } - *s = 0; - } else - snprintf(buf, sizeof(buf), "Not tainted"); + return _print_tainted(false); +} - return buf; +/** + * print_tainted_verbose - A more verbose version of print_tainted() + */ +const char *print_tainted_verbose(void) +{ + return _print_tainted(true); } int test_taint(unsigned flag) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index bdf0087d6442..d70ab49d5b4a 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -261,7 +261,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) } #ifdef CONFIG_CHECKPOINT_RESTORE -static int pid_ns_ctl_handler(struct ctl_table *table, int write, +static int pid_ns_ctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid_namespace *pid_ns = task_active_pid_ns(current); diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index fe9fb991dc42..18ecaef6be41 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -5,7 +5,7 @@ #include <linux/pid_namespace.h> #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) -static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table, +static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { struct pid_namespace *ns = task_active_pid_ns(current); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 753b8dd42a59..82b884b67152 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -200,12 +200,11 @@ void free_all_swap_pages(int swap) while ((node = swsusp_extents.rb_node)) { struct swsusp_extent *ext; - unsigned long offset; ext = rb_entry(node, struct swsusp_extent, node); rb_erase(node, &swsusp_extents); - for (offset = ext->start; offset <= ext->end; offset++) - swap_free(swp_entry(swap, offset)); + swap_free_nr(swp_entry(swap, ext->start), + ext->end - ext->start + 1); kfree(ext); } diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 6c2afee5ef62..19dcc5832651 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -8,7 +8,7 @@ #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) void __init printk_sysctl_init(void); -int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, +int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #else #define printk_sysctl_init() do { } while (0) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7d91593f0ecf..054c0e7784fd 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -197,7 +197,7 @@ __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) -int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, +int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; @@ -4372,15 +4372,15 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) EXPORT_SYMBOL_GPL(kmsg_dump_rewind); /** - * console_replay_all - replay kernel log on consoles + * console_try_replay_all - try to replay kernel log on consoles * * Try to obtain lock on console subsystem and replay all * available records in printk buffer on the consoles. * Does nothing if lock is not obtained. * - * Context: Any context. + * Context: Any, except for NMI. */ -void console_replay_all(void) +void console_try_replay_all(void) { if (console_trylock()) { __console_rewind_all(); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index 3e47dedce9e5..f5072dc85f7a 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -11,7 +11,7 @@ static const int ten_thousand = 10000; -static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, +static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write && !capable(CAP_SYS_ADMIN)) diff --git a/kernel/profile.c b/kernel/profile.c index 2b775cc5c28f..ff68d3816182 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -47,13 +47,6 @@ static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); -static cpumask_var_t prof_cpu_mask; -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); -static DEFINE_PER_CPU(int, cpu_profile_flip); -static DEFINE_MUTEX(profile_flip_mutex); -#endif /* CONFIG_SMP */ - int profile_setup(char *str) { static const char schedstr[] = "schedule"; @@ -114,11 +107,6 @@ int __ref profile_init(void) buffer_bytes = prof_len*sizeof(atomic_t); - if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_copy(prof_cpu_mask, cpu_possible_mask); - prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); if (prof_buffer) return 0; @@ -132,195 +120,16 @@ int __ref profile_init(void) if (prof_buffer) return 0; - free_cpumask_var(prof_cpu_mask); return -ENOMEM; } -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -/* - * Each cpu has a pair of open-addressed hashtables for pending - * profile hits. read_profile() IPI's all cpus to request them - * to flip buffers and flushes their contents to prof_buffer itself. - * Flip requests are serialized by the profile_flip_mutex. The sole - * use of having a second hashtable is for avoiding cacheline - * contention that would otherwise happen during flushes of pending - * profile hits required for the accuracy of reported profile hits - * and so resurrect the interrupt livelock issue. - * - * The open-addressed hashtables are indexed by profile buffer slot - * and hold the number of pending hits to that profile buffer slot on - * a cpu in an entry. When the hashtable overflows, all pending hits - * are accounted to their corresponding profile buffer slots with - * atomic_add() and the hashtable emptied. As numerous pending hits - * may be accounted to a profile buffer slot in a hashtable entry, - * this amortizes a number of atomic profile buffer increments likely - * to be far larger than the number of entries in the hashtable, - * particularly given that the number of distinct profile buffer - * positions to which hits are accounted during short intervals (e.g. - * several seconds) is usually very small. Exclusion from buffer - * flipping is provided by interrupt disablement (note that for - * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from - * process context). - * The hash function is meant to be lightweight as opposed to strong, - * and was vaguely inspired by ppc64 firmware-supported inverted - * pagetable hash functions, but uses a full hashtable full of finite - * collision chains, not just pairs of them. - * - * -- nyc - */ -static void __profile_flip_buffers(void *unused) -{ - int cpu = smp_processor_id(); - - per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); -} - -static void profile_flip_buffers(void) -{ - int i, j, cpu; - - mutex_lock(&profile_flip_mutex); - j = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; - for (i = 0; i < NR_PROFILE_HIT; ++i) { - if (!hits[i].hits) { - if (hits[i].pc) - hits[i].pc = 0; - continue; - } - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].hits = hits[i].pc = 0; - } - } - mutex_unlock(&profile_flip_mutex); -} - -static void profile_discard_flip_buffers(void) -{ - int i, cpu; - - mutex_lock(&profile_flip_mutex); - i = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; - memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); - } - mutex_unlock(&profile_flip_mutex); -} - -static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) -{ - unsigned long primary, secondary, flags, pc = (unsigned long)__pc; - int i, j, cpu; - struct profile_hit *hits; - - pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); - i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - cpu = get_cpu(); - hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; - if (!hits) { - put_cpu(); - return; - } - /* - * We buffer the global profiler buffer into a per-CPU - * queue and thus reduce the number of global (and possibly - * NUMA-alien) accesses. The write-queue is self-coalescing: - */ - local_irq_save(flags); - do { - for (j = 0; j < PROFILE_GRPSZ; ++j) { - if (hits[i + j].pc == pc) { - hits[i + j].hits += nr_hits; - goto out; - } else if (!hits[i + j].hits) { - hits[i + j].pc = pc; - hits[i + j].hits = nr_hits; - goto out; - } - } - i = (i + secondary) & (NR_PROFILE_HIT - 1); - } while (i != primary); - - /* - * Add the current hit(s) and flush the write-queue out - * to the global buffer: - */ - atomic_add(nr_hits, &prof_buffer[pc]); - for (i = 0; i < NR_PROFILE_HIT; ++i) { - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].pc = hits[i].hits = 0; - } -out: - local_irq_restore(flags); - put_cpu(); -} - -static int profile_dead_cpu(unsigned int cpu) -{ - struct page *page; - int i; - - if (cpumask_available(prof_cpu_mask)) - cpumask_clear_cpu(cpu, prof_cpu_mask); - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); - per_cpu(cpu_profile_hits, cpu)[i] = NULL; - __free_page(page); - } - } - return 0; -} - -static int profile_prepare_cpu(unsigned int cpu) -{ - int i, node = cpu_to_mem(cpu); - struct page *page; - - per_cpu(cpu_profile_flip, cpu) = 0; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) - continue; - - page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); - if (!page) { - profile_dead_cpu(cpu); - return -ENOMEM; - } - per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); - - } - return 0; -} - -static int profile_online_cpu(unsigned int cpu) -{ - if (cpumask_available(prof_cpu_mask)) - cpumask_set_cpu(cpu, prof_cpu_mask); - - return 0; -} - -#else /* !CONFIG_SMP */ -#define profile_flip_buffers() do { } while (0) -#define profile_discard_flip_buffers() do { } while (0) - static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; - atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); + if (pc < prof_len) + atomic_add(nr_hits, &prof_buffer[pc]); } -#endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -334,8 +143,8 @@ void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); - if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && - cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) + /* This is the old kernel-only legacy profiling */ + if (!user_mode(regs)) profile_hit(type, (void *)profile_pc(regs)); } @@ -358,7 +167,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) char *pnt; unsigned long sample_step = 1UL << prof_shift; - profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) @@ -404,7 +212,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return -EINVAL; } #endif - profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } @@ -418,40 +225,14 @@ static const struct proc_ops profile_proc_ops = { int __ref create_proc_profile(void) { struct proc_dir_entry *entry; -#ifdef CONFIG_SMP - enum cpuhp_state online_state; -#endif - int err = 0; if (!prof_on) return 0; -#ifdef CONFIG_SMP - err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", - profile_prepare_cpu, profile_dead_cpu); - if (err) - return err; - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", - profile_online_cpu, NULL); - if (err < 0) - goto err_state_prep; - online_state = err; - err = 0; -#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); - if (!entry) - goto err_state_onl; - proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); - - return err; -err_state_onl: -#ifdef CONFIG_SMP - cpuhp_remove_state(online_state); -err_state_prep: - cpuhp_remove_state(CPUHP_PROFILE_PREPARE); -#endif + if (entry) + proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); return err; } subsys_initcall(create_proc_profile); diff --git a/kernel/resource_kunit.c b/kernel/resource_kunit.c index 58ab9f914602..0e509985a44a 100644 --- a/kernel/resource_kunit.c +++ b/kernel/resource_kunit.c @@ -149,4 +149,5 @@ static struct kunit_suite resource_test_suite = { }; kunit_test_suite(resource_test_suite); +MODULE_DESCRIPTION("I/O Port & Memory Resource manager unit tests"); MODULE_LICENSE("GPL"); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ae5ef3013a55..a9f655025607 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1806,7 +1806,7 @@ static void uclamp_sync_util_min_rt_default(void) uclamp_update_util_min_rt_default(p); } -static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, +static int sysctl_sched_uclamp_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; @@ -4392,7 +4392,7 @@ static void reset_memory_tiering(void) } } -static int sysctl_numa_balancing(struct ctl_table *table, int write, +static int sysctl_numa_balancing(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4461,7 +4461,7 @@ out: __setup("schedstats=", setup_schedstats); #ifdef CONFIG_PROC_SYSCTL -static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, +static int sysctl_schedstats(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 63e49c8ffc4d..310523c1b9e3 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -26,9 +26,9 @@ int sysctl_sched_rt_runtime = 950000; #ifdef CONFIG_SYSCTL static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ; -static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sched_rt_sysctls[] = { { @@ -2952,7 +2952,7 @@ static void sched_rt_do_global(void) raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); } -static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_period, old_runtime; @@ -2991,7 +2991,7 @@ undo: return ret; } -static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 784a0be81e84..76504b776d03 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -285,7 +285,7 @@ void rebuild_sched_domains_energy(void) } #ifdef CONFIG_PROC_SYSCTL -static int sched_energy_aware_handler(struct ctl_table *table, int write, +static int sched_energy_aware_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, state; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index dc51e521bc1d..385d48293a5f 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2431,7 +2431,7 @@ static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged, return audit_seccomp_actions_logged(new, old, !ret); } -static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, +static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int write, void *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 0f9712584913..39fd620a7db6 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -21,7 +21,7 @@ static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); #ifdef CONFIG_SYSCTL -static int stack_erasing_sysctl(struct ctl_table *table, int write, +static int stack_erasing_sysctl(const struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e4421594fc25..79e6cb1d5c48 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -256,7 +256,7 @@ static bool proc_first_pos_non_zero_ignore(loff_t *ppos, * * Returns 0 on success. */ -int proc_dostring(struct ctl_table *table, int write, +int proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write) @@ -702,7 +702,7 @@ int do_proc_douintvec(const struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_dobool(struct ctl_table *table, int write, void *buffer, +int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp; @@ -739,7 +739,7 @@ int proc_dobool(struct ctl_table *table, int write, void *buffer, * * Returns 0 on success. */ -int proc_dointvec(struct ctl_table *table, int write, void *buffer, +int proc_dointvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); @@ -758,7 +758,7 @@ int proc_dointvec(struct ctl_table *table, int write, void *buffer, * * Returns 0 on success. */ -int proc_douintvec(struct ctl_table *table, int write, void *buffer, +int proc_douintvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, @@ -769,7 +769,7 @@ int proc_douintvec(struct ctl_table *table, int write, void *buffer, * Taint values can only be increased * This means we can safely use a temporary. */ -static int proc_taint(struct ctl_table *table, int write, +static int proc_taint(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -864,7 +864,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp, * * Returns 0 on success or -EINVAL on write when the range check fails. */ -int proc_dointvec_minmax(struct ctl_table *table, int write, +int proc_dointvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct do_proc_dointvec_minmax_conv_param param = { @@ -933,7 +933,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, * * Returns 0 on success or -ERANGE on write when the range check fails. */ -int proc_douintvec_minmax(struct ctl_table *table, int write, +int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct do_proc_douintvec_minmax_conv_param param = { @@ -961,7 +961,7 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, * * Returns 0 on success or an error on write when the range check fails. */ -int proc_dou8vec_minmax(struct ctl_table *table, int write, +int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp; @@ -998,7 +998,7 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); #ifdef CONFIG_MAGIC_SYSRQ -static int sysrq_sysctl_handler(struct ctl_table *table, int write, +static int sysrq_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int tmp, ret; @@ -1115,7 +1115,7 @@ static int do_proc_doulongvec_minmax(const struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_minmax(struct ctl_table *table, int write, +int proc_doulongvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l); @@ -1138,7 +1138,7 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_doulongvec_minmax(table, write, buffer, @@ -1259,14 +1259,14 @@ static int do_proc_dointvec_ms_jiffies_minmax_conv(bool *negp, unsigned long *lv * * Returns 0 on success. */ -int proc_dointvec_jiffies(struct ctl_table *table, int write, +int proc_dointvec_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_jiffies_conv,NULL); } -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct do_proc_dointvec_minmax_conv_param param = { @@ -1292,7 +1292,7 @@ int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, +int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_dointvec(table, write, buffer, lenp, ppos, @@ -1315,14 +1315,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void *buffer, +int proc_dointvec_ms_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_ms_jiffies_conv, NULL); } -static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer, +static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid *new_pid; @@ -1361,7 +1361,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer, * * Returns 0 on success. */ -int proc_do_large_bitmap(struct ctl_table *table, int write, +int proc_do_large_bitmap(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err = 0; @@ -1493,85 +1493,85 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, #else /* CONFIG_PROC_SYSCTL */ -int proc_dostring(struct ctl_table *table, int write, +int proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dobool(struct ctl_table *table, int write, +int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec(struct ctl_table *table, int write, +int proc_dointvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_douintvec(struct ctl_table *table, int write, +int proc_douintvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_minmax(struct ctl_table *table, int write, +int proc_dointvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_douintvec_minmax(struct ctl_table *table, int write, +int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dou8vec_minmax(struct ctl_table *table, int write, +int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_jiffies(struct ctl_table *table, int write, +int proc_dointvec_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, +int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, +int proc_dointvec_ms_jiffies(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_doulongvec_minmax(struct ctl_table *table, int write, +int proc_doulongvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_do_large_bitmap(struct ctl_table *table, int write, +int proc_do_large_bitmap(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; @@ -1580,7 +1580,7 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, #endif /* CONFIG_PROC_SYSCTL */ #if defined(CONFIG_SYSCTL) -int proc_do_static_key(struct ctl_table *table, int write, +int proc_do_static_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; diff --git a/kernel/task_work.c b/kernel/task_work.c index 5c2daa7ad3f9..5d14d639ac71 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -6,12 +6,14 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ +#ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); +#endif /** * task_work_add - ask the @task to execute @work->func() @@ -57,6 +59,8 @@ int task_work_add(struct task_struct *task, struct callback_head *work, if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; + if (!IS_ENABLED(CONFIG_IRQ_WORK)) + return -EINVAL; } else { /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); @@ -81,9 +85,11 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; +#ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; +#endif default: WARN_ON_ONCE(1); break; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 48288dd4a102..64b0d8a0aa0f 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -289,7 +289,7 @@ static void timers_update_migration(void) } #ifdef CONFIG_SYSCTL -static int timer_migration_handler(struct ctl_table *table, int write, +static int timer_migration_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 84413114db5c..8d57f7686bb0 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -475,9 +475,54 @@ static bool tmigr_check_lonely(struct tmigr_group *group) return bitmap_weight(&active, BIT_CNT) <= 1; } -typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *); +/** + * struct tmigr_walk - data required for walking the hierarchy + * @nextexp: Next CPU event expiry information which is handed into + * the timer migration code by the timer code + * (get_next_timer_interrupt()) + * @firstexp: Contains the first event expiry information when + * hierarchy is completely idle. When CPU itself was the + * last going idle, information makes sure, that CPU will + * be back in time. When using this value in the remote + * expiry case, firstexp is stored in the per CPU tmigr_cpu + * struct of CPU which expires remote timers. It is updated + * in top level group only. Be aware, there could occur a + * new top level of the hierarchy between the 'top level + * call' in tmigr_update_events() and the check for the + * parent group in walk_groups(). Then @firstexp might + * contain a value != KTIME_MAX even if it was not the + * final top level. This is not a problem, as the worst + * outcome is a CPU which might wake up a little early. + * @evt: Pointer to tmigr_event which needs to be queued (of idle + * child group) + * @childmask: groupmask of child group + * @remote: Is set, when the new timer path is executed in + * tmigr_handle_remote_cpu() + * @basej: timer base in jiffies + * @now: timer base monotonic + * @check: is set if there is the need to handle remote timers; + * required in tmigr_requires_handle_remote() only + * @tmc_active: this flag indicates, whether the CPU which triggers + * the hierarchy walk is !idle in the timer migration + * hierarchy. When the CPU is idle and the whole hierarchy is + * idle, only the first event of the top level has to be + * considered. + */ +struct tmigr_walk { + u64 nextexp; + u64 firstexp; + struct tmigr_event *evt; + u8 childmask; + bool remote; + unsigned long basej; + u64 now; + bool check; + bool tmc_active; +}; + +typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, struct tmigr_walk *); -static void __walk_groups(up_f up, void *data, +static void __walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc) { struct tmigr_group *child = NULL, *group = tmc->tmgroup; @@ -490,64 +535,17 @@ static void __walk_groups(up_f up, void *data, child = group; group = group->parent; + data->childmask = child->groupmask; } while (group); } -static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc) +static void walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc) { lockdep_assert_held(&tmc->lock); __walk_groups(up, data, tmc); } -/** - * struct tmigr_walk - data required for walking the hierarchy - * @nextexp: Next CPU event expiry information which is handed into - * the timer migration code by the timer code - * (get_next_timer_interrupt()) - * @firstexp: Contains the first event expiry information when last - * active CPU of hierarchy is on the way to idle to make - * sure CPU will be back in time. - * @evt: Pointer to tmigr_event which needs to be queued (of idle - * child group) - * @childmask: childmask of child group - * @remote: Is set, when the new timer path is executed in - * tmigr_handle_remote_cpu() - */ -struct tmigr_walk { - u64 nextexp; - u64 firstexp; - struct tmigr_event *evt; - u8 childmask; - bool remote; -}; - -/** - * struct tmigr_remote_data - data required for remote expiry hierarchy walk - * @basej: timer base in jiffies - * @now: timer base monotonic - * @firstexp: returns expiry of the first timer in the idle timer - * migration hierarchy to make sure the timer is handled in - * time; it is stored in the per CPU tmigr_cpu struct of - * CPU which expires remote timers - * @childmask: childmask of child group - * @check: is set if there is the need to handle remote timers; - * required in tmigr_requires_handle_remote() only - * @tmc_active: this flag indicates, whether the CPU which triggers - * the hierarchy walk is !idle in the timer migration - * hierarchy. When the CPU is idle and the whole hierarchy is - * idle, only the first event of the top level has to be - * considered. - */ -struct tmigr_remote_data { - unsigned long basej; - u64 now; - u64 firstexp; - u8 childmask; - bool check; - bool tmc_active; -}; - /* * Returns the next event of the timerqueue @group->events * @@ -618,10 +616,9 @@ static u64 tmigr_next_groupevt_expires(struct tmigr_group *group) static bool tmigr_active_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { union tmigr_state curstate, newstate; - struct tmigr_walk *data = ptr; bool walk_done; u8 childmask; @@ -649,8 +646,7 @@ static bool tmigr_active_up(struct tmigr_group *group, } while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)); - if ((walk_done == false) && group->parent) - data->childmask = group->childmask; + trace_tmigr_group_set_cpu_active(group, newstate, childmask); /* * The group is active (again). The group event might be still queued @@ -666,8 +662,6 @@ static bool tmigr_active_up(struct tmigr_group *group, */ group->groupevt.ignore = true; - trace_tmigr_group_set_cpu_active(group, newstate, childmask); - return walk_done; } @@ -675,7 +669,7 @@ static void __tmigr_cpu_activate(struct tmigr_cpu *tmc) { struct tmigr_walk data; - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; trace_tmigr_cpu_active(tmc); @@ -860,10 +854,8 @@ unlock: static bool tmigr_new_timer_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_walk *data = ptr; - return tmigr_update_events(group, child, data); } @@ -995,9 +987,8 @@ unlock: static bool tmigr_handle_remote_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_remote_data *data = ptr; struct tmigr_event *evt; unsigned long jif; u8 childmask; @@ -1034,12 +1025,10 @@ again: } /* - * Update of childmask for the next level and keep track of the expiry - * of the first event that needs to be handled (group->next_expiry was - * updated by tmigr_next_expired_groupevt(), next was set by - * tmigr_handle_remote_cpu()). + * Keep track of the expiry of the first event that needs to be handled + * (group->next_expiry was updated by tmigr_next_expired_groupevt(), + * next was set by tmigr_handle_remote_cpu()). */ - data->childmask = group->childmask; data->firstexp = group->next_expiry; raw_spin_unlock_irq(&group->lock); @@ -1055,12 +1044,12 @@ again: void tmigr_handle_remote(void) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - struct tmigr_remote_data data; + struct tmigr_walk data; if (tmigr_is_not_available(tmc)) return; - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; data.firstexp = KTIME_MAX; /* @@ -1068,7 +1057,7 @@ void tmigr_handle_remote(void) * in tmigr_handle_remote_up() anyway. Keep this check to speed up the * return when nothing has to be done. */ - if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) { + if (!tmigr_check_migrator(tmc->tmgroup, tmc->groupmask)) { /* * If this CPU was an idle migrator, make sure to clear its wakeup * value so it won't chase timers that have already expired elsewhere. @@ -1097,9 +1086,8 @@ void tmigr_handle_remote(void) static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_remote_data *data = ptr; u8 childmask; childmask = data->childmask; @@ -1118,7 +1106,7 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, * group before reading the next_expiry value. */ if (group->parent && !data->tmc_active) - goto out; + return false; /* * The lock is required on 32bit architectures to read the variable @@ -1143,9 +1131,6 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, raw_spin_unlock(&group->lock); } -out: - /* Update of childmask for the next level */ - data->childmask = group->childmask; return false; } @@ -1157,7 +1142,7 @@ out: bool tmigr_requires_handle_remote(void) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - struct tmigr_remote_data data; + struct tmigr_walk data; unsigned long jif; bool ret = false; @@ -1165,7 +1150,7 @@ bool tmigr_requires_handle_remote(void) return ret; data.now = get_jiffies_update(&jif); - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; data.firstexp = KTIME_MAX; data.tmc_active = !tmc->idle; data.check = false; @@ -1230,14 +1215,13 @@ u64 tmigr_cpu_new_timer(u64 nextexp) if (nextexp != tmc->cpuevt.nextevt.expires || tmc->cpuevt.ignore) { ret = tmigr_new_timer(tmc, nextexp); + /* + * Make sure the reevaluation of timers in idle path + * will not miss an event. + */ + WRITE_ONCE(tmc->wakeup, ret); } } - /* - * Make sure the reevaluation of timers in idle path will not miss an - * event. - */ - WRITE_ONCE(tmc->wakeup, ret); - trace_tmigr_cpu_new_timer_idle(tmc, nextexp); raw_spin_unlock(&tmc->lock); return ret; @@ -1245,10 +1229,9 @@ u64 tmigr_cpu_new_timer(u64 nextexp) static bool tmigr_inactive_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { union tmigr_state curstate, newstate, childstate; - struct tmigr_walk *data = ptr; bool walk_done; u8 childmask; @@ -1299,9 +1282,10 @@ static bool tmigr_inactive_up(struct tmigr_group *group, WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active)); - if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, - newstate.state)) + if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)) { + trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); break; + } /* * The memory barrier is paired with the cmpxchg() in @@ -1317,22 +1301,6 @@ static bool tmigr_inactive_up(struct tmigr_group *group, /* Event Handling */ tmigr_update_events(group, child, data); - if (group->parent && (walk_done == false)) - data->childmask = group->childmask; - - /* - * data->firstexp was set by tmigr_update_events() and contains the - * expiry of the first global event which needs to be handled. It - * differs from KTIME_MAX if: - * - group is the top level group and - * - group is idle (which means CPU was the last active CPU in the - * hierarchy) and - * - there is a pending event in the hierarchy - */ - WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent); - - trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); - return walk_done; } @@ -1341,7 +1309,7 @@ static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp) struct tmigr_walk data = { .nextexp = nextexp, .firstexp = KTIME_MAX, .evt = &tmc->cpuevt, - .childmask = tmc->childmask }; + .childmask = tmc->groupmask }; /* * If nextexp is KTIME_MAX, the CPU event will be ignored because the @@ -1400,7 +1368,7 @@ u64 tmigr_cpu_deactivate(u64 nextexp) * the only one in the level 0 group; and if it is the * only one in level 0 group, but there are more than a * single group active on the way to top level) - * * nextevt - when CPU is offline and has to handle timer on his own + * * nextevt - when CPU is offline and has to handle timer on its own * or when on the way to top in every group only a single * child is active but @nextevt is before the lowest * next_expiry encountered while walking up to top level. @@ -1419,7 +1387,7 @@ u64 tmigr_quick_check(u64 nextevt) if (WARN_ON_ONCE(tmc->idle)) return nextevt; - if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask)) + if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->groupmask)) return KTIME_MAX; do { @@ -1442,6 +1410,66 @@ u64 tmigr_quick_check(u64 nextevt) return KTIME_MAX; } +/* + * tmigr_trigger_active() - trigger a CPU to become active again + * + * This function is executed on a CPU which is part of cpu_online_mask, when the + * last active CPU in the hierarchy is offlining. With this, it is ensured that + * the other CPU is active and takes over the migrator duty. + */ +static long tmigr_trigger_active(void *unused) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + WARN_ON_ONCE(!tmc->online || tmc->idle); + + return 0; +} + +static int tmigr_cpu_offline(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int migrator; + u64 firstexp; + + raw_spin_lock_irq(&tmc->lock); + tmc->online = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* + * CPU has to handle the local events on his own, when on the way to + * offline; Therefore nextevt value is set to KTIME_MAX + */ + firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); + trace_tmigr_cpu_offline(tmc); + raw_spin_unlock_irq(&tmc->lock); + + if (firstexp != KTIME_MAX) { + migrator = cpumask_any_but(cpu_online_mask, cpu); + work_on_cpu(migrator, tmigr_trigger_active, NULL); + } + + return 0; +} + +static int tmigr_cpu_online(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + /* Check whether CPU data was successfully initialized */ + if (WARN_ON_ONCE(!tmc->tmgroup)) + return -EINVAL; + + raw_spin_lock_irq(&tmc->lock); + trace_tmigr_cpu_online(tmc); + tmc->idle = timer_base_is_idle(); + if (!tmc->idle) + __tmigr_cpu_activate(tmc); + tmc->online = true; + raw_spin_unlock_irq(&tmc->lock); + return 0; +} + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { @@ -1514,21 +1542,25 @@ static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node, } static void tmigr_connect_child_parent(struct tmigr_group *child, - struct tmigr_group *parent) + struct tmigr_group *parent, + bool activate) { - union tmigr_state childstate; + struct tmigr_walk data; raw_spin_lock_irq(&child->lock); raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); child->parent = parent; - child->childmask = BIT(parent->num_children++); + child->groupmask = BIT(parent->num_children++); raw_spin_unlock(&parent->lock); raw_spin_unlock_irq(&child->lock); trace_tmigr_connect_child_parent(child); + if (!activate) + return; + /* * To prevent inconsistent states, active children need to be active in * the new parent as well. Inactive children are already marked inactive @@ -1544,21 +1576,24 @@ static void tmigr_connect_child_parent(struct tmigr_group *child, * child to the new parent. So tmigr_connect_child_parent() is * executed with the formerly top level group (child) and the newly * created group (parent). + * + * * It is ensured that the child is active, as this setup path is + * executed in hotplug prepare callback. This is exectued by an + * already connected and !idle CPU. Even if all other CPUs go idle, + * the CPU executing the setup will be responsible up to current top + * level group. And the next time it goes inactive, it will release + * the new childmask and parent to subsequent walkers through this + * @child. Therefore propagate active state unconditionally. */ - childstate.state = atomic_read(&child->migr_state); - if (childstate.migrator != TMIGR_NONE) { - struct tmigr_walk data; - - data.childmask = child->childmask; + data.childmask = child->groupmask; - /* - * There is only one new level per time. When connecting the - * child and the parent and set the child active when the parent - * is inactive, the parent needs to be the uppermost - * level. Otherwise there went something wrong! - */ - WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); - } + /* + * There is only one new level per time (which is protected by + * tmigr_mutex). When connecting the child and the parent and set the + * child active when the parent is inactive, the parent needs to be the + * uppermost level. Otherwise there went something wrong! + */ + WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); } static int tmigr_setup_groups(unsigned int cpu, unsigned int node) @@ -1611,12 +1646,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) * Update tmc -> group / child -> group connection */ if (i == 0) { - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu); raw_spin_lock_irq(&group->lock); tmc->tmgroup = group; - tmc->childmask = BIT(group->num_children++); + tmc->groupmask = BIT(group->num_children++); raw_spin_unlock_irq(&group->lock); @@ -1626,7 +1661,8 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) continue; } else { child = stack[i - 1]; - tmigr_connect_child_parent(child, group); + /* Will be activated at online time */ + tmigr_connect_child_parent(child, group, false); } /* check if uppermost level was newly created */ @@ -1637,12 +1673,21 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) lvllist = &tmigr_level_list[top]; if (group->num_children == 1 && list_is_singular(lvllist)) { + /* + * The target CPU must never do the prepare work, except + * on early boot when the boot CPU is the target. Otherwise + * it may spuriously activate the old top level group inside + * the new one (nevertheless whether old top level group is + * active or not) and/or release an uninitialized childmask. + */ + WARN_ON_ONCE(cpu == raw_smp_processor_id()); + lvllist = &tmigr_level_list[top - 1]; list_for_each_entry(child, lvllist, list) { if (child->parent) continue; - tmigr_connect_child_parent(child, group); + tmigr_connect_child_parent(child, group, true); } } } @@ -1664,80 +1709,31 @@ static int tmigr_add_cpu(unsigned int cpu) return ret; } -static int tmigr_cpu_online(unsigned int cpu) -{ - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - int ret; - - /* First online attempt? Initialize CPU data */ - if (!tmc->tmgroup) { - raw_spin_lock_init(&tmc->lock); - - ret = tmigr_add_cpu(cpu); - if (ret < 0) - return ret; - - if (tmc->childmask == 0) - return -EINVAL; - - timerqueue_init(&tmc->cpuevt.nextevt); - tmc->cpuevt.nextevt.expires = KTIME_MAX; - tmc->cpuevt.ignore = true; - tmc->cpuevt.cpu = cpu; - - tmc->remote = false; - WRITE_ONCE(tmc->wakeup, KTIME_MAX); - } - raw_spin_lock_irq(&tmc->lock); - trace_tmigr_cpu_online(tmc); - tmc->idle = timer_base_is_idle(); - if (!tmc->idle) - __tmigr_cpu_activate(tmc); - tmc->online = true; - raw_spin_unlock_irq(&tmc->lock); - return 0; -} - -/* - * tmigr_trigger_active() - trigger a CPU to become active again - * - * This function is executed on a CPU which is part of cpu_online_mask, when the - * last active CPU in the hierarchy is offlining. With this, it is ensured that - * the other CPU is active and takes over the migrator duty. - */ -static long tmigr_trigger_active(void *unused) +static int tmigr_cpu_prepare(unsigned int cpu) { - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu); + int ret = 0; - WARN_ON_ONCE(!tmc->online || tmc->idle); - - return 0; -} - -static int tmigr_cpu_offline(unsigned int cpu) -{ - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - int migrator; - u64 firstexp; + /* Not first online attempt? */ + if (tmc->tmgroup) + return ret; - raw_spin_lock_irq(&tmc->lock); - tmc->online = false; + raw_spin_lock_init(&tmc->lock); + timerqueue_init(&tmc->cpuevt.nextevt); + tmc->cpuevt.nextevt.expires = KTIME_MAX; + tmc->cpuevt.ignore = true; + tmc->cpuevt.cpu = cpu; + tmc->remote = false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); - /* - * CPU has to handle the local events on his own, when on the way to - * offline; Therefore nextevt value is set to KTIME_MAX - */ - firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); - trace_tmigr_cpu_offline(tmc); - raw_spin_unlock_irq(&tmc->lock); + ret = tmigr_add_cpu(cpu); + if (ret < 0) + return ret; - if (firstexp != KTIME_MAX) { - migrator = cpumask_any_but(cpu_online_mask, cpu); - work_on_cpu(migrator, tmigr_trigger_active, NULL); - } + if (tmc->groupmask == 0) + return -EINVAL; - return 0; + return ret; } static int __init tmigr_init(void) @@ -1796,6 +1792,11 @@ static int __init tmigr_init(void) tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP, tmigr_crossnode_level); + ret = cpuhp_setup_state(CPUHP_TMIGR_PREPARE, "tmigr:prepare", + tmigr_cpu_prepare, NULL); + if (ret) + goto err; + ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", tmigr_cpu_online, tmigr_cpu_offline); if (ret) @@ -1807,4 +1808,4 @@ err: pr_err("Timer migration setup failed\n"); return ret; } -late_initcall(tmigr_init); +early_initcall(tmigr_init); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 6c37d94a37d9..154accc7a543 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -22,7 +22,17 @@ struct tmigr_event { * struct tmigr_group - timer migration hierarchy group * @lock: Lock protecting the event information and group hierarchy * information during setup - * @parent: Pointer to the parent group + * @parent: Pointer to the parent group. Pointer is updated when a + * new hierarchy level is added because of a CPU coming + * online the first time. Once it is set, the pointer will + * not be removed or updated. When accessing parent pointer + * lock less to decide whether to abort a propagation or + * not, it is not a problem. The worst outcome is an + * unnecessary/early CPU wake up. But do not access parent + * pointer several times in the same 'action' (like + * activation, deactivation, check for remote expiry,...) + * without holding the lock as it is not ensured that value + * will not change. * @groupevt: Next event of the group which is only used when the * group is !active. The group event is then queued into * the parent timer queue. @@ -41,9 +51,8 @@ struct tmigr_event { * @num_children: Counter of group children to make sure the group is only * filled with TMIGR_CHILDREN_PER_GROUP; Required for setup * only - * @childmask: childmask of the group in the parent group; is set - * during setup and will never change; can be read - * lockless + * @groupmask: mask of the group in the parent group; is set during + * setup and will never change; can be read lockless * @list: List head that is added to the per level * tmigr_level_list; is required during setup when a * new group needs to be connected to the existing @@ -59,7 +68,7 @@ struct tmigr_group { unsigned int level; int numa_node; unsigned int num_children; - u8 childmask; + u8 groupmask; struct list_head list; }; @@ -79,7 +88,7 @@ struct tmigr_group { * hierarchy * @remote: Is set when timers of the CPU are expired remotely * @tmgroup: Pointer to the parent group - * @childmask: childmask of tmigr_cpu in the parent group + * @groupmask: mask of tmigr_cpu in the parent group * @wakeup: Stores the first timer when the timer migration * hierarchy is completely idle and remote expiry was done; * is returned to timer code in the idle path and is only @@ -92,7 +101,7 @@ struct tmigr_cpu { bool idle; bool remote; struct tmigr_group *tmgroup; - u8 childmask; + u8 groupmask; u64 wakeup; struct tmigr_event cpuevt; }; @@ -108,8 +117,8 @@ union tmigr_state { u32 state; /** * struct - split state of tmigr_group - * @active: Contains each childmask bit of the active children - * @migrator: Contains childmask of the child which is migrator + * @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 diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e5d6a4ab433b..4c28dd177ca6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7920,6 +7920,7 @@ out: void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { + kmsan_unpoison_memory(fregs, sizeof(*fregs)); __ftrace_ops_list_func(ip, parent_ip, NULL, fregs); } #else @@ -8734,7 +8735,7 @@ static bool is_permanent_ops_registered(void) } static int -ftrace_enable_sysctl(struct ctl_table *table, int write, +ftrace_enable_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = -ENODEV; diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index cb0871fbdb07..314ffc143039 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on"); static struct completion done; -#define MIN(x, y) ((x) < (y) ? (x) : (y)) - static void busy_wait(ulong time) { u64 start, end; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 578a49ff5c32..10cd38bce2f1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2767,7 +2767,7 @@ static void output_printk(struct trace_event_buffer *fbuffer) raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } -int tracepoint_printk_sysctl(struct ctl_table *table, int write, +int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 3a2b46847c8b..42b0d998d103 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2885,7 +2885,7 @@ err: return -ENODEV; } -static int set_max_user_events_sysctl(struct ctl_table *table, int write, +static int set_max_user_events_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 5a48dba912ea..7f9572a37333 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -514,7 +514,7 @@ static const struct file_operations stack_trace_filter_fops = { #endif /* CONFIG_DYNAMIC_FTRACE */ int -stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, +stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int was_enabled; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 4252f0645b9e..16b283f9d831 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -76,7 +76,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; - strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm)); + strscpy_pad(stats->ac_comm, tsk->comm); } diff --git a/kernel/umh.c b/kernel/umh.c index 598b3ffe1522..ff1f13a27d29 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -495,7 +495,7 @@ int call_usermodehelper(const char *path, char **argv, char **envp, int wait) EXPORT_SYMBOL(call_usermodehelper); #if defined(CONFIG_SYSCTL) -static int proc_cap_handler(struct ctl_table *table, int write, +static int proc_cap_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 04e4513f2985..7282f61a8650 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -30,7 +30,7 @@ static void *get_uts(const struct ctl_table *table) * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? */ -static int proc_do_uts_string(struct ctl_table *table, int write, +static int proc_do_uts_string(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table uts_table; diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index 1d5eadd9dd61..8b4f8cc2e0ec 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -216,12 +216,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(kallsyms_num_syms); VMCOREINFO_SYMBOL(kallsyms_token_table); VMCOREINFO_SYMBOL(kallsyms_token_index); -#ifdef CONFIG_KALLSYMS_BASE_RELATIVE VMCOREINFO_SYMBOL(kallsyms_offsets); VMCOREINFO_SYMBOL(kallsyms_relative_base); -#else - VMCOREINFO_SYMBOL(kallsyms_addresses); -#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ #endif /* CONFIG_KALLSYMS */ arch_crash_save_vmcoreinfo(); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 51915b44ac73..830a83895493 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -983,7 +983,7 @@ static void proc_watchdog_update(void) * -------------------|----------------------------------|------------------------------- * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED */ -static int proc_watchdog_common(int which, struct ctl_table *table, int write, +static int proc_watchdog_common(int which, const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old, *param = table->data; @@ -1010,7 +1010,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, /* * /proc/sys/kernel/watchdog */ -static int proc_watchdog(struct ctl_table *table, int write, +static int proc_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED | @@ -1021,7 +1021,7 @@ static int proc_watchdog(struct ctl_table *table, int write, /* * /proc/sys/kernel/nmi_watchdog */ -static int proc_nmi_watchdog(struct ctl_table *table, int write, +static int proc_nmi_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!watchdog_hardlockup_available && write) @@ -1034,7 +1034,7 @@ static int proc_nmi_watchdog(struct ctl_table *table, int write, /* * /proc/sys/kernel/soft_watchdog */ -static int proc_soft_watchdog(struct ctl_table *table, int write, +static int proc_soft_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED, @@ -1045,7 +1045,7 @@ static int proc_soft_watchdog(struct ctl_table *table, int write, /* * /proc/sys/kernel/watchdog_thresh */ -static int proc_watchdog_thresh(struct ctl_table *table, int write, +static int proc_watchdog_thresh(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old; @@ -1068,7 +1068,7 @@ static int proc_watchdog_thresh(struct ctl_table *table, int write, * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ -static int proc_watchdog_cpumask(struct ctl_table *table, int write, +static int proc_watchdog_cpumask(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c index d577c4a8321e..59c1d86a73a2 100644 --- a/kernel/watchdog_perf.c +++ b/kernel/watchdog_perf.c @@ -75,11 +75,15 @@ static bool watchdog_check_timestamp(void) __this_cpu_write(last_timestamp, now); return true; } -#else -static inline bool watchdog_check_timestamp(void) + +static void watchdog_init_timestamp(void) { - return true; + __this_cpu_write(nmi_rearmed, 0); + __this_cpu_write(last_timestamp, ktime_get_mono_fast_ns()); } +#else +static inline bool watchdog_check_timestamp(void) { return true; } +static inline void watchdog_init_timestamp(void) { } #endif static struct perf_event_attr wd_hw_attr = { @@ -161,6 +165,7 @@ void watchdog_hardlockup_enable(unsigned int cpu) if (!atomic_fetch_inc(&watchdog_cpus)) pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); + watchdog_init_timestamp(); perf_event_enable(this_cpu_read(watchdog_ev)); } |