diff options
Diffstat (limited to 'kernel')
155 files changed, 6127 insertions, 3268 deletions
diff --git a/kernel/.gitignore b/kernel/.gitignore index 6e699100872f..34d1e77ee9df 100644 --- a/kernel/.gitignore +++ b/kernel/.gitignore @@ -1,5 +1,6 @@ # # Generated files # +kheaders.md5 timeconst.h hz.bc diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index fbba478ae522..bf770d7556f7 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -229,7 +229,7 @@ config MUTEX_SPIN_ON_OWNER config RWSEM_SPIN_ON_OWNER def_bool y - depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW + depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW config LOCK_SPIN_ON_OWNER def_bool y @@ -251,3 +251,10 @@ config ARCH_USE_QUEUED_RWLOCKS config QUEUED_RWLOCKS def_bool y if ARCH_USE_QUEUED_RWLOCKS depends on SMP + +config ARCH_HAS_MMIOWB + bool + +config MMIOWB + def_bool y if ARCH_HAS_MMIOWB + depends on SMP diff --git a/kernel/Makefile b/kernel/Makefile index 6c57e78817da..298437bb2c6a 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -30,6 +30,7 @@ KCOV_INSTRUMENT_extable.o := n # Don't self-instrument. KCOV_INSTRUMENT_kcov.o := n KASAN_SANITIZE_kcov.o := n +CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) # cond_syscall is currently not LTO compatible CFLAGS_sys_ni.o = $(DISABLE_LTO) @@ -70,6 +71,7 @@ obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_USER_NS) += user_namespace.o obj-$(CONFIG_PID_NS) += pid_namespace.o obj-$(CONFIG_IKCONFIG) += configs.o +obj-$(CONFIG_IKHEADERS_PROC) += kheaders.o obj-$(CONFIG_SMP) += stop_machine.o obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o obj-$(CONFIG_AUDIT) += audit.o auditfilter.o @@ -121,3 +123,12 @@ $(obj)/configs.o: $(obj)/config_data.gz targets += config_data.gz $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(call if_changed,gzip) + +$(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz + +quiet_cmd_genikh = CHK $(obj)/kheaders_data.tar.xz +cmd_genikh = $(srctree)/kernel/gen_ikh_data.sh $@ +$(obj)/kheaders_data.tar.xz: FORCE + $(call cmd,genikh) + +clean-files := kheaders_data.tar.xz kheaders.md5 diff --git a/kernel/acct.c b/kernel/acct.c index addf7732fb56..81f9831a7859 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -227,7 +227,7 @@ static int acct_on(struct filename *pathname) filp_close(file, NULL); return PTR_ERR(internal); } - err = mnt_want_write(internal); + err = __mnt_want_write(internal); if (err) { mntput(internal); kfree(acct); @@ -252,7 +252,7 @@ static int acct_on(struct filename *pathname) old = xchg(&ns->bacct, &acct->pin); mutex_unlock(&acct->lock); pin_kill(old); - mnt_drop_write(mnt); + __mnt_drop_write(mnt); mntput(mnt); return 0; } diff --git a/kernel/async.c b/kernel/async.c index f6bd0d9885e1..12c332e4e13e 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -119,7 +119,7 @@ static void async_run_entry_fn(struct work_struct *work) /* 1) run (and print duration) */ if (initcall_debug && system_state < SYSTEM_RUNNING) { - pr_debug("calling %lli_%pF @ %i\n", + pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); @@ -128,7 +128,7 @@ static void async_run_entry_fn(struct work_struct *work) if (initcall_debug && system_state < SYSTEM_RUNNING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n", + pr_debug("initcall %lli_%pS returned 0 after %lld usecs\n", (long long)entry->cookie, entry->func, (long long)ktime_to_ns(delta) >> 10); diff --git a/kernel/audit.c b/kernel/audit.c index c89ea48c70a6..b96bf69183f4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2220,7 +2220,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, if (!audit_enabled) return; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; diff --git a/kernel/audit.h b/kernel/audit.h index 958d5b8fc1b3..2071725a999f 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -231,7 +231,7 @@ extern int audit_comparator(const u32 left, const u32 op, const u32 right); extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); extern int parent_len(const char *path); -extern int audit_compare_dname_path(const char *dname, const char *path, int plen); +extern int audit_compare_dname_path(const struct qstr *dname, const char *path, int plen); extern struct sk_buff *audit_make_reply(int seq, int type, int done, int multi, const void *payload, int size); extern void audit_panic(const char *message); diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 37ae95cfb7f4..b5737b826951 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -164,7 +164,7 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark) static int audit_mark_handle_event(struct fsnotify_group *group, struct inode *to_tell, u32 mask, const void *data, int data_type, - const unsigned char *dname, u32 cookie, + const struct qstr *dname, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index abfb112f26aa..e49c912f862d 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -1040,7 +1040,7 @@ static void evict_chunk(struct audit_chunk *chunk) static int audit_tree_handle_event(struct fsnotify_group *group, struct inode *to_tell, u32 mask, const void *data, int data_type, - const unsigned char *file_name, u32 cookie, + const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { return 0; diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index e8d1adeb2223..b50c574223fa 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -255,7 +255,7 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc /* Update inode info in audit rules based on filesystem event. */ static void audit_update_watch(struct audit_parent *parent, - const char *dname, dev_t dev, + const struct qstr *dname, dev_t dev, unsigned long ino, unsigned invalidating) { struct audit_watch *owatch, *nwatch, *nextw; @@ -482,7 +482,7 @@ void audit_remove_watch_rule(struct audit_krule *krule) static int audit_watch_handle_event(struct fsnotify_group *group, struct inode *to_tell, u32 mask, const void *data, int data_type, - const unsigned char *dname, u32 cookie, + const struct qstr *dname, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 63f8b3f26fab..303fb04770ce 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1114,22 +1114,24 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz) int err = 0; struct audit_entry *entry; - entry = audit_data_to_entry(data, datasz); - if (IS_ERR(entry)) - return PTR_ERR(entry); - switch (type) { case AUDIT_ADD_RULE: + entry = audit_data_to_entry(data, datasz); + if (IS_ERR(entry)) + return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: + entry = audit_data_to_entry(data, datasz); + if (IS_ERR(entry)) + return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: - err = -EINVAL; WARN_ON(1); + return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { @@ -1290,12 +1292,12 @@ int parent_len(const char *path) * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ -int audit_compare_dname_path(const char *dname, const char *path, int parentlen) +int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; - dlen = strlen(dname); + dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; @@ -1306,7 +1308,7 @@ int audit_compare_dname_path(const char *dname, const char *path, int parentlen) p = path + parentlen; - return strncmp(p, dname, dlen); + return strncmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) @@ -1315,8 +1317,6 @@ int audit_filter(int msgtype, unsigned int listtype) int ret = 1; /* Audit by default */ rcu_read_lock(); - if (list_empty(&audit_filter_list[listtype])) - goto unlock_and_return; list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d1eab1d4a930..95ae27edd417 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -771,15 +771,13 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, return AUDIT_DISABLED; rcu_read_lock(); - if (!list_empty(list)) { - list_for_each_entry_rcu(e, list, list) { - if (audit_in_mask(&e->rule, ctx->major) && - audit_filter_rules(tsk, &e->rule, ctx, NULL, - &state, false)) { - rcu_read_unlock(); - ctx->current_state = state; - return state; - } + list_for_each_entry_rcu(e, list, list) { + if (audit_in_mask(&e->rule, ctx->major) && + audit_filter_rules(tsk, &e->rule, ctx, NULL, + &state, false)) { + rcu_read_unlock(); + ctx->current_state = state; + return state; } } rcu_read_unlock(); @@ -798,9 +796,6 @@ static int audit_filter_inode_name(struct task_struct *tsk, struct audit_entry *e; enum audit_state state; - if (list_empty(list)) - return 0; - list_for_each_entry_rcu(e, list, list) { if (audit_in_mask(&e->rule, ctx->major) && audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) { @@ -808,7 +803,6 @@ static int audit_filter_inode_name(struct task_struct *tsk, return 1; } } - return 0; } @@ -840,6 +834,13 @@ static inline void audit_proctitle_free(struct audit_context *context) context->proctitle.len = 0; } +static inline void audit_free_module(struct audit_context *context) +{ + if (context->type == AUDIT_KERN_MODULE) { + kfree(context->module.name); + context->module.name = NULL; + } +} static inline void audit_free_names(struct audit_context *context) { struct audit_names *n, *next; @@ -923,6 +924,7 @@ int audit_alloc(struct task_struct *tsk) static inline void audit_free_context(struct audit_context *context) { + audit_free_module(context); audit_free_names(context); unroll_tree_refs(context, NULL, 0); free_tree_refs(context); @@ -1139,7 +1141,8 @@ out: kfree(buf_head); } -void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) +static void audit_log_cap(struct audit_buffer *ab, char *prefix, + kernel_cap_t *cap) { int i; @@ -1266,7 +1269,6 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "name="); if (context->module.name) { audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); } else audit_log_format(ab, "(null)"); @@ -1628,7 +1630,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, return; } - context->arch = syscall_get_arch(); + context->arch = syscall_get_arch(current); context->major = major; context->argv[0] = a1; context->argv[1] = a2; @@ -1697,6 +1699,7 @@ void __audit_syscall_exit(int success, long return_code) context->in_syscall = 0; context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + audit_free_module(context); audit_free_names(context); unroll_tree_refs(context, NULL, 0); audit_free_aux(context); @@ -1897,8 +1900,9 @@ static inline int audit_copy_fcaps(struct audit_names *name, } /* Copy inode data into an audit_names. */ -void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - struct inode *inode, unsigned int flags) +static void audit_copy_inode(struct audit_names *name, + const struct dentry *dentry, + struct inode *inode, unsigned int flags) { name->ino = inode->i_ino; name->dev = inode->i_sb->s_dev; @@ -1935,18 +1939,16 @@ void __audit_inode(struct filename *name, const struct dentry *dentry, return; rcu_read_lock(); - if (!list_empty(list)) { - list_for_each_entry_rcu(e, list, list) { - for (i = 0; i < e->rule.field_count; i++) { - struct audit_field *f = &e->rule.fields[i]; - - if (f->type == AUDIT_FSTYPE - && audit_comparator(inode->i_sb->s_magic, - f->op, f->val) - && e->rule.action == AUDIT_NEVER) { - rcu_read_unlock(); - return; - } + list_for_each_entry_rcu(e, list, list) { + for (i = 0; i < e->rule.field_count; i++) { + struct audit_field *f = &e->rule.fields[i]; + + if (f->type == AUDIT_FSTYPE + && audit_comparator(inode->i_sb->s_magic, + f->op, f->val) + && e->rule.action == AUDIT_NEVER) { + rcu_read_unlock(); + return; } } } @@ -2045,7 +2047,7 @@ void __audit_inode_child(struct inode *parent, { struct audit_context *context = audit_context(); struct inode *inode = d_backing_inode(dentry); - const char *dname = dentry->d_name.name; + const struct qstr *dname = &dentry->d_name; struct audit_names *n, *found_parent = NULL, *found_child = NULL; struct audit_entry *e; struct list_head *list = &audit_filter_list[AUDIT_FILTER_FS]; @@ -2055,18 +2057,16 @@ void __audit_inode_child(struct inode *parent, return; rcu_read_lock(); - if (!list_empty(list)) { - list_for_each_entry_rcu(e, list, list) { - for (i = 0; i < e->rule.field_count; i++) { - struct audit_field *f = &e->rule.fields[i]; - - if (f->type == AUDIT_FSTYPE - && audit_comparator(parent->i_sb->s_magic, - f->op, f->val) - && e->rule.action == AUDIT_NEVER) { - rcu_read_unlock(); - return; - } + list_for_each_entry_rcu(e, list, list) { + for (i = 0; i < e->rule.field_count; i++) { + struct audit_field *f = &e->rule.fields[i]; + + if (f->type == AUDIT_FSTYPE + && audit_comparator(parent->i_sb->s_magic, + f->op, f->val) + && e->rule.action == AUDIT_NEVER) { + rcu_read_unlock(); + return; } } } @@ -2099,7 +2099,7 @@ void __audit_inode_child(struct inode *parent, (n->type != type && n->type != AUDIT_TYPE_UNKNOWN)) continue; - if (!strcmp(dname, n->name->name) || + if (!strcmp(dname->name, n->name->name) || !audit_compare_dname_path(dname, n->name->name, found_parent ? found_parent->name_len : @@ -2512,6 +2512,35 @@ void __audit_fanotify(unsigned int response) AUDIT_FANOTIFY, "resp=%u", response); } +void __audit_tk_injoffset(struct timespec64 offset) +{ + audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_INJOFFSET, + "sec=%lli nsec=%li", + (long long)offset.tv_sec, offset.tv_nsec); +} + +static void audit_log_ntp_val(const struct audit_ntp_data *ad, + const char *op, enum audit_ntp_type type) +{ + const struct audit_ntp_val *val = &ad->vals[type]; + + if (val->newval == val->oldval) + return; + + audit_log(audit_context(), GFP_KERNEL, AUDIT_TIME_ADJNTPVAL, + "op=%s old=%lli new=%lli", op, val->oldval, val->newval); +} + +void __audit_ntp_log(const struct audit_ntp_data *ad) +{ + audit_log_ntp_val(ad, "offset", AUDIT_NTP_OFFSET); + audit_log_ntp_val(ad, "freq", AUDIT_NTP_FREQ); + audit_log_ntp_val(ad, "status", AUDIT_NTP_STATUS); + audit_log_ntp_val(ad, "tai", AUDIT_NTP_TAI); + audit_log_ntp_val(ad, "tick", AUDIT_NTP_TICK); + audit_log_ntp_val(ad, "adjust", AUDIT_NTP_ADJUST); +} + static void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; @@ -2580,7 +2609,7 @@ void audit_seccomp(unsigned long syscall, long signr, int code) return; audit_log_task(ab); audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x", - signr, syscall_get_arch(), syscall, + signr, syscall_get_arch(current), syscall, in_compat_syscall(), KSTK_EIP(current), code); audit_log_end(ab); } diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index 1323360d90e3..a563c8fdad0d 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -48,19 +48,14 @@ static void backtrace_test_irq(void) #ifdef CONFIG_STACKTRACE static void backtrace_test_saved(void) { - struct stack_trace trace; unsigned long entries[8]; + unsigned int nr_entries; pr_info("Testing a saved backtrace.\n"); pr_info("The following trace is a kernel self test and not a bug!\n"); - trace.nr_entries = 0; - trace.max_entries = ARRAY_SIZE(entries); - trace.entries = entries; - trace.skip = 0; - - save_stack_trace(&trace); - print_stack_trace(&trace, 0); + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); + stack_trace_print(entries, nr_entries, 0); } #else static void backtrace_test_saved(void) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c72e0d8e1e65..584636c9e2eb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -22,7 +22,7 @@ #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr) if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size == 0 || attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; @@ -160,6 +161,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + array->elem_size * (index & array->index_mask); } +static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, + u32 off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + + if (map->max_entries != 1) + return -ENOTSUPP; + if (off >= map->value_size) + return -EINVAL; + + *imm = (unsigned long)array->value; + return 0; +} + +static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, + u32 *off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u64 base = (unsigned long)array->value; + u64 range = array->elem_size; + + if (map->max_entries != 1) + return -ENOTSUPP; + if (imm < base || imm >= base + range) + return -ENOENT; + + *off = imm - base; + return 0; +} + /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { @@ -360,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, return; } - seq_printf(m, "%u: ", *(u32 *)key); + if (map->btf_key_type_id) + seq_printf(m, "%u: ", *(u32 *)key); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_puts(m, "\n"); @@ -397,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map, { u32 int_data; + /* One exception for keyless BTF: .bss/.data/.rodata map */ + if (btf_type_is_void(key_type)) { + if (map->map_type != BPF_MAP_TYPE_ARRAY || + map->max_entries != 1) + return -EINVAL; + + if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC) + return -EINVAL; + + return 0; + } + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; @@ -419,6 +463,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_direct_value_addr = array_map_direct_value_addr, + .map_direct_value_meta = array_map_direct_value_meta, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; @@ -440,6 +486,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr) /* only file descriptors can be stored in this type of map */ if (attr->value_size != sizeof(u32)) return -EINVAL; + /* Program read-only/write-only not supported for special maps yet. */ + if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) + return -EINVAL; return array_map_alloc_check(attr); } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index bd3921b1514b..cad09858a5f2 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -185,6 +185,16 @@ i < btf_type_vlen(struct_type); \ i++, member++) +#define for_each_vsi(i, struct_type, member) \ + for (i = 0, member = btf_type_var_secinfo(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +#define for_each_vsi_from(i, from, struct_type, member) \ + for (i = from, member = btf_type_var_secinfo(struct_type) + from; \ + i < btf_type_vlen(struct_type); \ + i++, member++) + static DEFINE_IDR(btf_idr); static DEFINE_SPINLOCK(btf_idr_lock); @@ -262,6 +272,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_RESTRICT] = "RESTRICT", [BTF_KIND_FUNC] = "FUNC", [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", }; struct btf_kind_operations { @@ -314,7 +326,7 @@ static bool btf_type_is_modifier(const struct btf_type *t) return false; } -static bool btf_type_is_void(const struct btf_type *t) +bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void; } @@ -375,13 +387,36 @@ static bool btf_type_is_int(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } +static bool btf_type_is_var(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; +} + +static bool btf_type_is_datasec(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; +} + +/* Types that act only as a source, not sink or intermediate + * type when resolving. + */ +static bool btf_type_is_resolve_source_only(const struct btf_type *t) +{ + return btf_type_is_var(t) || + btf_type_is_datasec(t); +} + /* What types need to be resolved? * * btf_type_is_modifier() is an obvious one. * * btf_type_is_struct() because its member refers to * another type (through member->type). - + * + * btf_type_is_var() because the variable refers to + * another type. btf_type_is_datasec() holds multiple + * btf_type_is_var() types that need resolving. + * * btf_type_is_array() because its element (array->type) * refers to another type. Array can be thought of a * special case of struct while array just has the same @@ -390,9 +425,11 @@ static bool btf_type_is_int(const struct btf_type *t) static bool btf_type_needs_resolve(const struct btf_type *t) { return btf_type_is_modifier(t) || - btf_type_is_ptr(t) || - btf_type_is_struct(t) || - btf_type_is_array(t); + btf_type_is_ptr(t) || + btf_type_is_struct(t) || + btf_type_is_array(t) || + btf_type_is_var(t) || + btf_type_is_datasec(t); } /* t->size can be used */ @@ -403,6 +440,7 @@ static bool btf_type_has_size(const struct btf_type *t) case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_DATASEC: return true; } @@ -467,6 +505,16 @@ static const struct btf_enum *btf_type_enum(const struct btf_type *t) return (const struct btf_enum *)(t + 1); } +static const struct btf_var *btf_type_var(const struct btf_type *t) +{ + return (const struct btf_var *)(t + 1); +} + +static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t) +{ + return (const struct btf_var_secinfo *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -478,23 +526,31 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) offset < btf->hdr.str_len; } -/* Only C-style identifier is permitted. This can be relaxed if - * necessary. - */ -static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) +static bool __btf_name_char_ok(char c, bool first, bool dot_ok) +{ + if ((first ? !isalpha(c) : + !isalnum(c)) && + c != '_' && + ((c == '.' && !dot_ok) || + c != '.')) + return false; + return true; +} + +static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) { /* offset must be valid */ const char *src = &btf->strings[offset]; const char *src_limit; - if (!isalpha(*src) && *src != '_') + if (!__btf_name_char_ok(*src, true, dot_ok)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { - if (!isalnum(*src) && *src != '_') + if (!__btf_name_char_ok(*src, false, dot_ok)) return false; src++; } @@ -502,6 +558,19 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) return !*src; } +/* Only C-style identifier is permitted. This can be relaxed if + * necessary. + */ +static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) +{ + return __btf_name_valid(btf, offset, false); +} + +static bool btf_name_valid_section(const struct btf *btf, u32 offset) +{ + return __btf_name_valid(btf, offset, true); +} + static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) { if (!offset) @@ -697,6 +766,32 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, __btf_verifier_log(log, "\n"); } +__printf(4, 5) +static void btf_verifier_log_vsi(struct btf_verifier_env *env, + const struct btf_type *datasec_type, + const struct btf_var_secinfo *vsi, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + if (env->phase != CHECK_META) + btf_verifier_log_type(env, datasec_type, NULL); + + __btf_verifier_log(log, "\t type_id=%u offset=%u size=%u", + vsi->type, vsi->offset, vsi->size); + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + static void btf_verifier_log_hdr(struct btf_verifier_env *env, u32 btf_data_size) { @@ -974,7 +1069,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, } else if (btf_type_is_ptr(size_type)) { size = sizeof(void *); } else { - if (WARN_ON_ONCE(!btf_type_is_modifier(size_type))) + if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) && + !btf_type_is_var(size_type))) return NULL; size = btf->resolved_sizes[size_type_id]; @@ -1509,7 +1605,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); - if (!next_type) { + if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -1542,6 +1638,53 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, return 0; } +static int btf_var_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || btf_type_is_resolve_source_only(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + if (btf_type_is_modifier(next_type)) { + const struct btf_type *resolved_type; + u32 resolved_type_id; + + resolved_type_id = next_type_id; + resolved_type = btf_type_id_resolve(btf, &resolved_type_id); + + if (btf_type_is_ptr(resolved_type) && + !env_type_is_resolve_sink(env, resolved_type) && + !env_type_is_resolved(env, resolved_type_id)) + return env_stack_push(env, resolved_type, + resolved_type_id); + } + + /* We must resolve to something concrete at this point, no + * forward types or similar that would resolve to size of + * zero is allowed. + */ + if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + env_stack_pop_resolved(env, next_type_id, next_type_size); + + return 0; +} + static int btf_ptr_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { @@ -1551,7 +1694,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); - if (!next_type) { + if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -1609,6 +1752,15 @@ static void btf_modifier_seq_show(const struct btf *btf, btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); } +static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + t = btf_type_id_resolve(btf, &type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); +} + static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) @@ -1776,7 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->index_type */ index_type_id = array->index_type; index_type = btf_type_by_id(btf, index_type_id); - if (btf_type_nosize_or_null(index_type)) { + if (btf_type_is_resolve_source_only(index_type) || + btf_type_nosize_or_null(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } @@ -1795,7 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->type */ elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); - if (btf_type_nosize_or_null(elem_type)) { + if (btf_type_is_resolve_source_only(elem_type) || + btf_type_nosize_or_null(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; @@ -2016,7 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env, const struct btf_type *member_type = btf_type_by_id(env->btf, member_type_id); - if (btf_type_nosize_or_null(member_type)) { + if (btf_type_is_resolve_source_only(member_type) || + btf_type_nosize_or_null(member_type)) { btf_verifier_log_member(env, v->t, member, "Invalid member"); return -EINVAL; @@ -2411,6 +2566,222 @@ static struct btf_kind_operations func_ops = { .seq_show = btf_df_seq_show, }; +static s32 btf_var_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_var *var; + u32 meta_needed = sizeof(*var); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + if (!t->name_off || + !__btf_name_valid(env->btf, t->name_off, true)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + /* A var cannot be in type void */ + if (!t->type || !BTF_TYPE_ID_VALID(t->type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + var = btf_type_var(t); + if (var->linkage != BTF_VAR_STATIC && + var->linkage != BTF_VAR_GLOBAL_ALLOCATED) { + btf_verifier_log_type(env, t, "Linkage not supported"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + const struct btf_var *var = btf_type_var(t); + + btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage); +} + +static const struct btf_kind_operations var_ops = { + .check_meta = btf_var_check_meta, + .resolve = btf_var_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_var_log, + .seq_show = btf_var_seq_show, +}; + +static s32 btf_datasec_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_var_secinfo *vsi; + u64 last_vsi_end_off = 0, sum = 0; + u32 i, meta_needed; + + meta_needed = btf_type_vlen(t) * sizeof(*vsi); + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (!btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen == 0"); + return -EINVAL; + } + + if (!t->size) { + btf_verifier_log_type(env, t, "size == 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + if (!t->name_off || + !btf_name_valid_section(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for_each_vsi(i, t, vsi) { + /* A var cannot be in type void */ + if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) { + btf_verifier_log_vsi(env, t, vsi, + "Invalid type_id"); + return -EINVAL; + } + + if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) { + btf_verifier_log_vsi(env, t, vsi, + "Invalid offset"); + return -EINVAL; + } + + if (!vsi->size || vsi->size > t->size) { + btf_verifier_log_vsi(env, t, vsi, + "Invalid size"); + return -EINVAL; + } + + last_vsi_end_off = vsi->offset + vsi->size; + if (last_vsi_end_off > t->size) { + btf_verifier_log_vsi(env, t, vsi, + "Invalid offset+size"); + return -EINVAL; + } + + btf_verifier_log_vsi(env, t, vsi, NULL); + sum += vsi->size; + } + + if (t->size < sum) { + btf_verifier_log_type(env, t, "Invalid btf_info size"); + return -EINVAL; + } + + return meta_needed; +} + +static int btf_datasec_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_var_secinfo *vsi; + struct btf *btf = env->btf; + u16 i; + + for_each_vsi_from(i, v->next_member, v->t, vsi) { + u32 var_type_id = vsi->type, type_id, type_size = 0; + const struct btf_type *var_type = btf_type_by_id(env->btf, + var_type_id); + if (!var_type || !btf_type_is_var(var_type)) { + btf_verifier_log_vsi(env, v->t, vsi, + "Not a VAR kind member"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, var_type) && + !env_type_is_resolved(env, var_type_id)) { + env_stack_set_next_member(env, i + 1); + return env_stack_push(env, var_type, var_type_id); + } + + type_id = var_type->type; + if (!btf_type_id_size(btf, &type_id, &type_size)) { + btf_verifier_log_vsi(env, v->t, vsi, "Invalid type"); + return -EINVAL; + } + + if (vsi->size < type_size) { + btf_verifier_log_vsi(env, v->t, vsi, "Invalid size"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, 0, 0); + return 0; +} + +static void btf_datasec_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_datasec_seq_show(const struct btf *btf, + const struct btf_type *t, u32 type_id, + void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_var_secinfo *vsi; + const struct btf_type *var; + u32 i; + + seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off)); + for_each_vsi(i, t, vsi) { + var = btf_type_by_id(btf, vsi->type); + if (i) + seq_puts(m, ","); + btf_type_ops(var)->seq_show(btf, var, vsi->type, + data + vsi->offset, bits_offset, m); + } + seq_puts(m, "}"); +} + +static const struct btf_kind_operations datasec_ops = { + .check_meta = btf_datasec_check_meta, + .resolve = btf_datasec_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_datasec_log, + .seq_show = btf_datasec_seq_show, +}; + static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { @@ -2542,6 +2913,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_RESTRICT] = &modifier_ops, [BTF_KIND_FUNC] = &func_ops, [BTF_KIND_FUNC_PROTO] = &func_proto_ops, + [BTF_KIND_VAR] = &var_ops, + [BTF_KIND_DATASEC] = &datasec_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -2622,13 +2995,17 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, if (!env_type_is_resolved(env, type_id)) return false; - if (btf_type_is_struct(t)) + if (btf_type_is_struct(t) || btf_type_is_datasec(t)) return !btf->resolved_ids[type_id] && - !btf->resolved_sizes[type_id]; + !btf->resolved_sizes[type_id]; - if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) { + if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || + btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); - return t && !btf_type_is_modifier(t); + return t && + !btf_type_is_modifier(t) && + !btf_type_is_var(t) && + !btf_type_is_datasec(t); } if (btf_type_is_array(t)) { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4e807973aa80..fcde0f7b2585 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -11,7 +11,10 @@ #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/cgroup.h> +#include <linux/filter.h> #include <linux/slab.h> +#include <linux/sysctl.h> +#include <linux/string.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <net/sock.h> @@ -701,7 +704,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); static const struct bpf_func_proto * -cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -710,6 +713,12 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: @@ -725,6 +734,12 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static const struct bpf_func_proto * +cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return cgroup_base_func_proto(func_id, prog); +} + static bool cgroup_dev_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -762,3 +777,356 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { .get_func_proto = cgroup_dev_func_proto, .is_valid_access = cgroup_dev_is_valid_access, }; + +/** + * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl + * + * @head: sysctl table header + * @table: sysctl table + * @write: sysctl is being read (= 0) or written (= 1) + * @buf: pointer to buffer passed by user space + * @pcount: value-result argument: value is size of buffer pointed to by @buf, + * result is size of @new_buf if program set new value, initial value + * otherwise + * @ppos: value-result argument: value is position at which read from or write + * to sysctl is happening, result is new position if program overrode it, + * initial value otherwise + * @new_buf: pointer to pointer to new buffer that will be allocated if program + * overrides new value provided by user space on sysctl write + * NOTE: it's caller responsibility to free *new_buf if it was set + * @type: type of program to be executed + * + * Program is run when sysctl is being accessed, either read or written, and + * can allow or deny such access. + * + * This function will return %-EPERM if an attached program is found and + * returned value != 1 during execution. In all other cases 0 is returned. + */ +int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, + struct ctl_table *table, int write, + void __user *buf, size_t *pcount, + loff_t *ppos, void **new_buf, + enum bpf_attach_type type) +{ + struct bpf_sysctl_kern ctx = { + .head = head, + .table = table, + .write = write, + .ppos = ppos, + .cur_val = NULL, + .cur_len = PAGE_SIZE, + .new_val = NULL, + .new_len = 0, + .new_updated = 0, + }; + struct cgroup *cgrp; + int ret; + + ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL); + if (ctx.cur_val) { + mm_segment_t old_fs; + loff_t pos = 0; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + if (table->proc_handler(table, 0, (void __user *)ctx.cur_val, + &ctx.cur_len, &pos)) { + /* Let BPF program decide how to proceed. */ + ctx.cur_len = 0; + } + set_fs(old_fs); + } else { + /* Let BPF program decide how to proceed. */ + ctx.cur_len = 0; + } + + if (write && buf && *pcount) { + /* BPF program should be able to override new value with a + * buffer bigger than provided by user. + */ + ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL); + ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount); + if (!ctx.new_val || + copy_from_user(ctx.new_val, buf, ctx.new_len)) + /* Let BPF program decide how to proceed. */ + ctx.new_len = 0; + } + + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); + rcu_read_unlock(); + + kfree(ctx.cur_val); + + if (ret == 1 && ctx.new_updated) { + *new_buf = ctx.new_val; + *pcount = ctx.new_len; + } else { + kfree(ctx.new_val); + } + + return ret == 1 ? 0 : -EPERM; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); + +static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, + size_t *lenp) +{ + ssize_t tmp_ret = 0, ret; + + if (dir->header.parent) { + tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp); + if (tmp_ret < 0) + return tmp_ret; + } + + ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp); + if (ret < 0) + return ret; + *bufp += ret; + *lenp -= ret; + ret += tmp_ret; + + /* Avoid leading slash. */ + if (!ret) + return ret; + + tmp_ret = strscpy(*bufp, "/", *lenp); + if (tmp_ret < 0) + return tmp_ret; + *bufp += tmp_ret; + *lenp -= tmp_ret; + + return ret + tmp_ret; +} + +BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf, + size_t, buf_len, u64, flags) +{ + ssize_t tmp_ret = 0, ret; + + if (!buf) + return -EINVAL; + + if (!(flags & BPF_F_SYSCTL_BASE_NAME)) { + if (!ctx->head) + return -EINVAL; + tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len); + if (tmp_ret < 0) + return tmp_ret; + } + + ret = strscpy(buf, ctx->table->procname, buf_len); + + return ret < 0 ? ret : tmp_ret + ret; +} + +static const struct bpf_func_proto bpf_sysctl_get_name_proto = { + .func = bpf_sysctl_get_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +static int copy_sysctl_value(char *dst, size_t dst_len, char *src, + size_t src_len) +{ + if (!dst) + return -EINVAL; + + if (!dst_len) + return -E2BIG; + + if (!src || !src_len) { + memset(dst, 0, dst_len); + return -EINVAL; + } + + memcpy(dst, src, min(dst_len, src_len)); + + if (dst_len > src_len) { + memset(dst + src_len, '\0', dst_len - src_len); + return src_len; + } + + dst[dst_len - 1] = '\0'; + + return -E2BIG; +} + +BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx, + char *, buf, size_t, buf_len) +{ + return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len); +} + +static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = { + .func = bpf_sysctl_get_current_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf, + size_t, buf_len) +{ + if (!ctx->write) { + if (buf && buf_len) + memset(buf, '\0', buf_len); + return -EINVAL; + } + return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len); +} + +static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = { + .func = bpf_sysctl_get_new_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx, + const char *, buf, size_t, buf_len) +{ + if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len) + return -EINVAL; + + if (buf_len > PAGE_SIZE - 1) + return -E2BIG; + + memcpy(ctx->new_val, buf, buf_len); + ctx->new_len = buf_len; + ctx->new_updated = 1; + + return 0; +} + +static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { + .func = bpf_sysctl_set_new_value, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +static const struct bpf_func_proto * +sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_strtol: + return &bpf_strtol_proto; + case BPF_FUNC_strtoul: + return &bpf_strtoul_proto; + case BPF_FUNC_sysctl_get_name: + return &bpf_sysctl_get_name_proto; + case BPF_FUNC_sysctl_get_current_value: + return &bpf_sysctl_get_current_value_proto; + case BPF_FUNC_sysctl_get_new_value: + return &bpf_sysctl_get_new_value_proto; + case BPF_FUNC_sysctl_set_new_value: + return &bpf_sysctl_set_new_value_proto; + default: + return cgroup_base_func_proto(func_id, prog); + } +} + +static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + const int size_default = sizeof(__u32); + + if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size) + return false; + + switch (off) { + case offsetof(struct bpf_sysctl, write): + if (type != BPF_READ) + return false; + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + case offsetof(struct bpf_sysctl, file_pos): + if (type == BPF_READ) { + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + } else { + return size == size_default; + } + default: + return false; + } +} + +static u32 sysctl_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct bpf_sysctl, write): + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sysctl_kern, write, + FIELD_SIZEOF(struct bpf_sysctl_kern, + write), + target_size)); + break; + case offsetof(struct bpf_sysctl, file_pos): + /* ppos is a pointer so it should be accessed via indirect + * loads and stores. Also for stores additional temporary + * register is used since neither src_reg nor dst_reg can be + * overridden. + */ + if (type == BPF_WRITE) { + int treg = BPF_REG_9; + + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + *insn++ = BPF_STX_MEM( + BPF_DW, si->dst_reg, treg, + offsetof(struct bpf_sysctl_kern, tmp_reg)); + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), + treg, si->dst_reg, + offsetof(struct bpf_sysctl_kern, ppos)); + *insn++ = BPF_STX_MEM( + BPF_SIZEOF(u32), treg, si->src_reg, 0); + *insn++ = BPF_LDX_MEM( + BPF_DW, treg, si->dst_reg, + offsetof(struct bpf_sysctl_kern, tmp_reg)); + } else { + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sysctl_kern, ppos)); + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + } + *target_size = sizeof(u32); + break; + } + + return insn - insn_buf; +} + +const struct bpf_verifier_ops cg_sysctl_verifier_ops = { + .get_func_proto = sysctl_func_proto, + .is_valid_access = sysctl_is_valid_access, + .convert_ctx_access = sysctl_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_sysctl_prog_ops = { +}; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ff09d32a8a1b..3ba56e73c90e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && - dst[i].src_reg == BPF_PSEUDO_MAP_FD) { + (dst[i].src_reg == BPF_PSEUDO_MAP_FD || + dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && @@ -438,6 +439,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; + int err; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { @@ -453,8 +455,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * we afterwards may not fail anymore. */ if (insn_adj_cnt > cnt_max && - bpf_adj_branches(prog, off, off + 1, off + len, true)) - return NULL; + (err = bpf_adj_branches(prog, off, off + 1, off + len, true))) + return ERR_PTR(err); /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as @@ -463,7 +465,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) - return NULL; + return ERR_PTR(-ENOMEM); prog_adj->len = insn_adj_cnt; @@ -848,7 +850,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp) if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - bpf_jit_binary_unlock_ro(hdr); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); @@ -1096,13 +1097,13 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); - if (!tmp) { + if (IS_ERR(tmp)) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); - return ERR_PTR(-ENOMEM); + return tmp; } clone = tmp; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8974b3755670..cf727d77c6c6 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -160,11 +160,15 @@ static void cpu_map_kthread_stop(struct work_struct *work) } static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_frame *xdpf) + struct xdp_frame *xdpf, + struct sk_buff *skb) { + unsigned int hard_start_headroom; unsigned int frame_size; void *pkt_data_start; - struct sk_buff *skb; + + /* Part of headroom was reserved to xdpf */ + hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; /* build_skb need to place skb_shared_info after SKB end, and * also want to know the memory "truesize". Thus, need to @@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) + + frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdpf->data - xdpf->headroom; - skb = build_skb(pkt_data_start, frame_size); - if (!skb) + pkt_data_start = xdpf->data - hard_start_headroom; + skb = build_skb_around(skb, pkt_data_start, frame_size); + if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdpf->headroom); + skb_reserve(skb, hard_start_headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); @@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * - RX ring dev queue index (skb_record_rx_queue) */ + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + return skb; } @@ -233,6 +240,8 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) } } +#define CPUMAP_BATCH 8 + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -245,8 +254,11 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { - unsigned int processed = 0, drops = 0, sched = 0; - struct xdp_frame *xdpf; + unsigned int drops = 0, sched = 0; + void *frames[CPUMAP_BATCH]; + void *skbs[CPUMAP_BATCH]; + gfp_t gfp = __GFP_ZERO | GFP_ATOMIC; + int i, n, m; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -262,18 +274,38 @@ static int cpu_map_kthread_run(void *data) sched = cond_resched(); } - /* Process packets in rcpu->queue */ - local_bh_disable(); /* * The bpf_cpu_map_entry is single consumer, with this * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - while ((xdpf = __ptr_ring_consume(rcpu->queue))) { - struct sk_buff *skb; + n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH); + + for (i = 0; i < n; i++) { + void *f = frames[i]; + struct page *page = virt_to_page(f); + + /* Bring struct page memory area to curr CPU. Read by + * build_skb_around via page_is_pfmemalloc(), and when + * freed written by page_frag_free call. + */ + prefetchw(page); + } + + m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs); + if (unlikely(m == 0)) { + for (i = 0; i < n; i++) + skbs[i] = NULL; /* effect: xdp_return_frame */ + drops = n; + } + + local_bh_disable(); + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + struct sk_buff *skb = skbs[i]; int ret; - skb = cpu_map_build_skb(rcpu, xdpf); + skb = cpu_map_build_skb(rcpu, xdpf, skb); if (!skb) { xdp_return_frame(xdpf); continue; @@ -283,13 +315,9 @@ static int cpu_map_kthread_run(void *data) ret = netif_receive_skb_core(skb); if (ret == NET_RX_DROP) drops++; - - /* Limit BH-disable period */ - if (++processed == 8) - break; } /* Feedback loop via tracepoint */ - trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched); + trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched); local_bh_enable(); /* resched point, may call do_softirq() */ } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index de73f55e42fd..d9ce383c0f9c 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, * part of the ldimm64 insn is accessible. */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || + insn->src_reg == BPF_PSEUDO_MAP_VALUE; char tmp[64]; - if (map_ptr && !allow_ptr_leaks) + if (is_ptr && !allow_ptr_leaks) imm = 0; verbose(cbs->private_data, "(%02x) r%d = %s\n", diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fed15cf94dca..192d32e77db3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -23,7 +23,7 @@ #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED) + BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) struct bucket { struct hlist_nulls_head head; @@ -262,8 +262,8 @@ static int htab_map_alloc_check(union bpf_attr *attr) /* Guard against local DoS, and discourage production use. */ return -EPERM; - if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) - /* reserved bits should not be used */ + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (!lru && percpu_lru) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a411fc17d265..4266ffde07ca 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -18,6 +18,9 @@ #include <linux/sched.h> #include <linux/uidgid.h> #include <linux/filter.h> +#include <linux/ctype.h> + +#include "../../lib/kstrtox.h" /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -363,4 +366,132 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif + +#define BPF_STRTOX_BASE_MASK 0x1F + +static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags, + unsigned long long *res, bool *is_negative) +{ + unsigned int base = flags & BPF_STRTOX_BASE_MASK; + const char *cur_buf = buf; + size_t cur_len = buf_len; + unsigned int consumed; + size_t val_len; + char str[64]; + + if (!buf || !buf_len || !res || !is_negative) + return -EINVAL; + + if (base != 0 && base != 8 && base != 10 && base != 16) + return -EINVAL; + + if (flags & ~BPF_STRTOX_BASE_MASK) + return -EINVAL; + + while (cur_buf < buf + buf_len && isspace(*cur_buf)) + ++cur_buf; + + *is_negative = (cur_buf < buf + buf_len && *cur_buf == '-'); + if (*is_negative) + ++cur_buf; + + consumed = cur_buf - buf; + cur_len -= consumed; + if (!cur_len) + return -EINVAL; + + cur_len = min(cur_len, sizeof(str) - 1); + memcpy(str, cur_buf, cur_len); + str[cur_len] = '\0'; + cur_buf = str; + + cur_buf = _parse_integer_fixup_radix(cur_buf, &base); + val_len = _parse_integer(cur_buf, base, res); + + if (val_len & KSTRTOX_OVERFLOW) + return -ERANGE; + + if (val_len == 0) + return -EINVAL; + + cur_buf += val_len; + consumed += cur_buf - str; + + return consumed; +} + +static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags, + long long *res) +{ + unsigned long long _res; + bool is_negative; + int err; + + err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); + if (err < 0) + return err; + if (is_negative) { + if ((long long)-_res > 0) + return -ERANGE; + *res = -_res; + } else { + if ((long long)_res < 0) + return -ERANGE; + *res = _res; + } + return err; +} + +BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags, + long *, res) +{ + long long _res; + int err; + + err = __bpf_strtoll(buf, buf_len, flags, &_res); + if (err < 0) + return err; + if (_res != (long)_res) + return -ERANGE; + *res = _res; + return err; +} + +const struct bpf_func_proto bpf_strtol_proto = { + .func = bpf_strtol, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags, + unsigned long *, res) +{ + unsigned long long _res; + bool is_negative; + int err; + + err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative); + if (err < 0) + return err; + if (is_negative) + return -EINVAL; + if (_res != (unsigned long)_res) + return -ERANGE; + *res = _res; + return err; +} + +const struct bpf_func_proto bpf_strtoul_proto = { + .func = bpf_strtoul, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; #endif diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2ada5e21dfa6..bc53e5b20ddc 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); -static void bpf_evict_inode(struct inode *inode) -{ - enum bpf_type type; - - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); - - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); - if (!bpf_inode_type(inode, &type)) - bpf_any_put(inode->i_private, type); -} - /* * Display the mount options in /proc/mounts. */ @@ -579,11 +566,22 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void bpf_free_inode(struct inode *inode) +{ + enum bpf_type type; + + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); + free_inode_nonrcu(inode); +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, - .evict_inode = bpf_evict_inode, + .free_inode = bpf_free_inode, }; enum { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 6b572e2de7fb..980e8f1f6cb5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -14,7 +14,7 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO #ifdef CONFIG_CGROUP_BPF #define LOCAL_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_cgroup_storage_map { struct bpf_map map; @@ -282,8 +282,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) if (attr->value_size > PAGE_SIZE) return ERR_PTR(-E2BIG); - if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK) - /* reserved bits should not be used */ + if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return ERR_PTR(-EINVAL); if (attr->max_entries) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 93a5cbbde421..e61630c2e50b 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -538,7 +538,7 @@ out: #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY) + BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { @@ -553,6 +553,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index b384ea9f3254..0b140d236889 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -11,8 +11,7 @@ #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) - + (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_queue_stack { struct bpf_map map; @@ -52,7 +51,8 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || attr->value_size == 0 || - attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 62f6bced3a3c..ad3ccf82f31d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -136,21 +136,29 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) void *bpf_map_area_alloc(size_t size, int numa_node) { - /* We definitely need __GFP_NORETRY, so OOM killer doesn't - * trigger under memory pressure as we really just want to - * fail instead. + /* We really just want to fail instead of triggering OOM killer + * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, + * which is used for lower order allocation requests. + * + * It has been observed that higher order allocation requests done by + * vmalloc with __GFP_NORETRY being set might fail due to not trying + * to reclaim memory from the page cache, thus we set + * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + + const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc_node(size, GFP_USER | flags, numa_node); + area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, + numa_node); if (area != NULL) return area; } - return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, - __builtin_return_address(0)); + return __vmalloc_node_flags_caller(size, numa_node, + GFP_KERNEL | __GFP_RETRY_MAYFAIL | + flags, __builtin_return_address(0)); } void bpf_map_area_free(void *area) @@ -158,13 +166,25 @@ void bpf_map_area_free(void *area) kvfree(area); } +static u32 bpf_map_flags_retain_permanent(u32 flags) +{ + /* Some map creation flags are not tied to the map object but + * rather to the map fd instead, so they have no meaning upon + * map object inspection since multiple file descriptors with + * different (access) properties can exist here. Thus, given + * this has zero meaning for the map itself, lets clear these + * from here. + */ + return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); +} + void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; - map->map_flags = attr->map_flags; + map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); } @@ -335,6 +355,18 @@ static int bpf_map_release(struct inode *inode, struct file *filp) return 0; } +static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) +{ + fmode_t mode = f.file->f_mode; + + /* Our file permissions may have been overridden by global + * map permissions facing syscall side. + */ + if (READ_ONCE(map->frozen)) + mode &= ~FMODE_CAN_WRITE; + return mode; +} + #ifdef CONFIG_PROC_FS static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { @@ -356,14 +388,16 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "max_entries:\t%u\n" "map_flags:\t%#x\n" "memlock:\t%llu\n" - "map_id:\t%u\n", + "map_id:\t%u\n" + "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, map->pages * 1ULL << PAGE_SHIFT, - map->id); + map->id, + READ_ONCE(map->frozen)); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", @@ -440,10 +474,10 @@ static int bpf_obj_name_cpy(char *dst, const char *src) const char *end = src + BPF_OBJ_NAME_LEN; memset(dst, 0, BPF_OBJ_NAME_LEN); - - /* Copy all isalnum() and '_' char */ + /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { - if (!isalnum(*src) && *src != '_') + if (!isalnum(*src) && + *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } @@ -470,9 +504,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 key_size, value_size; int ret = 0; - key_type = btf_type_id_size(btf, &btf_key_id, &key_size); - if (!key_type || key_size != map->key_size) - return -EINVAL; + /* Some maps allow key to be unspecified. */ + if (btf_key_id) { + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || key_size != map->key_size) + return -EINVAL; + } else { + key_type = btf_type_by_id(btf, 0); + if (!map->ops->map_check_btf) + return -EINVAL; + } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) @@ -481,9 +522,12 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->spin_lock_off = btf_find_spin_lock(btf, value_type); if (map_value_has_spin_lock(map)) { + if (map->map_flags & BPF_F_RDONLY_PROG) + return -EACCES; if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_SK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { @@ -537,7 +581,7 @@ static int map_create(union bpf_attr *attr) if (attr->btf_key_type_id || attr->btf_value_type_id) { struct btf *btf; - if (!attr->btf_key_type_id || !attr->btf_value_type_id) { + if (!attr->btf_value_type_id) { err = -EINVAL; goto free_map_nouncharge; } @@ -705,8 +749,7 @@ static int map_lookup_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_READ)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } @@ -835,8 +878,7 @@ static int map_update_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -947,8 +989,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -999,8 +1040,7 @@ static int map_get_next_key(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_READ)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } @@ -1067,8 +1107,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -1110,6 +1149,36 @@ err_put: return err; } +#define BPF_MAP_FREEZE_LAST_FIELD map_fd + +static int map_freeze(const union bpf_attr *attr) +{ + int err = 0, ufd = attr->map_fd; + struct bpf_map *map; + struct fd f; + + if (CHECK_ATTR(BPF_MAP_FREEZE)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + if (READ_ONCE(map->frozen)) { + err = -EBUSY; + goto err_put; + } + if (!capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto err_put; + } + + WRITE_ONCE(map->frozen, true); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -1549,7 +1618,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) /* eBPF programs must be GPL compatible to use GPL-ed functions */ is_gpl = license_is_gpl_compatible(license); - if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS) + if (attr->insn_cnt == 0 || + attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) return -E2BIG; if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && @@ -1720,12 +1790,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } raw_tp->btp = btp; - prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd, - BPF_PROG_TYPE_RAW_TRACEPOINT); + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out_free_tp; } + if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && + prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { + err = -EINVAL; + goto out_put_prog; + } err = bpf_probe_register(raw_tp->btp, prog); if (err) @@ -1819,6 +1893,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_FLOW_DISSECTOR: ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; break; + case BPF_CGROUP_SYSCTL: + ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; + break; default: return -EINVAL; } @@ -1897,6 +1974,9 @@ static int bpf_prog_detach(const union bpf_attr *attr) return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: return skb_flow_dissector_bpf_prog_detach(attr); + case BPF_CGROUP_SYSCTL: + ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; + break; default: return -EINVAL; } @@ -1930,9 +2010,12 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: + case BPF_CGROUP_SYSCTL: break; case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_prog_query(attr, uattr); default: return -EINVAL; } @@ -1940,7 +2023,7 @@ static int bpf_prog_query(const union bpf_attr *attr, return cgroup_bpf_prog_query(attr, uattr); } -#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration +#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1953,6 +2036,14 @@ static int bpf_prog_test_run(const union bpf_attr *attr, if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; + if ((attr->test.ctx_size_in && !attr->test.ctx_in) || + (!attr->test.ctx_size_in && attr->test.ctx_in)) + return -EINVAL; + + if ((attr->test.ctx_size_out && !attr->test.ctx_out) || + (!attr->test.ctx_size_out && attr->test.ctx_out)) + return -EINVAL; + prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -2063,13 +2154,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, - unsigned long addr) + unsigned long addr, u32 *off, + u32 *type) { + const struct bpf_map *map; int i; - for (i = 0; i < prog->aux->used_map_cnt; i++) - if (prog->aux->used_maps[i] == (void *)addr) - return prog->aux->used_maps[i]; + for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { + map = prog->aux->used_maps[i]; + if (map == (void *)addr) { + *type = BPF_PSEUDO_MAP_FD; + return map; + } + if (!map->ops->map_direct_value_meta) + continue; + if (!map->ops->map_direct_value_meta(map, addr, off)) { + *type = BPF_PSEUDO_MAP_VALUE; + return map; + } + } + return NULL; } @@ -2077,6 +2181,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) { const struct bpf_map *map; struct bpf_insn *insns; + u32 off, type; u64 imm; int i; @@ -2104,11 +2209,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; - map = bpf_map_from_imm(prog, imm); + map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { - insns[i].src_reg = BPF_PSEUDO_MAP_FD; + insns[i].src_reg = type; insns[i].imm = map->id; - insns[i + 1].imm = 0; + insns[i + 1].imm = off; continue; } } @@ -2698,6 +2803,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; + case BPF_MAP_FREEZE: + err = map_freeze(&attr); + break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr); break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce166a002d16..7b05e8938d5c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -176,7 +176,6 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 #define BPF_COMPLEXITY_LIMIT_STATES 64 @@ -212,7 +211,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; - int ptr_id; + int ref_obj_id; int func_id; }; @@ -346,35 +345,23 @@ static bool reg_type_may_be_null(enum bpf_reg_type type) type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool type_is_refcounted(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET; -} - -static bool type_is_refcounted_or_null(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; -} - -static bool reg_is_refcounted(const struct bpf_reg_state *reg) -{ - return type_is_refcounted(reg->type); -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && map_value_has_spin_lock(reg->map_ptr); } -static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type_is_refcounted_or_null(reg->type); + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCKET_OR_NULL || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool arg_type_is_refcounted(enum bpf_arg_type type) +static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { - return type == ARG_PTR_TO_SOCKET; + return type == ARG_PTR_TO_SOCK_COMMON; } /* Determine whether the function releases some resources allocated by another @@ -389,7 +376,14 @@ static bool is_release_function(enum bpf_func_id func_id) static bool is_acquire_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_lookup_tcp || - func_id == BPF_FUNC_sk_lookup_udp; + func_id == BPF_FUNC_sk_lookup_udp || + func_id == BPF_FUNC_skc_lookup_tcp; +} + +static bool is_ptr_cast_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_tcp_sock || + func_id == BPF_FUNC_sk_fullsock; } /* string representation of 'enum bpf_reg_type' */ @@ -411,6 +405,7 @@ static const char * const reg_type_str[] = { [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", + [PTR_TO_TP_BUFFER] = "tp_buffer", }; static char slot_type_char[] = { @@ -466,6 +461,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, ",call_%d", func(env, reg)->callsite); } else { verbose(env, "(id=%d", reg->id); + if (reg_type_may_be_refcounted_or_null(t)) + verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); if (t != SCALAR_VALUE) verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) @@ -1095,7 +1092,7 @@ static int check_subprogs(struct bpf_verifier_env *env) */ subprog[env->subprog_cnt].start = insn_cnt; - if (env->log.level > 1) + if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); @@ -1142,6 +1139,7 @@ static int mark_reg_read(struct bpf_verifier_env *env, struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ + int cnt = 0; while (parent) { /* if read wasn't screened by an earlier write ... */ @@ -1153,12 +1151,25 @@ static int mark_reg_read(struct bpf_verifier_env *env, parent->var_off.value, parent->off); return -EFAULT; } + if (parent->live & REG_LIVE_READ) + /* The parentage chain never changes and + * this parent was already marked as LIVE_READ. + * There is no need to keep walking the chain again and + * keep re-marking all parents as LIVE_READ. + * This case happens when the same register is read + * multiple times without writes into it in-between. + */ + break; /* ... then we depend on parent's value */ parent->live |= REG_LIVE_READ; state = parent; parent = state->parent; writes = true; + cnt++; } + + if (env->longest_mark_read_walk < cnt) + env->longest_mark_read_walk = cnt; return 0; } @@ -1167,30 +1178,32 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg, *regs = state->regs; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); return -EINVAL; } + reg = ®s[regno]; if (t == SRC_OP) { /* check whether register used as source operand can be read */ - if (regs[regno].type == NOT_INIT) { + if (reg->type == NOT_INIT) { verbose(env, "R%d !read_ok\n", regno); return -EACCES; } /* We don't need to worry about FP liveness because it's read-only */ - if (regno != BPF_REG_FP) - return mark_reg_read(env, ®s[regno], - regs[regno].parent); + if (regno == BPF_REG_FP) + return 0; + + return mark_reg_read(env, reg, reg->parent); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } - regs[regno].live |= REG_LIVE_WRITTEN; + reg->live |= REG_LIVE_WRITTEN; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } @@ -1416,7 +1429,7 @@ static int check_stack_access(struct bpf_verifier_env *env, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable stack access var_off=%s off=%d size=%d", + verbose(env, "variable stack access var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } @@ -1429,6 +1442,28 @@ static int check_stack_access(struct bpf_verifier_env *env, return 0; } +static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, + int off, int size, enum bpf_access_type type) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map = regs[regno].map_ptr; + u32 cap = bpf_map_flags_to_cap(map); + + if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { + verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + + if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { + verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n", + map->value_size, off, size); + return -EACCES; + } + + return 0; +} + /* check read/write into map element returned by bpf_map_lookup_elem() */ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) @@ -1458,7 +1493,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (env->log.level) + if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, state); /* The minimum value is only important with signed @@ -1901,8 +1936,9 @@ continue_func: } frame++; if (frame >= MAX_CALL_FRAMES) { - WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); - return -EFAULT; + verbose(env, "the call stack of %d frames is too deep !\n", + frame); + return -E2BIG; } goto process_func; } @@ -1958,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env, return 0; } +static int check_tp_buffer_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int regno, int off, int size) +{ + if (off < 0) { + verbose(env, + "R%d invalid tracepoint buffer access: off=%d, size=%d", + regno, off, size); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, + "R%d invalid variable buffer offset: off=%d, var_off=%s", + regno, off, tn_buf); + return -EACCES; + } + if (off + size > env->prog->aux->max_tp_access) + env->prog->aux->max_tp_access = off + size; + + return 0; +} + + /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ @@ -2014,7 +2076,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } - + err = check_map_access_type(env, regno, off, size, t); + if (err) + return err; err = check_map_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); @@ -2100,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_TP_BUFFER) { + err = check_tp_buffer_access(env, reg, regno, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -2160,6 +2228,29 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins BPF_SIZE(insn->code), BPF_WRITE, -1, true); } +static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno, + int off, int access_size, + bool zero_size_allowed) +{ + struct bpf_reg_state *reg = reg_state(env, regno); + + if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || + access_size < 0 || (access_size == 0 && !zero_size_allowed)) { + if (tnum_is_const(reg->var_off)) { + verbose(env, "invalid stack type R%d off=%d access_size=%d\n", + regno, off, access_size); + } else { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n", + regno, tn_buf, access_size); + } + return -EACCES; + } + return 0; +} + /* when register 'regno' is passed into function that will read 'access_size' * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized. @@ -2172,7 +2263,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); - int off, i, slot, spi; + int err, min_off, max_off, i, slot, spi; if (reg->type != PTR_TO_STACK) { /* Allow zero-byte read from NULL, regardless of pointer type */ @@ -2186,21 +2277,57 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return -EACCES; } - /* Only allow fixed-offset stack reads */ - if (!tnum_is_const(reg->var_off)) { - char tn_buf[48]; + if (tnum_is_const(reg->var_off)) { + min_off = max_off = reg->var_off.value + reg->off; + err = __check_stack_boundary(env, regno, min_off, access_size, + zero_size_allowed); + if (err) + return err; + } else { + /* Variable offset is prohibited for unprivileged mode for + * simplicity since it requires corresponding support in + * Spectre masking for stack ALU. + * See also retrieve_ptr_limit(). + */ + if (!env->allow_ptr_leaks) { + char tn_buf[48]; - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid variable stack read R%d var_off=%s\n", - regno, tn_buf); - return -EACCES; - } - off = reg->off + reg->var_off.value; - if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || - access_size < 0 || (access_size == 0 && !zero_size_allowed)) { - verbose(env, "invalid stack type R%d off=%d access_size=%d\n", - regno, off, access_size); - return -EACCES; + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n", + regno, tn_buf); + return -EACCES; + } + /* Only initialized buffer on stack is allowed to be accessed + * with variable offset. With uninitialized buffer it's hard to + * guarantee that whole memory is marked as initialized on + * helper return since specific bounds are unknown what may + * cause uninitialized stack leaking. + */ + if (meta && meta->raw_mode) + meta = NULL; + + if (reg->smax_value >= BPF_MAX_VAR_OFF || + reg->smax_value <= -BPF_MAX_VAR_OFF) { + verbose(env, "R%d unbounded indirect variable offset stack access\n", + regno); + return -EACCES; + } + min_off = reg->smin_value + reg->off; + max_off = reg->smax_value + reg->off; + err = __check_stack_boundary(env, regno, min_off, access_size, + zero_size_allowed); + if (err) { + verbose(env, "R%d min value is outside of stack bound\n", + regno); + return err; + } + err = __check_stack_boundary(env, regno, max_off, access_size, + zero_size_allowed); + if (err) { + verbose(env, "R%d max value is outside of stack bound\n", + regno); + return err; + } } if (meta && meta->raw_mode) { @@ -2209,10 +2336,10 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, return 0; } - for (i = 0; i < access_size; i++) { + for (i = min_off; i < max_off + access_size; i++) { u8 *stype; - slot = -(off + i) - 1; + slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) goto err; @@ -2225,8 +2352,16 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, goto mark; } err: - verbose(env, "invalid indirect read from stack off %d+%d size %d\n", - off, i, access_size); + if (tnum_is_const(reg->var_off)) { + verbose(env, "invalid indirect read from stack off %d+%d size %d\n", + min_off, i - min_off, access_size); + } else { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n", + tn_buf, i - min_off, access_size); + } return -EACCES; mark: /* reading any byte out of 8-byte 'spill_slot' will cause @@ -2235,7 +2370,7 @@ mark: mark_reg_read(env, &state->stack[spi].spilled_ptr, state->stack[spi].spilled_ptr.parent); } - return update_stack_depth(env, state, off); + return update_stack_depth(env, state, min_off); } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, @@ -2250,6 +2385,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_VALUE: + if (check_map_access_type(env, regno, reg->off, access_size, + meta && meta->raw_mode ? BPF_WRITE : + BPF_READ)) + return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); default: /* scalar_value|ptr_to_stack or invalid ptr */ @@ -2356,6 +2495,22 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type) type == ARG_CONST_SIZE_OR_ZERO; } +static bool arg_type_is_int_ptr(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_INT || + type == ARG_PTR_TO_LONG; +} + +static int int_ptr_type_to_size(enum bpf_arg_type type) +{ + if (type == ARG_PTR_TO_INT) + return sizeof(u32); + else if (type == ARG_PTR_TO_LONG) + return sizeof(u64); + + return -EINVAL; +} + static int check_func_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) @@ -2388,10 +2543,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && - type != expected_type) + if (register_is_null(reg) && + arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) + /* final test in check_stack_boundary() */; + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -2414,16 +2574,19 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ if (!type_is_sk_pointer(type)) goto err_type; + if (reg->ref_obj_id) { + if (meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + } } else if (arg_type == ARG_PTR_TO_SOCKET) { expected_type = PTR_TO_SOCKET; if (type != expected_type) goto err_type; - if (meta->ptr_id || !reg->id) { - verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", - meta->ptr_id, reg->id); - return -EFAULT; - } - meta->ptr_id = reg->id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -2449,6 +2612,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; + } else if (arg_type_is_int_ptr(arg_type)) { + expected_type = PTR_TO_STACK; + if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && + type != expected_type) + goto err_type; } else { verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -2475,6 +2644,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta->map_ptr->key_size, false, NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && + !register_is_null(reg)) || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -2530,6 +2701,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); + } else if (arg_type_is_int_ptr(arg_type)) { + int size = int_ptr_type_to_size(arg_type); + + err = check_helper_mem_access(env, regno, size, false, meta); + if (err) + return err; + err = check_ptr_alignment(env, reg, 0, size, true); } return err; @@ -2617,6 +2795,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_map_push_elem) goto error; break; + case BPF_MAP_TYPE_SK_STORAGE: + if (func_id != BPF_FUNC_sk_storage_get && + func_id != BPF_FUNC_sk_storage_delete) + goto error; + break; default: break; } @@ -2680,6 +2863,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_sk_storage_get: + case BPF_FUNC_sk_storage_delete: + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) + goto error; + break; default: break; } @@ -2740,32 +2928,38 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } -static bool check_refcount_ok(const struct bpf_func_proto *fn) +static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id) { int count = 0; - if (arg_type_is_refcounted(fn->arg1_type)) + if (arg_type_may_be_refcounted(fn->arg1_type)) count++; - if (arg_type_is_refcounted(fn->arg2_type)) + if (arg_type_may_be_refcounted(fn->arg2_type)) count++; - if (arg_type_is_refcounted(fn->arg3_type)) + if (arg_type_may_be_refcounted(fn->arg3_type)) count++; - if (arg_type_is_refcounted(fn->arg4_type)) + if (arg_type_may_be_refcounted(fn->arg4_type)) count++; - if (arg_type_is_refcounted(fn->arg5_type)) + if (arg_type_may_be_refcounted(fn->arg5_type)) count++; + /* A reference acquiring function cannot acquire + * another refcounted ptr. + */ + if (is_acquire_function(func_id) && count) + return false; + /* We only support one arg being unreferenced at the moment, * which is sufficient for the helper functions we have right now. */ return count <= 1; } -static int check_func_proto(const struct bpf_func_proto *fn) +static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && - check_refcount_ok(fn) ? 0 : -EINVAL; + check_refcount_ok(fn, func_id) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2799,19 +2993,20 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } static void release_reg_references(struct bpf_verifier_env *env, - struct bpf_func_state *state, int id) + struct bpf_func_state *state, + int ref_obj_id) { struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].id == id) + if (regs[i].ref_obj_id == ref_obj_id) mark_reg_unknown(env, regs, i); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; - if (reg_is_refcounted(reg) && reg->id == id) + if (reg->ref_obj_id == ref_obj_id) __mark_reg_unknown(reg); } } @@ -2820,15 +3015,20 @@ static void release_reg_references(struct bpf_verifier_env *env, * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, - struct bpf_call_arg_meta *meta) + int ref_obj_id) { struct bpf_verifier_state *vstate = env->cur_state; + int err; int i; + err = release_reference_state(cur_func(env), ref_obj_id); + if (err) + return err; + for (i = 0; i <= vstate->curframe; i++) - release_reg_references(env, vstate->frame[i], meta->ptr_id); + release_reg_references(env, vstate->frame[i], ref_obj_id); - return release_reference_state(cur_func(env), meta->ptr_id); + return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, @@ -2897,7 +3097,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* and go analyze first insn of the callee */ *insn_idx = target_insn; - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, caller); verbose(env, "callee:\n"); @@ -2937,7 +3137,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return err; *insn_idx = callee->callsite + 1; - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee); verbose(env, "to caller at %d:\n", *insn_idx); @@ -2971,6 +3171,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; + struct bpf_map *map = meta->map_ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && @@ -2981,11 +3182,24 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, func_id != BPF_FUNC_map_peek_elem) return 0; - if (meta->map_ptr == NULL) { + if (map == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } + /* In case of read-only, some additional restrictions + * need to be applied in order to prevent altering the + * state of the map from program side. + */ + if ((map->map_flags & BPF_F_RDONLY_PROG) && + (func_id == BPF_FUNC_map_delete_elem || + func_id == BPF_FUNC_map_update_elem || + func_id == BPF_FUNC_map_push_elem || + func_id == BPF_FUNC_map_pop_elem)) { + verbose(env, "write into map forbidden\n"); + return -EACCES; + } + if (!BPF_MAP_PTR(aux->map_state)) bpf_map_ptr_store(aux, meta->map_ptr, meta->map_ptr->unpriv_array); @@ -3047,7 +3261,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; - err = check_func_proto(fn); + err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); @@ -3093,7 +3307,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } } else if (is_release_function(func_id)) { - err = release_reference(env, &meta); + err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -3149,17 +3363,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - if (is_acquire_function(func_id)) { - int id = acquire_reference_state(env, insn_idx); - - if (id < 0) - return id; - /* For release_reference() */ - regs[BPF_REG_0].id = id; - } else { - /* For mark_ptr_or_null_reg() */ - regs[BPF_REG_0].id = ++env->id_gen; - } + regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; @@ -3170,6 +3378,20 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + if (is_ptr_cast_function(func_id)) { + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; + } else if (is_acquire_function(func_id)) { + int id = acquire_reference_state(env, insn_idx); + + if (id < 0) + return id; + /* For mark_ptr_or_null_reg() */ + regs[BPF_REG_0].id = id; + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = id; + } + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); err = check_map_func_compatibility(env, meta.map_ptr, func_id); @@ -3268,6 +3490,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, switch (ptr_reg->type) { case PTR_TO_STACK: + /* Indirect variable offset stack access is prohibited in + * unprivileged mode so it's not handled here. + */ off = ptr_reg->off + ptr_reg->var_off.value; if (mask_to_left) *ptr_limit = MAX_BPF_STACK + off; @@ -3368,7 +3593,7 @@ do_sim: *dst_reg = *ptr_reg; } ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); - if (!ptr_is_dst_reg) + if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? -EFAULT : 0; } @@ -4124,15 +4349,35 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static void __find_good_pkt_pointers(struct bpf_func_state *state, + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type, u16 new_range) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + reg = &state->regs[i]; + if (reg->type == type && reg->id == dst_reg->id) + /* keep the maximum range already checked */ + reg->range = max(reg->range, new_range); + } + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg->type == type && reg->id == dst_reg->id) + reg->range = max(reg->range, new_range); + } +} + static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { - struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs, *reg; u16 new_range; - int i, j; + int i; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -4197,20 +4442,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ - for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == type && regs[i].id == dst_reg->id) - /* keep the maximum range already checked */ - regs[i].range = max(regs[i].range, new_range); - - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); - } - } + for (i = 0; i <= vstate->curframe; i++) + __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, + new_range); } /* compute branch direction of the expression "if (reg opcode val) goto target;" @@ -4665,17 +4899,41 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { reg->type = PTR_TO_TCP_SOCK; } - if (is_null || !(reg_is_refcounted(reg) || - reg_may_point_to_spin_lock(reg))) { - /* We don't need id from this point onwards anymore, - * thus we should better reset it, so that state - * pruning has chances to take effect. + if (is_null) { + /* We don't need id and ref_obj_id from this point + * onwards anymore, thus we should better reset it, + * so that state pruning has chances to take effect. + */ + reg->id = 0; + reg->ref_obj_id = 0; + } else if (!reg_may_point_to_spin_lock(reg)) { + /* For not-NULL ptr, reg->ref_obj_id will be reset + * in release_reg_references(). + * + * reg->id is still used by spin_lock ptr. Other + * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } +static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, + bool is_null) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + mark_ptr_or_null_reg(state, reg, id, is_null); + } +} + /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ @@ -4683,24 +4941,20 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *regs = state->regs; + u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; - int i, j; - - if (reg_is_refcounted_or_null(®s[regno]) && is_null) - release_reference_state(state, id); + int i; - for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(state, ®s[i], id, is_null); + if (ref_obj_id && ref_obj_id == id && is_null) + /* regs[regno] is in the " == NULL" branch. + * No one could have freed the reference state before + * doing the NULL check. + */ + WARN_ON_ONCE(release_reference_state(state, id)); - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - mark_ptr_or_null_reg(state, reg, id, is_null); - } - } + for (i = 0; i <= vstate->curframe; i++) + __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, @@ -4939,23 +5193,17 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, insn->dst_reg); return -EACCES; } - if (env->log.level) + if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, this_branch->frame[this_branch->curframe]); return 0; } -/* return the map pointer stored inside BPF_LD_IMM64 instruction */ -static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) -{ - u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32; - - return (struct bpf_map *) (unsigned long) imm64; -} - /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { + struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { @@ -4979,11 +5227,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } - /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */ - BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD); + map = env->used_maps[aux->map_index]; + mark_reg_known_zero(env, regs, insn->dst_reg); + regs[insn->dst_reg].map_ptr = map; + + if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { + regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + regs[insn->dst_reg].off = aux->map_off; + if (map_value_has_spin_lock(map)) + regs[insn->dst_reg].id = ++env->id_gen; + } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + } else { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - regs[insn->dst_reg].type = CONST_PTR_TO_MAP; - regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn); return 0; } @@ -5107,6 +5366,7 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SYSCTL: break; default: return 0; @@ -5177,10 +5437,6 @@ enum { #define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) -static int *insn_stack; /* stack of insns to process */ -static int cur_stack; /* current stack index */ -static int *insn_state; - /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction @@ -5188,6 +5444,9 @@ static int *insn_state; */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { + int *insn_stack = env->cfg.insn_stack; + int *insn_state = env->cfg.insn_state; + if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return 0; @@ -5208,9 +5467,9 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; - if (cur_stack >= env->prog->len) + if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; - insn_stack[cur_stack++] = w; + insn_stack[env->cfg.cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { verbose_linfo(env, t, "%d: ", t); @@ -5234,27 +5493,28 @@ static int check_cfg(struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; + int *insn_stack, *insn_state; int ret = 0; int i, t; - insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; - insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); + insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_stack) { - kfree(insn_state); + kvfree(insn_state); return -ENOMEM; } insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ - cur_stack = 1; + env->cfg.cur_stack = 1; peek_stack: - if (cur_stack == 0) + if (env->cfg.cur_stack == 0) goto check_state; - t = insn_stack[cur_stack - 1]; + t = insn_stack[env->cfg.cur_stack - 1]; if (BPF_CLASS(insns[t].code) == BPF_JMP || BPF_CLASS(insns[t].code) == BPF_JMP32) { @@ -5323,7 +5583,7 @@ peek_stack: mark_explored: insn_state[t] = EXPLORED; - if (cur_stack-- <= 0) { + if (env->cfg.cur_stack-- <= 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; @@ -5341,8 +5601,9 @@ check_state: ret = 0; /* cfg looks good */ err_free: - kfree(insn_state); - kfree(insn_stack); + kvfree(insn_state); + kvfree(insn_stack); + env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } @@ -6031,6 +6292,22 @@ static bool states_equal(struct bpf_verifier_env *env, return true; } +static int propagate_liveness_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + struct bpf_reg_state *parent_reg) +{ + int err; + + if (parent_reg->live & REG_LIVE_READ || !(reg->live & REG_LIVE_READ)) + return 0; + + err = mark_reg_read(env, reg, parent_reg); + if (err) + return err; + + return 0; +} + /* A write screens off any subsequent reads; but write marks come from the * straight-line code between a state and its parent. When we arrive at an * equivalent state (jump target or such) we didn't arrive by the straight-line @@ -6042,8 +6319,9 @@ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, struct bpf_verifier_state *vparent) { - int i, frame, err = 0; + struct bpf_reg_state *state_reg, *parent_reg; struct bpf_func_state *state, *parent; + int i, frame, err = 0; if (vparent->curframe != vstate->curframe) { WARN(1, "propagate_live: parent frame %d current frame %d\n", @@ -6052,29 +6330,28 @@ static int propagate_liveness(struct bpf_verifier_env *env, } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); - /* We don't need to worry about FP liveness because it's read-only */ - for (i = 0; i < BPF_REG_FP; i++) { - if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) - continue; - if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], - &vparent->frame[vstate->curframe]->regs[i]); + for (frame = 0; frame <= vstate->curframe; frame++) { + parent = vparent->frame[frame]; + state = vstate->frame[frame]; + parent_reg = parent->regs; + state_reg = state->regs; + /* We don't need to worry about FP liveness, it's read-only */ + for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { + err = propagate_liveness_reg(env, &state_reg[i], + &parent_reg[i]); if (err) return err; } - } - /* ... and stack slots */ - for (frame = 0; frame <= vstate->curframe; frame++) { - state = vstate->frame[frame]; - parent = vparent->frame[frame]; + /* Propagate stack slots. */ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && i < parent->allocated_stack / BPF_REG_SIZE; i++) { - if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) - continue; - if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) - mark_reg_read(env, &state->stack[i].spilled_ptr, - &parent->stack[i].spilled_ptr); + parent_reg = &parent->stack[i].spilled_ptr; + state_reg = &state->stack[i].spilled_ptr; + err = propagate_liveness_reg(env, state_reg, + parent_reg); + if (err) + return err; } } return err; @@ -6083,11 +6360,13 @@ static int propagate_liveness(struct bpf_verifier_env *env, static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; - struct bpf_verifier_state_list *sl; + struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - sl = env->explored_states[insn_idx]; + pprev = &env->explored_states[insn_idx]; + sl = *pprev; + if (!sl) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here @@ -6098,6 +6377,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) while (sl != STATE_LIST_MARK) { if (states_equal(env, &sl->state, cur)) { + sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. @@ -6113,10 +6393,40 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return err; return 1; } - sl = sl->next; states_cnt++; + sl->miss_cnt++; + /* heuristic to determine whether this state is beneficial + * to keep checking from state equivalence point of view. + * Higher numbers increase max_states_per_insn and verification time, + * but do not meaningfully decrease insn_processed. + */ + if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { + /* the state is unlikely to be useful. Remove it to + * speed up verification + */ + *pprev = sl->next; + if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { + free_verifier_state(&sl->state, false); + kfree(sl); + env->peak_states--; + } else { + /* cannot free this state, since parentage chain may + * walk it later. Add it for free_list instead to + * be freed at the end of verification + */ + sl->next = env->free_list; + env->free_list = sl; + } + sl = *pprev; + continue; + } + pprev = &sl->next; + sl = *pprev; } + if (env->max_states_per_insn < states_cnt) + env->max_states_per_insn = states_cnt; + if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return 0; @@ -6130,6 +6440,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; + env->total_states++; + env->peak_states++; /* add new state to the head of linked list */ new = &new_sl->state; @@ -6214,8 +6526,7 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_verifier_state *state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; - int insn_cnt = env->prog->len, i; - int insn_processed = 0; + int insn_cnt = env->prog->len; bool do_print_state = false; env->prev_linfo = NULL; @@ -6250,10 +6561,10 @@ static int do_check(struct bpf_verifier_env *env) insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); - if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { + if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", - insn_processed); + env->insn_processed); return -E2BIG; } @@ -6262,7 +6573,7 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, @@ -6280,8 +6591,9 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (env->log.level > 1 || (env->log.level && do_print_state)) { - if (env->log.level > 1) + if (env->log.level & BPF_LOG_LEVEL2 || + (env->log.level & BPF_LOG_LEVEL && do_print_state)) { + if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "%d:", env->insn_idx); else verbose(env, "\nfrom %d to %d%s:", @@ -6292,7 +6604,7 @@ static int do_check(struct bpf_verifier_env *env) do_print_state = false; } - if (env->log.level) { + if (env->log.level & BPF_LOG_LEVEL) { const struct bpf_insn_cbs cbs = { .cb_print = verbose, .private_data = env, @@ -6557,16 +6869,6 @@ process_bpf_exit: env->insn_idx++; } - verbose(env, "processed %d insns (limit %d), stack depth ", - insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); - for (i = 0; i < env->subprog_cnt; i++) { - u32 depth = env->subprog_info[i].stack_depth; - - verbose(env, "%d", depth); - if (i + 1 < env->subprog_cnt) - verbose(env, "+"); - } - verbose(env, "\n"); env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -6664,8 +6966,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { + struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; + u64 addr; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -6674,13 +6978,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return -EINVAL; } - if (insn->src_reg == 0) + if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; - if (insn[0].src_reg != BPF_PSEUDO_MAP_FD || - insn[1].imm != 0) { - verbose(env, "unrecognized bpf_ld_imm64 insn\n"); + /* In final convert_pseudo_ld_imm64() step, this is + * converted into regular 64-bit imm load insn. + */ + if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && + insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || + (insn[0].src_reg == BPF_PSEUDO_MAP_FD && + insn[1].imm != 0)) { + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -6698,16 +7008,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return err; } - /* store map pointer inside BPF_LD_IMM64 instruction */ - insn[0].imm = (u32) (unsigned long) map; - insn[1].imm = ((u64) (unsigned long) map) >> 32; + aux = &env->insn_aux_data[i]; + if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + addr = (unsigned long)map; + } else { + u32 off = insn[1].imm; + + if (off >= BPF_MAX_VAR_OFF) { + verbose(env, "direct value offset of %u is not allowed\n", off); + fdput(f); + return -EINVAL; + } + + if (!map->ops->map_direct_value_addr) { + verbose(env, "no direct value access support for this map type\n"); + fdput(f); + return -EINVAL; + } + + err = map->ops->map_direct_value_addr(map, &addr, off); + if (err) { + verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", + map->value_size, off); + fdput(f); + return err; + } + + aux->map_off = off; + addr += off; + } + + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; /* check whether we recorded this map already */ - for (j = 0; j < env->used_map_cnt; j++) + for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { + aux->map_index = j; fdput(f); goto next_insn; } + } if (env->used_map_cnt >= MAX_USED_MAPS) { fdput(f); @@ -6724,6 +7065,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) fdput(f); return PTR_ERR(map); } + + aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && @@ -6829,8 +7172,13 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of struct bpf_prog *new_prog; new_prog = bpf_patch_insn_single(env->prog, off, patch, len); - if (!new_prog) + if (IS_ERR(new_prog)) { + if (PTR_ERR(new_prog) == -ERANGE) + verbose(env, + "insn %d cannot be patched due to 16-bit range\n", + env->insn_aux_data[off].orig_idx); return NULL; + } if (adjust_insn_aux_data(env, new_prog->len, off, len)) return NULL; adjust_subprog_starts(env, off, len); @@ -7368,9 +7716,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->src_reg != BPF_PSEUDO_CALL) continue; subprog = insn->off; - insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) - func[subprog]->bpf_func - - __bpf_call_base; + insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - + __bpf_call_base; } /* we use the aux data to keep a list of the start addresses @@ -7772,6 +8119,14 @@ static void free_states(struct bpf_verifier_env *env) struct bpf_verifier_state_list *sl, *sln; int i; + sl = env->free_list; + while (sl) { + sln = sl->next; + free_verifier_state(&sl->state, false); + kfree(sl); + sl = sln; + } + if (!env->explored_states) return; @@ -7787,12 +8142,37 @@ static void free_states(struct bpf_verifier_env *env) } } - kfree(env->explored_states); + kvfree(env->explored_states); +} + +static void print_verification_stats(struct bpf_verifier_env *env) +{ + int i; + + if (env->log.level & BPF_LOG_STATS) { + verbose(env, "verification time %lld usec\n", + div_u64(env->verification_time, 1000)); + verbose(env, "stack depth "); + for (i = 0; i < env->subprog_cnt; i++) { + u32 depth = env->subprog_info[i].stack_depth; + + verbose(env, "%d", depth); + if (i + 1 < env->subprog_cnt) + verbose(env, "+"); + } + verbose(env, "\n"); + } + verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " + "total_states %d peak_states %d mark_read %d\n", + env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, + env->max_states_per_insn, env->total_states, + env->peak_states, env->longest_mark_read_walk); } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, union bpf_attr __user *uattr) { + u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; struct bpf_verifier_log *log; int i, len, ret = -EINVAL; @@ -7820,9 +8200,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; + is_priv = capable(CAP_SYS_ADMIN); /* grab the mutex to protect few globals used by verifier */ - mutex_lock(&bpf_verifier_lock); + if (!is_priv) + mutex_lock(&bpf_verifier_lock); if (attr->log_level || attr->log_buf || attr->log_size) { /* user requested verbose verifier output @@ -7834,8 +8216,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, ret = -EINVAL; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || - !log->level || !log->ubuf) + if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || + !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) goto err_unlock; } @@ -7845,7 +8227,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - is_priv = capable(CAP_SYS_ADMIN); env->allow_ptr_leaks = is_priv; ret = replace_map_fd_with_map_ptr(env); @@ -7858,7 +8239,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto skip_full_check; } - env->explored_states = kcalloc(env->prog->len, + env->explored_states = kvcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; @@ -7916,6 +8297,9 @@ skip_full_check: if (ret == 0) ret = fixup_call_args(env); + env->verification_time = ktime_get_ns() - start_time; + print_verification_stats(env); + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; if (log->level && !log->ubuf) { @@ -7955,7 +8339,8 @@ err_release_maps: release_maps(env); *prog = env->prog; err_unlock: - mutex_unlock(&bpf_verifier_lock); + if (!is_priv) + mutex_unlock(&bpf_verifier_lock); vfree(env->insn_aux_data); err_free_env: kfree(env); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 4834c4214e9c..6a1942ed781c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -740,11 +740,10 @@ static inline int nr_cpusets(void) * Must be called with cpuset_mutex held. * * The three key local variables below are: - * q - a linked-list queue of cpuset pointers, used to implement a - * top-down scan of all cpusets. This scan loads a pointer - * to each cpuset marked is_sched_load_balance into the - * array 'csa'. For our purposes, rebuilding the schedulers - * sched domains, we can ignore !is_sched_load_balance cpusets. + * cp - cpuset pointer, used (together with pos_css) to perform a + * top-down scan of all cpusets. For our purposes, rebuilding + * the schedulers sched domains, we can ignore !is_sched_load_ + * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, @@ -775,7 +774,7 @@ static inline int nr_cpusets(void) static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { - struct cpuset *cp; /* scans q */ + struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..f2ef10460698 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -9,6 +9,7 @@ #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> +#include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> @@ -564,6 +565,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } +static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) +{ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + /* + * When CPU hotplug is disabled, then taking the CPU down is not + * possible because takedown_cpu() and the architecture and + * subsystem specific mechanisms are not available. So the CPU + * which would be completely unplugged again needs to stay around + * in the current state. + */ + return st->state <= CPUHP_BRINGUP_CPU; +} + static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -574,8 +589,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); + if (can_rollback_cpu(st)) { + st->target = prev_state; + undo_cpu_up(cpu, st); + } break; } } @@ -844,6 +861,8 @@ static int take_cpu_down(void *_param) /* Give up timekeeping duties */ tick_handover_do_timer(); + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; @@ -1183,8 +1202,15 @@ int freeze_secondary_cpus(int primary) int cpu, error = 0; cpu_maps_update_begin(); - if (!cpu_online(primary)) + if (primary == -1) { primary = cpumask_first(cpu_online_mask); + if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) + primary = housekeeping_any_cpu(HK_FLAG_TIMER); + } else { + if (!cpu_online(primary)) + primary = cpumask_first(cpu_online_mask); + } + /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time @@ -2017,19 +2043,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static const char *smt_states[] = { - [CPU_SMT_ENABLED] = "on", - [CPU_SMT_DISABLED] = "off", - [CPU_SMT_FORCE_DISABLED] = "forceoff", - [CPU_SMT_NOT_SUPPORTED] = "notsupported", -}; - -static ssize_t -show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); -} - static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); @@ -2100,9 +2113,10 @@ static int cpuhp_smt_enable(void) return ret; } + static ssize_t -store_smt_control(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { int ctrlval, ret; @@ -2140,14 +2154,44 @@ store_smt_control(struct device *dev, struct device_attribute *attr, unlock_device_hotplug(); return ret ? ret : count; } + +#else /* !CONFIG_HOTPLUG_SMT */ +static ssize_t +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return -ENODEV; +} +#endif /* CONFIG_HOTPLUG_SMT */ + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", + [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + const char *state = smt_states[cpu_smt_control]; + + return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return __store_smt_control(dev, attr, buf, count); +} static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); static ssize_t show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) { - bool active = topology_max_smt_threads() > 1; - - return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); + return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR(active, 0444, show_smt_active, NULL); @@ -2163,21 +2207,17 @@ static const struct attribute_group cpuhp_smt_attr_group = { NULL }; -static int __init cpu_smt_state_init(void) +static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } -#else -static inline int cpu_smt_state_init(void) { return 0; } -#endif - static int __init cpuhp_sysfs_init(void) { int cpu, ret; - ret = cpu_smt_state_init(); + ret = cpu_smt_sysfs_init(); if (ret) return ret; @@ -2198,7 +2238,7 @@ static int __init cpuhp_sysfs_init(void) return 0; } device_initcall(cpuhp_sysfs_init); -#endif +#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that @@ -2288,3 +2328,18 @@ void __init boot_cpu_hotplug_init(void) #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } + +enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; + +static int __init mitigations_parse_cmdline(char *arg) +{ + if (!strcmp(arg, "off")) + cpu_mitigations = CPU_MITIGATIONS_OFF; + else if (!strcmp(arg, "auto")) + cpu_mitigations = CPU_MITIGATIONS_AUTO; + else if (!strcmp(arg, "auto,nosmt")) + cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + + return 0; +} +early_param("mitigations", mitigations_parse_cmdline); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index a06ba3013b3b..83d711f8d665 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -38,6 +38,9 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL bool +config ARCH_HAS_DMA_PREP_COHERENT + bool + config ARCH_HAS_DMA_COHERENT_TO_PFN bool @@ -57,6 +60,7 @@ config SWIOTLB config DMA_REMAP depends on MMU + select GENERIC_ALLOCATOR bool config DMA_DIRECT_REMAP diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 45d51e8e26f6..badd77670d00 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -89,8 +89,8 @@ struct dma_debug_entry { int sg_mapped_ents; enum map_err_types map_err_type; #ifdef CONFIG_STACKTRACE - struct stack_trace stacktrace; - unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; + unsigned int stack_len; + unsigned long stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; #endif }; @@ -174,7 +174,7 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry) #ifdef CONFIG_STACKTRACE if (entry) { pr_warning("Mapped at:\n"); - print_stack_trace(&entry->stacktrace, 0); + stack_trace_print(entry->stack_entries, entry->stack_len, 0); } #endif } @@ -704,12 +704,10 @@ static struct dma_debug_entry *dma_entry_alloc(void) spin_unlock_irqrestore(&free_entries_lock, flags); #ifdef CONFIG_STACKTRACE - entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES; - entry->stacktrace.entries = entry->st_entries; - entry->stacktrace.skip = 2; - save_stack_trace(&entry->stacktrace); + entry->stack_len = stack_trace_save(entry->stack_entries, + ARRAY_SIZE(entry->stack_entries), + 1); #endif - return entry; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index fcdb23e8d2fc..2c2772e9702a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -311,7 +311,7 @@ static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, size_t size) { return swiotlb_force != SWIOTLB_FORCE && - (!dev || dma_capable(dev, dma_addr, size)); + dma_capable(dev, dma_addr, size); } dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index c000906348c9..f7afdadb6770 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -238,17 +238,13 @@ u64 dma_get_required_mask(struct device *dev) } EXPORT_SYMBOL_GPL(dma_get_required_mask); -#ifndef arch_dma_alloc_attrs -#define arch_dma_alloc_attrs(dev) (true) -#endif - void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; - WARN_ON_ONCE(dev && !dev->coherent_dma_mask); + WARN_ON_ONCE(!dev->coherent_dma_mask); if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) return cpu_addr; @@ -256,9 +252,6 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, /* let the implementation decide on the zone to allocate from: */ flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); - if (!arch_dma_alloc_attrs(&dev)) - return NULL; - if (dma_is_direct(ops)) cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs); else if (ops->alloc) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 53012db1e53c..6f7619c1f877 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -452,6 +452,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, unsigned long mask; unsigned long offset_slots; unsigned long max_slots; + unsigned long tmp_io_tlb_used; if (no_iotlb_memory) panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); @@ -538,9 +539,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, } while (index != wrap); not_found: + tmp_io_tlb_used = io_tlb_used; + spin_unlock_irqrestore(&io_tlb_lock, flags); if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) - dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size); + dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", + size, io_tlb_nslabs, tmp_io_tlb_used); return DMA_MAPPING_ERROR; found: io_tlb_used += nslots; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1032a16bd186..abbd4b3b96c2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event, event->pmu->del(event, 0); event->oncpu = -1; - if (event->pending_disable) { - event->pending_disable = 0; + if (READ_ONCE(event->pending_disable) >= 0) { + WRITE_ONCE(event->pending_disable, -1); state = PERF_EVENT_STATE_OFF; } perf_event_set_state(event, state); @@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable); void perf_event_disable_inatomic(struct perf_event *event) { - event->pending_disable = 1; + WRITE_ONCE(event->pending_disable, smp_processor_id()); + /* can fail, see perf_pending_event_disable() */ irq_work_queue(&event->pending); } @@ -2477,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, perf_pmu_enable(cpuctx->ctx.pmu); } +void perf_pmu_resched(struct pmu *pmu) +{ + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); + perf_ctx_unlock(cpuctx, task_ctx); +} + /* * Cross CPU call to install and enable a performance event * @@ -5810,10 +5821,45 @@ void perf_event_wakeup(struct perf_event *event) } } +static void perf_pending_event_disable(struct perf_event *event) +{ + int cpu = READ_ONCE(event->pending_disable); + + if (cpu < 0) + return; + + if (cpu == smp_processor_id()) { + WRITE_ONCE(event->pending_disable, -1); + perf_event_disable_local(event); + return; + } + + /* + * CPU-A CPU-B + * + * perf_event_disable_inatomic() + * @pending_disable = CPU-A; + * irq_work_queue(); + * + * sched-out + * @pending_disable = -1; + * + * sched-in + * perf_event_disable_inatomic() + * @pending_disable = CPU-B; + * irq_work_queue(); // FAILS + * + * irq_work_run() + * perf_pending_event() + * + * But the event runs on CPU-B and wants disabling there. + */ + irq_work_queue_on(&event->pending, cpu); +} + static void perf_pending_event(struct irq_work *entry) { - struct perf_event *event = container_of(entry, - struct perf_event, pending); + struct perf_event *event = container_of(entry, struct perf_event, pending); int rctx; rctx = perf_swevent_get_recursion_context(); @@ -5822,10 +5868,7 @@ static void perf_pending_event(struct irq_work *entry) * and we won't recurse 'further'. */ - if (event->pending_disable) { - event->pending_disable = 0; - perf_event_disable_local(event); - } + perf_pending_event_disable(event); if (event->pending_wakeup) { event->pending_wakeup = 0; @@ -7189,6 +7232,7 @@ static void perf_event_mmap_output(struct perf_event *event, struct perf_output_handle handle; struct perf_sample_data sample; int size = mmap_event->event_id.header.size; + u32 type = mmap_event->event_id.header.type; int ret; if (!perf_event_mmap_match(event, data)) @@ -7232,6 +7276,7 @@ static void perf_event_mmap_output(struct perf_event *event, perf_output_end(&handle); out: mmap_event->event_id.header.size = size; + mmap_event->event_id.header.type = type; } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) @@ -9042,26 +9087,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (task == TASK_TOMBSTONE) return; - if (!ifh->nr_file_filters) - return; - - mm = get_task_mm(event->ctx->task); - if (!mm) - goto restart; + if (ifh->nr_file_filters) { + mm = get_task_mm(event->ctx->task); + if (!mm) + goto restart; - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); + } raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - event->addr_filter_ranges[count].start = 0; - event->addr_filter_ranges[count].size = 0; + if (filter->path.dentry) { + /* + * Adjust base offset if the filter is associated to a + * binary that needs to be mapped: + */ + event->addr_filter_ranges[count].start = 0; + event->addr_filter_ranges[count].size = 0; - /* - * Adjust base offset if the filter is associated to a binary - * that needs to be mapped: - */ - if (filter->path.dentry) perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]); + } else { + event->addr_filter_ranges[count].start = filter->offset; + event->addr_filter_ranges[count].size = filter->size; + } count++; } @@ -9069,9 +9117,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) event->addr_filters_gen++; raw_spin_unlock_irqrestore(&ifh->lock, flags); - up_read(&mm->mmap_sem); + if (ifh->nr_file_filters) { + up_read(&mm->mmap_sem); - mmput(mm); + mmput(mm); + } restart: perf_event_stop(event, 1); @@ -10234,6 +10284,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_waitqueue_head(&event->waitq); + event->pending_disable = -1; init_irq_work(&event->pending, perf_pending_event); mutex_init(&event->mmap_mutex); @@ -11876,7 +11927,7 @@ static void __init perf_event_init_all_cpus(void) } } -void perf_swevent_init_cpu(unsigned int cpu) +static void perf_swevent_init_cpu(unsigned int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index a4047321d7d8..674b35383491 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * store that will be enabled on successful return */ if (!handle->size) { /* A, matches D */ - event->pending_disable = 1; + event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); local_set(&rb->aux_nest, 0); goto err_put; @@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; } - if (size || handle->aux_flags) { - /* - * Only send RECORD_AUX if we have something useful to communicate - * - * Note: the OVERWRITE records by themselves are not considered - * useful, as they don't communicate any *new* information, - * aside from the short-lived offset, that becomes history at - * the next event sched-in and therefore isn't useful. - * The userspace that needs to copy out AUX data in overwrite - * mode should know to use user_page::aux_head for the actual - * offset. So, from now on we don't output AUX records that - * have *only* OVERWRITE flag set. - */ - - if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE) - perf_event_aux_event(handle->event, aux_head, size, - handle->aux_flags); - } + /* + * Only send RECORD_AUX if we have something useful to communicate + * + * Note: the OVERWRITE records by themselves are not considered + * useful, as they don't communicate any *new* information, + * aside from the short-lived offset, that becomes history at + * the next event sched-in and therefore isn't useful. + * The userspace that needs to copy out AUX data in overwrite + * mode should know to use user_page::aux_head for the actual + * offset. So, from now on we don't output AUX records that + * have *only* OVERWRITE flag set. + */ + if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + perf_event_aux_event(handle->event, aux_head, size, + handle->aux_flags); rb->user_page->aux_head = rb->aux_head; if (rb_need_aux_wakeup(rb)) @@ -480,7 +477,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) - handle->event->pending_disable = 1; + handle->event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); } @@ -613,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, * PMU requests more than one contiguous chunks of memory * for SW double buffering */ - if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) && - !overwrite) { + if (!overwrite) { if (!max_order) return -EINVAL; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c5cde87329c7..4ca7364c956d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2028,7 +2028,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) if (uc->handler) { rc = uc->handler(uc, regs); WARN(rc & ~UPROBE_HANDLER_MASK, - "bad rc=0x%x from %pf()\n", rc, uc->handler); + "bad rc=0x%x from %ps()\n", rc, uc->handler); } if (uc->ret_handler) @@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = { .priority = INT_MAX-1, /* notified after kprobes, kgdb */ }; -static int __init init_uprobes(void) +void __init uprobes_init(void) { int i; for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); - if (percpu_init_rwsem(&dup_mmap_sem)) - return -ENOMEM; + BUG_ON(percpu_init_rwsem(&dup_mmap_sem)); - return register_die_notifier(&uprobe_exception_nb); + BUG_ON(register_die_notifier(&uprobe_exception_nb)); } -__initcall(init_uprobes); diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 17f75b545f66..feb80712b913 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -210,7 +210,7 @@ static int fei_seq_show(struct seq_file *m, void *v) { struct fei_attr *attr = list_entry(v, struct fei_attr, list); - seq_printf(m, "%pf\n", attr->kp.addr); + seq_printf(m, "%ps\n", attr->kp.addr); return 0; } diff --git a/kernel/fork.c b/kernel/fork.c index 9dcd18aa210b..8b03d93ba068 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -11,6 +11,7 @@ * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ +#include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> @@ -21,6 +22,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> +#include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> @@ -815,6 +817,7 @@ void __init fork_init(void) #endif lockdep_init_task(&init_task); + uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, @@ -1298,13 +1301,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) complete_vfork_done(tsk); } -/* - * Allocate a new mm structure and copy contents from the - * mm structure of the passed in task structure. +/** + * dup_mm() - duplicates an existing mm structure + * @tsk: the task_struct with which the new mm will be associated. + * @oldmm: the mm to duplicate. + * + * Allocates a new mm structure and duplicates the provided @oldmm structure + * content into it. + * + * Return: the duplicated mm or NULL on failure. */ -static struct mm_struct *dup_mm(struct task_struct *tsk) +static struct mm_struct *dup_mm(struct task_struct *tsk, + struct mm_struct *oldmm) { - struct mm_struct *mm, *oldmm = current->mm; + struct mm_struct *mm; int err; mm = allocate_mm(); @@ -1371,7 +1381,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) } retval = -ENOMEM; - mm = dup_mm(tsk); + mm = dup_mm(tsk, current->mm); if (!mm) goto fail_nomem; @@ -1662,6 +1672,58 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_RCU */ } +static int pidfd_release(struct inode *inode, struct file *file) +{ + struct pid *pid = file->private_data; + + file->private_data = NULL; + put_pid(pid); + return 0; +} + +#ifdef CONFIG_PROC_FS +static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct pid_namespace *ns = proc_pid_ns(file_inode(m->file)); + struct pid *pid = f->private_data; + + seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns)); + seq_putc(m, '\n'); +} +#endif + +const struct file_operations pidfd_fops = { + .release = pidfd_release, +#ifdef CONFIG_PROC_FS + .show_fdinfo = pidfd_show_fdinfo, +#endif +}; + +/** + * pidfd_create() - Create a new pid file descriptor. + * + * @pid: struct pid that the pidfd will reference + * + * This creates a new pid file descriptor with the O_CLOEXEC flag set. + * + * Note, that this function can only be called after the fd table has + * been unshared to avoid leaking the pidfd to the new process. + * + * Return: On success, a cloexec pidfd is returned. + * On error, a negative errno number will be returned. + */ +static int pidfd_create(struct pid *pid) +{ + int fd; + + fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), + O_RDWR | O_CLOEXEC); + if (fd < 0) + put_pid(pid); + + return fd; +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -1674,13 +1736,14 @@ static __latent_entropy struct task_struct *copy_process( unsigned long clone_flags, unsigned long stack_start, unsigned long stack_size, + int __user *parent_tidptr, int __user *child_tidptr, struct pid *pid, int trace, unsigned long tls, int node) { - int retval; + int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; @@ -1730,6 +1793,31 @@ static __latent_entropy struct task_struct *copy_process( return ERR_PTR(-EINVAL); } + if (clone_flags & CLONE_PIDFD) { + int reserved; + + /* + * - CLONE_PARENT_SETTID is useless for pidfds and also + * parent_tidptr is used to return pidfds. + * - CLONE_DETACHED is blocked so that we can potentially + * reuse it later for CLONE_PIDFD. + * - CLONE_THREAD is blocked until someone really needs it. + */ + if (clone_flags & + (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD)) + return ERR_PTR(-EINVAL); + + /* + * Verify that parent_tidptr is sane so we can potentially + * reuse it later. + */ + if (get_user(reserved, parent_tidptr)) + return ERR_PTR(-EFAULT); + + if (reserved != 0) + return ERR_PTR(-EINVAL); + } + /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple @@ -1936,6 +2024,22 @@ static __latent_entropy struct task_struct *copy_process( } } + /* + * This has to happen after we've potentially unshared the file + * descriptor table (so that the pidfd doesn't leak into the child + * if the fd table isn't shared). + */ + if (clone_flags & CLONE_PIDFD) { + retval = pidfd_create(pid); + if (retval < 0) + goto bad_fork_free_pid; + + pidfd = retval; + retval = put_user(pidfd, parent_tidptr); + if (retval) + goto bad_fork_put_pidfd; + } + #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1996,7 +2100,7 @@ static __latent_entropy struct task_struct *copy_process( */ retval = cgroup_can_fork(p); if (retval) - goto bad_fork_free_pid; + goto bad_fork_put_pidfd; /* * From this point on we must avoid any synchronous user-space @@ -2111,6 +2215,9 @@ bad_fork_cancel_cgroup: spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); +bad_fork_put_pidfd: + if (clone_flags & CLONE_PIDFD) + ksys_close(pidfd); bad_fork_free_pid: cgroup_threadgroup_change_end(current); if (pid != &init_struct_pid) @@ -2176,7 +2283,7 @@ static inline void init_idle_pids(struct task_struct *idle) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0, + task = copy_process(CLONE_VM, 0, 0, NULL, NULL, &init_struct_pid, 0, 0, cpu_to_node(cpu)); if (!IS_ERR(task)) { init_idle_pids(task); @@ -2186,6 +2293,11 @@ struct task_struct *fork_idle(int cpu) return task; } +struct mm_struct *copy_init_mm(void) +{ + return dup_mm(NULL, &init_mm); +} + /* * Ok, this is the main fork-routine. * @@ -2223,7 +2335,7 @@ long _do_fork(unsigned long clone_flags, trace = 0; } - p = copy_process(clone_flags, stack_start, stack_size, + p = copy_process(clone_flags, stack_start, stack_size, parent_tidptr, child_tidptr, NULL, trace, tls, NUMA_NO_NODE); add_latent_entropy(); diff --git a/kernel/futex.c b/kernel/futex.c index c3b73b0311bc..6262f1534ac9 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1311,13 +1311,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval, static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) { + int err; u32 uninitialized_var(curval); if (unlikely(should_fail_futex(true))) return -EFAULT; - if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) - return -EFAULT; + err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (unlikely(err)) + return err; /* If user space value changed, let the caller retry */ return curval != uval ? -EAGAIN : 0; @@ -1502,10 +1504,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ if (unlikely(should_fail_futex(true))) ret = -EFAULT; - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) { - ret = -EFAULT; - - } else if (curval != uval) { + ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (!ret && (curval != uval)) { /* * If a unconditional UNLOCK_PI operation (user space did not * try the TID->0 transition) raced with a waiter setting the @@ -1700,32 +1700,32 @@ retry_private: double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { - double_unlock_hb(hb1, hb2); -#ifndef CONFIG_MMU - /* - * we don't get EFAULT from MMU faults if we don't have an MMU, - * but we might get them from range checking - */ - ret = op_ret; - goto out_put_keys; -#endif - - if (unlikely(op_ret != -EFAULT)) { + if (!IS_ENABLED(CONFIG_MMU) || + unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { + /* + * we don't get EFAULT from MMU faults if we don't have + * an MMU, but we might get them from range checking + */ ret = op_ret; goto out_put_keys; } - ret = fault_in_user_writeable(uaddr2); - if (ret) - goto out_put_keys; + if (op_ret == -EFAULT) { + ret = fault_in_user_writeable(uaddr2); + if (ret) + goto out_put_keys; + } - if (!(flags & FLAGS_SHARED)) + if (!(flags & FLAGS_SHARED)) { + cond_resched(); goto retry_private; + } put_futex_key(&key2); put_futex_key(&key1); + cond_resched(); goto retry; } @@ -2350,7 +2350,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, u32 uval, uninitialized_var(curval), newval; struct task_struct *oldowner, *newowner; u32 newtid; - int ret; + int ret, err = 0; lockdep_assert_held(q->lock_ptr); @@ -2421,14 +2421,17 @@ retry: if (!pi_state->owner) newtid |= FUTEX_OWNER_DIED; - if (get_futex_value_locked(&uval, uaddr)) - goto handle_fault; + err = get_futex_value_locked(&uval, uaddr); + if (err) + goto handle_err; for (;;) { newval = (uval & FUTEX_OWNER_DIED) | newtid; - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) - goto handle_fault; + err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); + if (err) + goto handle_err; + if (curval == uval) break; uval = curval; @@ -2456,23 +2459,37 @@ retry: return 0; /* - * To handle the page fault we need to drop the locks here. That gives - * the other task (either the highest priority waiter itself or the - * task which stole the rtmutex) the chance to try the fixup of the - * pi_state. So once we are back from handling the fault we need to - * check the pi_state after reacquiring the locks and before trying to - * do another fixup. When the fixup has been done already we simply - * return. + * In order to reschedule or handle a page fault, we need to drop the + * locks here. In the case of a fault, this gives the other task + * (either the highest priority waiter itself or the task which stole + * the rtmutex) the chance to try the fixup of the pi_state. So once we + * are back from handling the fault we need to check the pi_state after + * reacquiring the locks and before trying to do another fixup. When + * the fixup has been done already we simply return. * * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely * drop hb->lock since the caller owns the hb -> futex_q relation. * Dropping the pi_mutex->wait_lock requires the state revalidate. */ -handle_fault: +handle_err: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(q->lock_ptr); - ret = fault_in_user_writeable(uaddr); + switch (err) { + case -EFAULT: + ret = fault_in_user_writeable(uaddr); + break; + + case -EAGAIN: + cond_resched(); + ret = 0; + break; + + default: + WARN_ON_ONCE(1); + ret = err; + break; + } spin_lock(q->lock_ptr); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); @@ -3041,10 +3058,8 @@ retry: * A unconditional UNLOCK_PI op raced against a waiter * setting the FUTEX_WAITERS bit. Try again. */ - if (ret == -EAGAIN) { - put_futex_key(&key); - goto retry; - } + if (ret == -EAGAIN) + goto pi_retry; /* * wake_futex_pi has detected invalid state. Tell user * space. @@ -3059,9 +3074,19 @@ retry: * preserve the WAITERS bit not the OWNER_DIED one. We are the * owner. */ - if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) { + if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) { spin_unlock(&hb->lock); - goto pi_faulted; + switch (ret) { + case -EFAULT: + goto pi_faulted; + + case -EAGAIN: + goto pi_retry; + + default: + WARN_ON_ONCE(1); + goto out_putkey; + } } /* @@ -3075,6 +3100,11 @@ out_putkey: put_futex_key(&key); return ret; +pi_retry: + put_futex_key(&key); + cond_resched(); + goto retry; + pi_faulted: put_futex_key(&key); @@ -3435,47 +3465,67 @@ err_unlock: static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { u32 uval, uninitialized_var(nval), mval; + int err; + + /* Futex address must be 32bit aligned */ + if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) + return -1; retry: if (get_user(uval, uaddr)) return -1; - if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) { - /* - * Ok, this dying thread is truly holding a futex - * of interest. Set the OWNER_DIED bit atomically - * via cmpxchg, and if the value had FUTEX_WAITERS - * set, wake up a waiter (if any). (We have to do a - * futex_wake() even if OWNER_DIED is already set - - * to handle the rare but possible case of recursive - * thread-death.) The rest of the cleanup is done in - * userspace. - */ - mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; - /* - * We are not holding a lock here, but we want to have - * the pagefault_disable/enable() protection because - * we want to handle the fault gracefully. If the - * access fails we try to fault in the futex with R/W - * verification via get_user_pages. get_user() above - * does not guarantee R/W access. If that fails we - * give up and leave the futex locked. - */ - if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) { + if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) + return 0; + + /* + * Ok, this dying thread is truly holding a futex + * of interest. Set the OWNER_DIED bit atomically + * via cmpxchg, and if the value had FUTEX_WAITERS + * set, wake up a waiter (if any). (We have to do a + * futex_wake() even if OWNER_DIED is already set - + * to handle the rare but possible case of recursive + * thread-death.) The rest of the cleanup is done in + * userspace. + */ + mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; + + /* + * We are not holding a lock here, but we want to have + * the pagefault_disable/enable() protection because + * we want to handle the fault gracefully. If the + * access fails we try to fault in the futex with R/W + * verification via get_user_pages. get_user() above + * does not guarantee R/W access. If that fails we + * give up and leave the futex locked. + */ + if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) { + switch (err) { + case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; - } - if (nval != uval) + + case -EAGAIN: + cond_resched(); goto retry; - /* - * Wake robust non-PI futexes here. The wakeup of - * PI futexes happens in exit_pi_state(): - */ - if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + default: + WARN_ON_ONCE(1); + return err; + } } + + if (nval != uval) + goto retry; + + /* + * Wake robust non-PI futexes here. The wakeup of + * PI futexes happens in exit_pi_state(): + */ + if (!pi && (uval & FUTEX_WAITERS)) + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + return 0; } diff --git a/kernel/gen_ikh_data.sh b/kernel/gen_ikh_data.sh new file mode 100755 index 000000000000..591a94f7b387 --- /dev/null +++ b/kernel/gen_ikh_data.sh @@ -0,0 +1,89 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This script generates an archive consisting of kernel headers +# for CONFIG_IKHEADERS_PROC. +set -e +spath="$(dirname "$(readlink -f "$0")")" +kroot="$spath/.." +outdir="$(pwd)" +tarfile=$1 +cpio_dir=$outdir/$tarfile.tmp + +# Script filename relative to the kernel source root +# We add it to the archive because it is small and any changes +# to this script will also cause a rebuild of the archive. +sfile="$(realpath --relative-to $kroot "$(readlink -f "$0")")" + +src_file_list=" +include/ +arch/$SRCARCH/include/ +$sfile +" + +obj_file_list=" +include/ +arch/$SRCARCH/include/ +" + +# Support incremental builds by skipping archive generation +# if timestamps of files being archived are not changed. + +# This block is useful for debugging the incremental builds. +# Uncomment it for debugging. +# iter=1 +# if [ ! -f /tmp/iter ]; then echo 1 > /tmp/iter; +# else; iter=$(($(cat /tmp/iter) + 1)); fi +# find $src_file_list -type f | xargs ls -lR > /tmp/src-ls-$iter +# find $obj_file_list -type f | xargs ls -lR > /tmp/obj-ls-$iter + +# include/generated/compile.h is ignored because it is touched even when none +# of the source files changed. This causes pointless regeneration, so let us +# ignore them for md5 calculation. +pushd $kroot > /dev/null +src_files_md5="$(find $src_file_list -type f | + grep -v "include/generated/compile.h" | + xargs ls -lR | md5sum | cut -d ' ' -f1)" +popd > /dev/null +obj_files_md5="$(find $obj_file_list -type f | + grep -v "include/generated/compile.h" | + xargs ls -lR | md5sum | cut -d ' ' -f1)" + +if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi +if [ -f kernel/kheaders.md5 ] && + [ "$(cat kernel/kheaders.md5|head -1)" == "$src_files_md5" ] && + [ "$(cat kernel/kheaders.md5|head -2|tail -1)" == "$obj_files_md5" ] && + [ "$(cat kernel/kheaders.md5|tail -1)" == "$tarfile_md5" ]; then + exit +fi + +if [ "${quiet}" != "silent_" ]; then + echo " GEN $tarfile" +fi + +rm -rf $cpio_dir +mkdir $cpio_dir + +pushd $kroot > /dev/null +for f in $src_file_list; + do find "$f" ! -name "*.cmd" ! -name ".*"; +done | cpio --quiet -pd $cpio_dir +popd > /dev/null + +# The second CPIO can complain if files already exist which can +# happen with out of tree builds. Just silence CPIO for now. +for f in $obj_file_list; + do find "$f" ! -name "*.cmd" ! -name ".*"; +done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 + +# Remove comments except SDPX lines +find $cpio_dir -type f -print0 | + xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' + +tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null + +echo "$src_files_md5" > kernel/kheaders.md5 +echo "$obj_files_md5" >> kernel/kheaders.md5 +echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5 + +rm -rf $cpio_dir diff --git a/kernel/iomem.c b/kernel/iomem.c index f7525e14ebc6..93c264444510 100644 --- a/kernel/iomem.c +++ b/kernel/iomem.c @@ -55,7 +55,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size, * * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. - * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM + * Moreover, if MEMREMAP_WB is specified and the requested remap region is RAM * memremap() will bypass establishing a new mapping and instead return * a pointer into the direct map. * @@ -86,7 +86,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) /* Try all mapping types requested until one returns non-NULL */ if (flags & MEMREMAP_WB) { /* - * MEMREMAP_WB is special in that it can be satisifed + * MEMREMAP_WB is special in that it can be satisfied * from the direct map. Some archs depend on the * capability of memremap() to autodetect cases where * the requested range is potentially in System RAM. diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 3faef4a77f71..51128bea3846 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1449,6 +1449,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info) int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; + + if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on); diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 516c00a5e867..c1eccd4f6520 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -152,7 +152,7 @@ static int irq_debug_show(struct seq_file *m, void *p) raw_spin_lock_irq(&desc->lock); data = irq_desc_get_irq_data(desc); - seq_printf(m, "handler: %pf\n", desc->handle_irq); + seq_printf(m, "handler: %ps\n", desc->handle_irq); seq_printf(m, "device: %s\n", desc->dev_name); seq_printf(m, "status: 0x%08x\n", desc->status_use_accessors); irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states, diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 5d5378ea0afe..f6e5515ee077 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -84,8 +84,6 @@ EXPORT_SYMBOL(devm_request_threaded_irq); * @dev: device to request interrupt for * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs - * @thread_fn: function to be called in a threaded interrupt context. NULL - * for devices which handle everything in @handler * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device, dev_name(dev) if NULL * @dev_id: A cookie passed back to the handler function @@ -222,9 +220,8 @@ devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct, irq_flow_handler_t handler) { struct irq_chip_generic *gc; - unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); - gc = devm_kzalloc(dev, sz, GFP_KERNEL); + gc = devm_kzalloc(dev, struct_size(gc, chip_types, num_ct), GFP_KERNEL); if (gc) irq_init_generic_chip(gc, name, num_ct, irq_base, reg_base, handler); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 6df5ddfdb0f8..a4ace611f47f 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -149,7 +149,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags res = action->handler(irq, action->dev_id); trace_irq_handler_exit(irq, action, res); - if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n", + if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pS enabled interrupts\n", irq, action->handler)) local_irq_disable(); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 13539e12cd80..c52b737ab8e3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -275,11 +275,12 @@ static struct attribute *irq_attrs[] = { &actions_attr.attr, NULL }; +ATTRIBUTE_GROUPS(irq); static struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, - .default_attrs = irq_attrs, + .default_groups = irq_groups, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) @@ -558,6 +559,7 @@ int __init early_irq_init(void) alloc_masks(&desc[i], node); raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + mutex_init(&desc[i].request_mutex); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9ec34a2a6638..78f3ddeb7fe4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -196,6 +196,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); + /* fall through */ case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); @@ -356,8 +357,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) desc->affinity_notify = notify; raw_spin_unlock_irqrestore(&desc->lock, flags); - if (old_notify) + if (old_notify) { + cancel_work_sync(&old_notify->work); kref_put(&old_notify->kref, old_notify->release); + } return 0; } @@ -778,7 +781,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags) ret = 0; break; default: - pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n", + pr_err("Setting trigger mode %lu for irq %u failed (%pS)\n", flags, irq_desc_get_irq(desc), chip->irq_set_type); } if (unmask) diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 6d2fa6914b30..2ed97a7c9b2a 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -212,9 +212,9 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret) */ raw_spin_lock_irqsave(&desc->lock, flags); for_each_action_of_desc(desc, action) { - printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); + printk(KERN_ERR "[<%p>] %ps", action->handler, action->handler); if (action->thread_fn) - printk(KERN_CONT " threaded [<%p>] %pf", + printk(KERN_CONT " threaded [<%p>] %ps", action->thread_fn, action->thread_fn); printk(KERN_CONT "\n"); } diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index 1e4cb63a5c82..90c735da15d0 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -9,6 +9,7 @@ #include <linux/idr.h> #include <linux/irq.h> #include <linux/math64.h> +#include <linux/log2.h> #include <trace/events/irq.h> @@ -18,16 +19,6 @@ DEFINE_STATIC_KEY_FALSE(irq_timing_enabled); DEFINE_PER_CPU(struct irq_timings, irq_timings); -struct irqt_stat { - u64 next_evt; - u64 last_ts; - u64 variance; - u32 avg; - u32 nr_samples; - int anomalies; - int valid; -}; - static DEFINE_IDR(irqt_stats); void irq_timings_enable(void) @@ -40,75 +31,360 @@ void irq_timings_disable(void) static_branch_disable(&irq_timing_enabled); } -/** - * irqs_update - update the irq timing statistics with a new timestamp +/* + * The main goal of this algorithm is to predict the next interrupt + * occurrence on the current CPU. + * + * Currently, the interrupt timings are stored in a circular array + * buffer every time there is an interrupt, as a tuple: the interrupt + * number and the associated timestamp when the event occurred <irq, + * timestamp>. + * + * For every interrupt occurring in a short period of time, we can + * measure the elapsed time between the occurrences for the same + * interrupt and we end up with a suite of intervals. The experience + * showed the interrupts are often coming following a periodic + * pattern. + * + * The objective of the algorithm is to find out this periodic pattern + * in a fastest way and use its period to predict the next irq event. + * + * When the next interrupt event is requested, we are in the situation + * where the interrupts are disabled and the circular buffer + * containing the timings is filled with the events which happened + * after the previous next-interrupt-event request. + * + * At this point, we read the circular buffer and we fill the irq + * related statistics structure. After this step, the circular array + * containing the timings is empty because all the values are + * dispatched in their corresponding buffers. + * + * Now for each interrupt, we can predict the next event by using the + * suffix array, log interval and exponential moving average + * + * 1. Suffix array + * + * Suffix array is an array of all the suffixes of a string. It is + * widely used as a data structure for compression, text search, ... + * For instance for the word 'banana', the suffixes will be: 'banana' + * 'anana' 'nana' 'ana' 'na' 'a' + * + * Usually, the suffix array is sorted but for our purpose it is + * not necessary and won't provide any improvement in the context of + * the solved problem where we clearly define the boundaries of the + * search by a max period and min period. + * + * The suffix array will build a suite of intervals of different + * length and will look for the repetition of each suite. If the suite + * is repeating then we have the period because it is the length of + * the suite whatever its position in the buffer. + * + * 2. Log interval + * + * We saw the irq timings allow to compute the interval of the + * occurrences for a specific interrupt. We can reasonibly assume the + * longer is the interval, the higher is the error for the next event + * and we can consider storing those interval values into an array + * where each slot in the array correspond to an interval at the power + * of 2 of the index. For example, index 12 will contain values + * between 2^11 and 2^12. + * + * At the end we have an array of values where at each index defines a + * [2^index - 1, 2 ^ index] interval values allowing to store a large + * number of values inside a small array. + * + * For example, if we have the value 1123, then we store it at + * ilog2(1123) = 10 index value. + * + * Storing those value at the specific index is done by computing an + * exponential moving average for this specific slot. For instance, + * for values 1800, 1123, 1453, ... fall under the same slot (10) and + * the exponential moving average is computed every time a new value + * is stored at this slot. + * + * 3. Exponential Moving Average + * + * The EMA is largely used to track a signal for stocks or as a low + * pass filter. The magic of the formula, is it is very simple and the + * reactivity of the average can be tuned with the factors called + * alpha. + * + * The higher the alphas are, the faster the average respond to the + * signal change. In our case, if a slot in the array is a big + * interval, we can have numbers with a big difference between + * them. The impact of those differences in the average computation + * can be tuned by changing the alpha value. + * + * + * -- The algorithm -- + * + * We saw the different processing above, now let's see how they are + * used together. + * + * For each interrupt: + * For each interval: + * Compute the index = ilog2(interval) + * Compute a new_ema(buffer[index], interval) + * Store the index in a circular buffer + * + * Compute the suffix array of the indexes + * + * For each suffix: + * If the suffix is reverse-found 3 times + * Return suffix + * + * Return Not found + * + * However we can not have endless suffix array to be build, it won't + * make sense and it will add an extra overhead, so we can restrict + * this to a maximum suffix length of 5 and a minimum suffix length of + * 2. The experience showed 5 is the majority of the maximum pattern + * period found for different devices. + * + * The result is a pattern finding less than 1us for an interrupt. * - * @irqs: an irqt_stat struct pointer - * @ts: the new timestamp + * Example based on real values: * - * The statistics are computed online, in other words, the code is - * designed to compute the statistics on a stream of values rather - * than doing multiple passes on the values to compute the average, - * then the variance. The integer division introduces a loss of - * precision but with an acceptable error margin regarding the results - * we would have with the double floating precision: we are dealing - * with nanosec, so big numbers, consequently the mantisse is - * negligeable, especially when converting the time in usec - * afterwards. + * Example 1 : MMC write/read interrupt interval: * - * The computation happens at idle time. When the CPU is not idle, the - * interrupts' timestamps are stored in the circular buffer, when the - * CPU goes idle and this routine is called, all the buffer's values - * are injected in the statistical model continuying to extend the - * statistics from the previous busy-idle cycle. + * 223947, 1240, 1384, 1386, 1386, + * 217416, 1236, 1384, 1386, 1387, + * 214719, 1241, 1386, 1387, 1384, + * 213696, 1234, 1384, 1386, 1388, + * 219904, 1240, 1385, 1389, 1385, + * 212240, 1240, 1386, 1386, 1386, + * 214415, 1236, 1384, 1386, 1387, + * 214276, 1234, 1384, 1388, ? * - * The observations showed a device will trigger a burst of periodic - * interrupts followed by one or two peaks of longer time, for - * instance when a SD card device flushes its cache, then the periodic - * intervals occur again. A one second inactivity period resets the - * stats, that gives us the certitude the statistical values won't - * exceed 1x10^9, thus the computation won't overflow. + * For each element, apply ilog2(value) * - * Basically, the purpose of the algorithm is to watch the periodic - * interrupts and eliminate the peaks. + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, ? * - * An interrupt is considered periodically stable if the interval of - * its occurences follow the normal distribution, thus the values - * comply with: + * Max period of 5, we take the last (max_period * 3) 15 elements as + * we can be confident if the pattern repeats itself three times it is + * a repeating pattern. * - * avg - 3 x stddev < value < avg + 3 x stddev + * 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, 8, + * 15, 8, 8, 8, ? * - * Which can be simplified to: + * Suffixes are: * - * -3 x stddev < value - avg < 3 x stddev + * 1) 8, 15, 8, 8, 8 <- max period + * 2) 8, 15, 8, 8 + * 3) 8, 15, 8 + * 4) 8, 15 <- min period * - * abs(value - avg) < 3 x stddev + * From there we search the repeating pattern for each suffix. * - * In order to save a costly square root computation, we use the - * variance. For the record, stddev = sqrt(variance). The equation - * above becomes: + * buffer: 8, 15, 8, 8, 8, 8, 15, 8, 8, 8, 8, 15, 8, 8, 8 + * | | | | | | | | | | | | | | | + * 8, 15, 8, 8, 8 | | | | | | | | | | + * 8, 15, 8, 8, 8 | | | | | + * 8, 15, 8, 8, 8 * - * abs(value - avg) < 3 x sqrt(variance) + * When moving the suffix, we found exactly 3 matches. * - * And finally we square it: + * The first suffix with period 5 is repeating. * - * (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2 + * The next event is (3 * max_period) % suffix_period * - * (value - avg) x (value - avg) < 9 x variance + * In this example, the result 0, so the next event is suffix[0] => 8 * - * Statistically speaking, any values out of this interval is - * considered as an anomaly and is discarded. However, a normal - * distribution appears when the number of samples is 30 (it is the - * rule of thumb in statistics, cf. "30 samples" on Internet). When - * there are three consecutive anomalies, the statistics are resetted. + * However, 8 is the index in the array of exponential moving average + * which was calculated on the fly when storing the values, so the + * interval is ema[8] = 1366 * + * + * Example 2: + * + * 4, 3, 5, 100, + * 3, 3, 5, 117, + * 4, 4, 5, 112, + * 4, 3, 4, 110, + * 3, 5, 3, 117, + * 4, 4, 5, 112, + * 4, 3, 4, 110, + * 3, 4, 5, 112, + * 4, 3, 4, 110 + * + * ilog2 + * + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4 + * + * Max period 5: + * 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4, + * 0, 0, 0, 4 + * + * Suffixes: + * + * 1) 0, 0, 4, 0, 0 + * 2) 0, 0, 4, 0 + * 3) 0, 0, 4 + * 4) 0, 0 + * + * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4 + * | | | | | | X + * 0, 0, 4, 0, 0, | X + * 0, 0 + * + * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4 + * | | | | | | | | | | | | | | | + * 0, 0, 4, 0, | | | | | | | | | | | + * 0, 0, 4, 0, | | | | | | | + * 0, 0, 4, 0, | | | + * 0 0 4 + * + * Pattern is found 3 times, the remaining is 1 which results from + * (max_period * 3) % suffix_period. This value is the index in the + * suffix arrays. The suffix array for a period 4 has the value 4 + * at index 1. + */ +#define EMA_ALPHA_VAL 64 +#define EMA_ALPHA_SHIFT 7 + +#define PREDICTION_PERIOD_MIN 2 +#define PREDICTION_PERIOD_MAX 5 +#define PREDICTION_FACTOR 4 +#define PREDICTION_MAX 10 /* 2 ^ PREDICTION_MAX useconds */ +#define PREDICTION_BUFFER_SIZE 16 /* slots for EMAs, hardly more than 16 */ + +struct irqt_stat { + u64 last_ts; + u64 ema_time[PREDICTION_BUFFER_SIZE]; + int timings[IRQ_TIMINGS_SIZE]; + int circ_timings[IRQ_TIMINGS_SIZE]; + int count; +}; + +/* + * Exponential moving average computation */ -static void irqs_update(struct irqt_stat *irqs, u64 ts) +static u64 irq_timings_ema_new(u64 value, u64 ema_old) +{ + s64 diff; + + if (unlikely(!ema_old)) + return value; + + diff = (value - ema_old) * EMA_ALPHA_VAL; + /* + * We can use a s64 type variable to be added with the u64 + * ema_old variable as this one will never have its topmost + * bit set, it will be always smaller than 2^63 nanosec + * interrupt interval (292 years). + */ + return ema_old + (diff >> EMA_ALPHA_SHIFT); +} + +static int irq_timings_next_event_index(int *buffer, size_t len, int period_max) +{ + int i; + + /* + * The buffer contains the suite of intervals, in a ilog2 + * basis, we are looking for a repetition. We point the + * beginning of the search three times the length of the + * period beginning at the end of the buffer. We do that for + * each suffix. + */ + for (i = period_max; i >= PREDICTION_PERIOD_MIN ; i--) { + + int *begin = &buffer[len - (i * 3)]; + int *ptr = begin; + + /* + * We look if the suite with period 'i' repeat + * itself. If it is truncated at the end, as it + * repeats we can use the period to find out the next + * element. + */ + while (!memcmp(ptr, begin, i * sizeof(*ptr))) { + ptr += i; + if (ptr >= &buffer[len]) + return begin[((i * 3) % i)]; + } + } + + return -1; +} + +static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now) +{ + int index, i, period_max, count, start, min = INT_MAX; + + if ((now - irqs->last_ts) >= NSEC_PER_SEC) { + irqs->count = irqs->last_ts = 0; + return U64_MAX; + } + + /* + * As we want to find three times the repetition, we need a + * number of intervals greater or equal to three times the + * maximum period, otherwise we truncate the max period. + */ + period_max = irqs->count > (3 * PREDICTION_PERIOD_MAX) ? + PREDICTION_PERIOD_MAX : irqs->count / 3; + + /* + * If we don't have enough irq timings for this prediction, + * just bail out. + */ + if (period_max <= PREDICTION_PERIOD_MIN) + return U64_MAX; + + /* + * 'count' will depends if the circular buffer wrapped or not + */ + count = irqs->count < IRQ_TIMINGS_SIZE ? + irqs->count : IRQ_TIMINGS_SIZE; + + start = irqs->count < IRQ_TIMINGS_SIZE ? + 0 : (irqs->count & IRQ_TIMINGS_MASK); + + /* + * Copy the content of the circular buffer into another buffer + * in order to linearize the buffer instead of dealing with + * wrapping indexes and shifted array which will be prone to + * error and extremelly difficult to debug. + */ + for (i = 0; i < count; i++) { + int index = (start + i) & IRQ_TIMINGS_MASK; + + irqs->timings[i] = irqs->circ_timings[index]; + min = min_t(int, irqs->timings[i], min); + } + + index = irq_timings_next_event_index(irqs->timings, count, period_max); + if (index < 0) + return irqs->last_ts + irqs->ema_time[min]; + + return irqs->last_ts + irqs->ema_time[index]; +} + +static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) { u64 old_ts = irqs->last_ts; - u64 variance = 0; u64 interval; - s64 diff; + int index; /* * The timestamps are absolute time values, we need to compute @@ -135,87 +411,28 @@ static void irqs_update(struct irqt_stat *irqs, u64 ts) * want as we need another timestamp to compute an interval. */ if (interval >= NSEC_PER_SEC) { - memset(irqs, 0, sizeof(*irqs)); - irqs->last_ts = ts; + irqs->count = 0; return; } /* - * Pre-compute the delta with the average as the result is - * used several times in this function. - */ - diff = interval - irqs->avg; - - /* - * Increment the number of samples. - */ - irqs->nr_samples++; - - /* - * Online variance divided by the number of elements if there - * is more than one sample. Normally the formula is division - * by nr_samples - 1 but we assume the number of element will be - * more than 32 and dividing by 32 instead of 31 is enough - * precise. - */ - if (likely(irqs->nr_samples > 1)) - variance = irqs->variance >> IRQ_TIMINGS_SHIFT; - - /* - * The rule of thumb in statistics for the normal distribution - * is having at least 30 samples in order to have the model to - * apply. Values outside the interval are considered as an - * anomaly. - */ - if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) { - /* - * After three consecutive anomalies, we reset the - * stats as it is no longer stable enough. - */ - if (irqs->anomalies++ >= 3) { - memset(irqs, 0, sizeof(*irqs)); - irqs->last_ts = ts; - return; - } - } else { - /* - * The anomalies must be consecutives, so at this - * point, we reset the anomalies counter. - */ - irqs->anomalies = 0; - } - - /* - * The interrupt is considered stable enough to try to predict - * the next event on it. + * Get the index in the ema table for this interrupt. The + * PREDICTION_FACTOR increase the interval size for the array + * of exponential average. */ - irqs->valid = 1; + index = likely(interval) ? + ilog2((interval >> 10) / PREDICTION_FACTOR) : 0; /* - * Online average algorithm: - * - * new_average = average + ((value - average) / count) - * - * The variance computation depends on the new average - * to be computed here first. - * + * Store the index as an element of the pattern in another + * circular array. */ - irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT); + irqs->circ_timings[irqs->count & IRQ_TIMINGS_MASK] = index; - /* - * Online variance algorithm: - * - * new_variance = variance + (value - average) x (value - new_average) - * - * Warning: irqs->avg is updated with the line above, hence - * 'interval - irqs->avg' is no longer equal to 'diff' - */ - irqs->variance = irqs->variance + (diff * (interval - irqs->avg)); + irqs->ema_time[index] = irq_timings_ema_new(interval, + irqs->ema_time[index]); - /* - * Update the next event - */ - irqs->next_evt = ts + irqs->avg; + irqs->count++; } /** @@ -259,6 +476,9 @@ u64 irq_timings_next_event(u64 now) */ lockdep_assert_irqs_disabled(); + if (!irqts->count) + return next_evt; + /* * Number of elements in the circular buffer: If it happens it * was flushed before, then the number of elements could be @@ -269,21 +489,19 @@ u64 irq_timings_next_event(u64 now) * type but with the cost of extra computation in the * interrupt handler hot path. We choose efficiency. * - * Inject measured irq/timestamp to the statistical model - * while decrementing the counter because we consume the data - * from our circular buffer. + * Inject measured irq/timestamp to the pattern prediction + * model while decrementing the counter because we consume the + * data from our circular buffer. */ - for (i = irqts->count & IRQ_TIMINGS_MASK, - irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count); - irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) { - irq = irq_timing_decode(irqts->values[i], &ts); + i = (irqts->count & IRQ_TIMINGS_MASK) - 1; + irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count); + for (; irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) { + irq = irq_timing_decode(irqts->values[i], &ts); s = idr_find(&irqt_stats, irq); - if (s) { - irqs = this_cpu_ptr(s); - irqs_update(irqs, ts); - } + if (s) + irq_timings_store(irq, this_cpu_ptr(s), ts); } /* @@ -294,26 +512,12 @@ u64 irq_timings_next_event(u64 now) irqs = this_cpu_ptr(s); - if (!irqs->valid) - continue; + ts = __irq_timings_next_event(irqs, i, now); + if (ts <= now) + return now; - if (irqs->next_evt <= now) { - irq = i; - next_evt = now; - - /* - * This interrupt mustn't use in the future - * until new events occur and update the - * statistics. - */ - irqs->valid = 0; - break; - } - - if (irqs->next_evt < next_evt) { - irq = i; - next_evt = irqs->next_evt; - } + if (ts < next_evt) + next_evt = ts; } return next_evt; diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 6b7cdf17ccf8..73288914ed5e 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -56,61 +56,70 @@ void __weak arch_irq_work_raise(void) */ } -/* - * Enqueue the irq_work @work on @cpu unless it's already pending - * somewhere. - * - * Can be re-enqueued while the callback is still in progress. - */ -bool irq_work_queue_on(struct irq_work *work, int cpu) +/* Enqueue on current CPU, work must already be claimed and preempt disabled */ +static void __irq_work_queue_local(struct irq_work *work) { - /* All work should have been flushed before going offline */ - WARN_ON_ONCE(cpu_is_offline(cpu)); - -#ifdef CONFIG_SMP - - /* Arch remote IPI send/receive backend aren't NMI safe */ - WARN_ON_ONCE(in_nmi()); + /* If the work is "lazy", handle it from next tick if any */ + if (work->flags & IRQ_WORK_LAZY) { + if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && + tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } else { + if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) + arch_irq_work_raise(); + } +} +/* Enqueue the irq work @work on the current CPU */ +bool irq_work_queue(struct irq_work *work) +{ /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; - if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) - arch_send_call_function_single_ipi(cpu); - -#else /* #ifdef CONFIG_SMP */ - irq_work_queue(work); -#endif /* #else #ifdef CONFIG_SMP */ + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + __irq_work_queue_local(work); + preempt_enable(); return true; } +EXPORT_SYMBOL_GPL(irq_work_queue); -/* Enqueue the irq work @work on the current CPU */ -bool irq_work_queue(struct irq_work *work) +/* + * Enqueue the irq_work @work on @cpu unless it's already pending + * somewhere. + * + * Can be re-enqueued while the callback is still in progress. + */ +bool irq_work_queue_on(struct irq_work *work, int cpu) { +#ifndef CONFIG_SMP + return irq_work_queue(work); + +#else /* CONFIG_SMP: */ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; - /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - - /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { - if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && - tick_nohz_tick_stopped()) - arch_irq_work_raise(); + if (cpu != smp_processor_id()) { + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); + if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) + arch_send_call_function_single_ipi(cpu); } else { - if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) - arch_irq_work_raise(); + __irq_work_queue_local(work); } - preempt_enable(); return true; +#endif /* CONFIG_SMP */ } -EXPORT_SYMBOL_GPL(irq_work_queue); + bool irq_work_needs_cpu(void) { diff --git a/kernel/jump_label.c b/kernel/jump_label.c index bad96b476eb6..de6efdecc70d 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -202,11 +202,13 @@ void static_key_disable(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_disable); -static void __static_key_slow_dec_cpuslocked(struct static_key *key, - unsigned long rate_limit, - struct delayed_work *work) +static bool static_key_slow_try_dec(struct static_key *key) { - lockdep_assert_cpus_held(); + int val; + + val = atomic_fetch_add_unless(&key->enabled, -1, 1); + if (val == 1) + return false; /* * The negative count check is valid even when a negative @@ -215,63 +217,70 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key, * returns is unbalanced, because all other static_key_slow_inc() * instances block while the update is in progress. */ - if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { - WARN(atomic_read(&key->enabled) < 0, - "jump label: negative count!\n"); + WARN(val < 0, "jump label: negative count!\n"); + return true; +} + +static void __static_key_slow_dec_cpuslocked(struct static_key *key) +{ + lockdep_assert_cpus_held(); + + if (static_key_slow_try_dec(key)) return; - } - if (rate_limit) { - atomic_inc(&key->enabled); - schedule_delayed_work(work, rate_limit); - } else { + jump_label_lock(); + if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); - } jump_label_unlock(); } -static void __static_key_slow_dec(struct static_key *key, - unsigned long rate_limit, - struct delayed_work *work) +static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); - __static_key_slow_dec_cpuslocked(key, rate_limit, work); + __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } -static void jump_label_update_timeout(struct work_struct *work) +void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); - __static_key_slow_dec(&key->key, 0, NULL); + __static_key_slow_dec(&key->key); } +EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); - __static_key_slow_dec(key, 0, NULL); + __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); - __static_key_slow_dec_cpuslocked(key, 0, NULL); + __static_key_slow_dec_cpuslocked(key); } -void static_key_slow_dec_deferred(struct static_key_deferred *key) +void __static_key_slow_dec_deferred(struct static_key *key, + struct delayed_work *work, + unsigned long timeout) { STATIC_KEY_CHECK_USE(key); - __static_key_slow_dec(&key->key, key->timeout, &key->work); + + if (static_key_slow_try_dec(key)) + return; + + schedule_delayed_work(work, timeout); } -EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); +EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); -void static_key_deferred_flush(struct static_key_deferred *key) +void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); - flush_delayed_work(&key->work); + flush_delayed_work(work); } -EXPORT_SYMBOL_GPL(static_key_deferred_flush); +EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d7140447be75..fd5c95ff9251 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1150,7 +1150,7 @@ int kernel_kexec(void) error = dpm_suspend_end(PMSG_FREEZE); if (error) goto Resume_devices; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); @@ -1183,7 +1183,7 @@ int kernel_kexec(void) Enable_irqs: local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); dpm_resume_start(PMSG_RESTORE); Resume_devices: dpm_resume_end(PMSG_RESTORE); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f1d0e00a3971..f7fb8f6a688f 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -688,7 +688,6 @@ static int kexec_calculate_store_digests(struct kimage *image) goto out_free_desc; desc->tfm = tfm; - desc->flags = 0; ret = crypto_shash_init(desc); if (ret < 0) diff --git a/kernel/kheaders.c b/kernel/kheaders.c new file mode 100644 index 000000000000..70ae6052920d --- /dev/null +++ b/kernel/kheaders.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel headers useful to build tracing programs + * such as for running eBPF tracing tools. + * + * (Borrowed code from kernel/configs.c) + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/uaccess.h> + +/* + * Define kernel_headers_data and kernel_headers_data_end, within which the + * compressed kernel headers are stored. The file is first compressed with xz. + */ + +asm ( +" .pushsection .rodata, \"a\" \n" +" .global kernel_headers_data \n" +"kernel_headers_data: \n" +" .incbin \"kernel/kheaders_data.tar.xz\" \n" +" .global kernel_headers_data_end \n" +"kernel_headers_data_end: \n" +" .popsection \n" +); + +extern char kernel_headers_data; +extern char kernel_headers_data_end; + +static ssize_t +ikheaders_read_current(struct file *file, char __user *buf, + size_t len, loff_t *offset) +{ + return simple_read_from_buffer(buf, len, offset, + &kernel_headers_data, + &kernel_headers_data_end - + &kernel_headers_data); +} + +static const struct file_operations ikheaders_file_ops = { + .read = ikheaders_read_current, + .llseek = default_llseek, +}; + +static int __init ikheaders_init(void) +{ + struct proc_dir_entry *entry; + + /* create the current headers file */ + entry = proc_create("kheaders.tar.xz", S_IRUGO, NULL, + &ikheaders_file_ops); + if (!entry) + return -ENOMEM; + + proc_set_size(entry, + &kernel_headers_data_end - + &kernel_headers_data); + return 0; +} + +static void __exit ikheaders_cleanup(void) +{ + remove_proc_entry("kheaders.tar.xz", NULL); +} + +module_init(ikheaders_init); +module_exit(ikheaders_cleanup); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Joel Fernandes"); +MODULE_DESCRIPTION("Echo the kernel header artifacts used to build the kernel"); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c83e54727131..b1ea30a5540e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; - int ret; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means @@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - ret = kprobe_optready(ap); - if (ret) - return ret; + if (!kprobe_optready(ap)) + return -EINVAL; optimize_kprobe(ap); return 0; diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 96b4179cee6a..99a5b5f46dc5 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -120,8 +120,8 @@ account_global_scheduler_latency(struct task_struct *tsk, break; } - /* 0 and ULONG_MAX entries mean end of backtrace: */ - if (record == 0 || record == ULONG_MAX) + /* 0 entry marks end of backtrace: */ + if (!record) break; } if (same) { @@ -141,20 +141,6 @@ account_global_scheduler_latency(struct task_struct *tsk, memcpy(&latency_record[i], lat, sizeof(struct latency_record)); } -/* - * Iterator to store a backtrace into a latency record entry - */ -static inline void store_stacktrace(struct task_struct *tsk, - struct latency_record *lat) -{ - struct stack_trace trace; - - memset(&trace, 0, sizeof(trace)); - trace.max_entries = LT_BACKTRACEDEPTH; - trace.entries = &lat->backtrace[0]; - save_stack_trace_tsk(tsk, &trace); -} - /** * __account_scheduler_latency - record an occurred latency * @tsk - the task struct of the task hitting the latency @@ -191,7 +177,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) lat.count = 1; lat.time = usecs; lat.max = usecs; - store_stacktrace(tsk, &lat); + + stack_trace_save_tsk(tsk, lat.backtrace, LT_BACKTRACEDEPTH, 0); raw_spin_lock_irqsave(&latency_lock, flags); @@ -210,8 +197,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) break; } - /* 0 and ULONG_MAX entries mean end of backtrace: */ - if (record == 0 || record == ULONG_MAX) + /* 0 entry is end of backtrace */ + if (!record) break; } if (same) { @@ -252,10 +239,10 @@ static int lstats_show(struct seq_file *m, void *v) lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; + if (!bt) break; - if (bt == ULONG_MAX) - break; + seq_printf(m, " %ps", (void *)bt); } seq_puts(m, "\n"); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index eb0ee10a1981..f6fbaff10e71 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -419,6 +419,7 @@ static struct attribute *klp_patch_attrs[] = { &force_kobj_attr.attr, NULL }; +ATTRIBUTE_GROUPS(klp_patch); static void klp_free_object_dynamic(struct klp_object *obj) { @@ -426,7 +427,13 @@ static void klp_free_object_dynamic(struct klp_object *obj) kfree(obj); } -static struct klp_object *klp_alloc_object_dynamic(const char *name) +static void klp_init_func_early(struct klp_object *obj, + struct klp_func *func); +static void klp_init_object_early(struct klp_patch *patch, + struct klp_object *obj); + +static struct klp_object *klp_alloc_object_dynamic(const char *name, + struct klp_patch *patch) { struct klp_object *obj; @@ -442,7 +449,7 @@ static struct klp_object *klp_alloc_object_dynamic(const char *name) } } - INIT_LIST_HEAD(&obj->func_list); + klp_init_object_early(patch, obj); obj->dynamic = true; return obj; @@ -471,6 +478,7 @@ static struct klp_func *klp_alloc_func_nop(struct klp_func *old_func, } } + klp_init_func_early(obj, func); /* * func->new_func is same as func->old_func. These addresses are * set when the object is loaded, see klp_init_object_loaded(). @@ -490,11 +498,9 @@ static int klp_add_object_nops(struct klp_patch *patch, obj = klp_find_object(patch, old_obj); if (!obj) { - obj = klp_alloc_object_dynamic(old_obj->name); + obj = klp_alloc_object_dynamic(old_obj->name, patch); if (!obj) return -ENOMEM; - - list_add_tail(&obj->node, &patch->obj_list); } klp_for_each_func(old_obj, old_func) { @@ -505,8 +511,6 @@ static int klp_add_object_nops(struct klp_patch *patch, func = klp_alloc_func_nop(old_func, obj); if (!func) return -ENOMEM; - - list_add_tail(&func->node, &obj->func_list); } return 0; @@ -546,7 +550,7 @@ static void klp_kobj_release_patch(struct kobject *kobj) static struct kobj_type klp_ktype_patch = { .release = klp_kobj_release_patch, .sysfs_ops = &kobj_sysfs_ops, - .default_attrs = klp_patch_attrs, + .default_groups = klp_patch_groups, }; static void klp_kobj_release_object(struct kobject *kobj) @@ -588,13 +592,7 @@ static void __klp_free_funcs(struct klp_object *obj, bool nops_only) continue; list_del(&func->node); - - /* Might be called from klp_init_patch() error path. */ - if (func->kobj_added) { - kobject_put(&func->kobj); - } else if (func->nop) { - klp_free_func_nop(func); - } + kobject_put(&func->kobj); } } @@ -624,13 +622,7 @@ static void __klp_free_objects(struct klp_patch *patch, bool nops_only) continue; list_del(&obj->node); - - /* Might be called from klp_init_patch() error path. */ - if (obj->kobj_added) { - kobject_put(&obj->kobj); - } else if (obj->dynamic) { - klp_free_object_dynamic(obj); - } + kobject_put(&obj->kobj); } } @@ -675,10 +667,8 @@ static void klp_free_patch_finish(struct klp_patch *patch) * this is called when the patch gets disabled and it * cannot get enabled again. */ - if (patch->kobj_added) { - kobject_put(&patch->kobj); - wait_for_completion(&patch->finish); - } + kobject_put(&patch->kobj); + wait_for_completion(&patch->finish); /* Put the module after the last access to struct klp_patch. */ if (!patch->forced) @@ -700,8 +690,6 @@ static void klp_free_patch_work_fn(struct work_struct *work) static int klp_init_func(struct klp_object *obj, struct klp_func *func) { - int ret; - if (!func->old_name) return -EINVAL; @@ -724,13 +712,9 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) * object. If the user selects 0 for old_sympos, then 1 will be used * since a unique symbol will be the first occurrence. */ - ret = kobject_init_and_add(&func->kobj, &klp_ktype_func, - &obj->kobj, "%s,%lu", func->old_name, - func->old_sympos ? func->old_sympos : 1); - if (!ret) - func->kobj_added = true; - - return ret; + return kobject_add(&func->kobj, &obj->kobj, "%s,%lu", + func->old_name, + func->old_sympos ? func->old_sympos : 1); } /* Arches may override this to finish any remaining arch-specific tasks */ @@ -801,11 +785,9 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) klp_find_object_module(obj); name = klp_is_module(obj) ? obj->name : "vmlinux"; - ret = kobject_init_and_add(&obj->kobj, &klp_ktype_object, - &patch->kobj, "%s", name); + ret = kobject_add(&obj->kobj, &patch->kobj, "%s", name); if (ret) return ret; - obj->kobj_added = true; klp_for_each_func(obj, func) { ret = klp_init_func(obj, func); @@ -819,6 +801,21 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) return ret; } +static void klp_init_func_early(struct klp_object *obj, + struct klp_func *func) +{ + kobject_init(&func->kobj, &klp_ktype_func); + list_add_tail(&func->node, &obj->func_list); +} + +static void klp_init_object_early(struct klp_patch *patch, + struct klp_object *obj) +{ + INIT_LIST_HEAD(&obj->func_list); + kobject_init(&obj->kobj, &klp_ktype_object); + list_add_tail(&obj->node, &patch->obj_list); +} + static int klp_init_patch_early(struct klp_patch *patch) { struct klp_object *obj; @@ -829,7 +826,7 @@ static int klp_init_patch_early(struct klp_patch *patch) INIT_LIST_HEAD(&patch->list); INIT_LIST_HEAD(&patch->obj_list); - patch->kobj_added = false; + kobject_init(&patch->kobj, &klp_ktype_patch); patch->enabled = false; patch->forced = false; INIT_WORK(&patch->free_work, klp_free_patch_work_fn); @@ -839,13 +836,10 @@ static int klp_init_patch_early(struct klp_patch *patch) if (!obj->funcs) return -EINVAL; - INIT_LIST_HEAD(&obj->func_list); - obj->kobj_added = false; - list_add_tail(&obj->node, &patch->obj_list); + klp_init_object_early(patch, obj); klp_for_each_func_static(obj, func) { - func->kobj_added = false; - list_add_tail(&func->node, &obj->func_list); + klp_init_func_early(obj, func); } } @@ -860,11 +854,9 @@ static int klp_init_patch(struct klp_patch *patch) struct klp_object *obj; int ret; - ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, - klp_root_kobj, "%s", patch->mod->name); + ret = kobject_add(&patch->kobj, klp_root_kobj, "%s", patch->mod->name); if (ret) return ret; - patch->kobj_added = true; if (patch->replace) { ret = klp_add_nops(patch); @@ -926,9 +918,6 @@ static int __klp_enable_patch(struct klp_patch *patch) if (WARN_ON(patch->enabled)) return -EINVAL; - if (!patch->kobj_added) - return -EINVAL; - pr_notice("enabling patch '%s'\n", patch->mod->name); klp_init_transition(patch, KLP_PATCHED); @@ -1003,11 +992,10 @@ int klp_enable_patch(struct klp_patch *patch) return -ENODEV; if (!klp_have_reliable_stack()) { - pr_err("This architecture doesn't have support for the livepatch consistency model.\n"); - return -EOPNOTSUPP; + pr_warn("This architecture doesn't have support for the livepatch consistency model.\n"); + pr_warn("The livepatch transition may never complete.\n"); } - mutex_lock(&klp_mutex); ret = klp_init_patch_early(patch); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 9c89ae8b337a..c53370d596be 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -202,15 +202,15 @@ void klp_update_patch_state(struct task_struct *task) * Determine whether the given stack trace includes any references to a * to-be-patched or to-be-unpatched function. */ -static int klp_check_stack_func(struct klp_func *func, - struct stack_trace *trace) +static int klp_check_stack_func(struct klp_func *func, unsigned long *entries, + unsigned int nr_entries) { unsigned long func_addr, func_size, address; struct klp_ops *ops; int i; - for (i = 0; i < trace->nr_entries; i++) { - address = trace->entries[i]; + for (i = 0; i < nr_entries; i++) { + address = entries[i]; if (klp_target_state == KLP_UNPATCHED) { /* @@ -254,29 +254,25 @@ static int klp_check_stack_func(struct klp_func *func, static int klp_check_stack(struct task_struct *task, char *err_buf) { static unsigned long entries[MAX_STACK_ENTRIES]; - struct stack_trace trace; struct klp_object *obj; struct klp_func *func; - int ret; + int ret, nr_entries; - trace.skip = 0; - trace.nr_entries = 0; - trace.max_entries = MAX_STACK_ENTRIES; - trace.entries = entries; - ret = save_stack_trace_tsk_reliable(task, &trace); + ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries)); WARN_ON_ONCE(ret == -ENOSYS); - if (ret) { + if (ret < 0) { snprintf(err_buf, STACK_ERR_BUF_SIZE, "%s: %s:%d has an unreliable stack\n", __func__, task->comm, task->pid); return ret; } + nr_entries = ret; klp_for_each_object(klp_transition_patch, obj) { if (!obj->patched) continue; klp_for_each_func(obj, func) { - ret = klp_check_stack_func(func, &trace); + ret = klp_check_stack_func(func, entries, nr_entries); if (ret) { snprintf(err_buf, STACK_ERR_BUF_SIZE, "%s: %s:%d is sleeping on function %s\n", diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 392c7f23af76..6fe2f333aecb 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -3,7 +3,7 @@ # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n -obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o +obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) @@ -25,8 +25,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o -obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o -obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o +obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o diff --git a/kernel/locking/lock_events.c b/kernel/locking/lock_events.c new file mode 100644 index 000000000000..fa2c2f951c6b --- /dev/null +++ b/kernel/locking/lock_events.c @@ -0,0 +1,179 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Waiman Long <waiman.long@hpe.com> + */ + +/* + * Collect locking event counts + */ +#include <linux/debugfs.h> +#include <linux/sched.h> +#include <linux/sched/clock.h> +#include <linux/fs.h> + +#include "lock_events.h" + +#undef LOCK_EVENT +#define LOCK_EVENT(name) [LOCKEVENT_ ## name] = #name, + +#define LOCK_EVENTS_DIR "lock_event_counts" + +/* + * When CONFIG_LOCK_EVENT_COUNTS is enabled, event counts of different + * types of locks will be reported under the <debugfs>/lock_event_counts/ + * directory. See lock_events_list.h for the list of available locking + * events. + * + * Writing to the special ".reset_counts" file will reset all the above + * locking event counts. This is a very slow operation and so should not + * be done frequently. + * + * These event counts are implemented as per-cpu variables which are + * summed and computed whenever the corresponding debugfs files are read. This + * minimizes added overhead making the counts usable even in a production + * environment. + */ +static const char * const lockevent_names[lockevent_num + 1] = { + +#include "lock_events_list.h" + + [LOCKEVENT_reset_cnts] = ".reset_counts", +}; + +/* + * Per-cpu counts + */ +DEFINE_PER_CPU(unsigned long, lockevents[lockevent_num]); + +/* + * The lockevent_read() function can be overridden. + */ +ssize_t __weak lockevent_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[64]; + int cpu, id, len; + u64 sum = 0; + + /* + * Get the counter ID stored in file->f_inode->i_private + */ + id = (long)file_inode(file)->i_private; + + if (id >= lockevent_num) + return -EBADF; + + for_each_possible_cpu(cpu) + sum += per_cpu(lockevents[id], cpu); + len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum); + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +/* + * Function to handle write request + * + * When idx = reset_cnts, reset all the counts. + */ +static ssize_t lockevent_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + int cpu; + + /* + * Get the counter ID stored in file->f_inode->i_private + */ + if ((long)file_inode(file)->i_private != LOCKEVENT_reset_cnts) + return count; + + for_each_possible_cpu(cpu) { + int i; + unsigned long *ptr = per_cpu_ptr(lockevents, cpu); + + for (i = 0 ; i < lockevent_num; i++) + WRITE_ONCE(ptr[i], 0); + } + return count; +} + +/* + * Debugfs data structures + */ +static const struct file_operations fops_lockevent = { + .read = lockevent_read, + .write = lockevent_write, + .llseek = default_llseek, +}; + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#include <asm/paravirt.h> + +static bool __init skip_lockevent(const char *name) +{ + static int pv_on __initdata = -1; + + if (pv_on < 0) + pv_on = !pv_is_native_spin_unlock(); + /* + * Skip PV qspinlock events on bare metal. + */ + if (!pv_on && !memcmp(name, "pv_", 3)) + return true; + return false; +} +#else +static inline bool skip_lockevent(const char *name) +{ + return false; +} +#endif + +/* + * Initialize debugfs for the locking event counts. + */ +static int __init init_lockevent_counts(void) +{ + struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL); + int i; + + if (!d_counts) + goto out; + + /* + * Create the debugfs files + * + * As reading from and writing to the stat files can be slow, only + * root is allowed to do the read/write to limit impact to system + * performance. + */ + for (i = 0; i < lockevent_num; i++) { + if (skip_lockevent(lockevent_names[i])) + continue; + if (!debugfs_create_file(lockevent_names[i], 0400, d_counts, + (void *)(long)i, &fops_lockevent)) + goto fail_undo; + } + + if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200, + d_counts, (void *)(long)LOCKEVENT_reset_cnts, + &fops_lockevent)) + goto fail_undo; + + return 0; +fail_undo: + debugfs_remove_recursive(d_counts); +out: + pr_warn("Could not create '%s' debugfs entries\n", LOCK_EVENTS_DIR); + return -ENOMEM; +} +fs_initcall(init_lockevent_counts); diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h new file mode 100644 index 000000000000..feb1acc54611 --- /dev/null +++ b/kernel/locking/lock_events.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Waiman Long <longman@redhat.com> + */ + +#ifndef __LOCKING_LOCK_EVENTS_H +#define __LOCKING_LOCK_EVENTS_H + +enum lock_events { + +#include "lock_events_list.h" + + lockevent_num, /* Total number of lock event counts */ + LOCKEVENT_reset_cnts = lockevent_num, +}; + +#ifdef CONFIG_LOCK_EVENT_COUNTS +/* + * Per-cpu counters + */ +DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]); + +/* + * Increment the PV qspinlock statistical counters + */ +static inline void __lockevent_inc(enum lock_events event, bool cond) +{ + if (cond) + __this_cpu_inc(lockevents[event]); +} + +#define lockevent_inc(ev) __lockevent_inc(LOCKEVENT_ ##ev, true) +#define lockevent_cond_inc(ev, c) __lockevent_inc(LOCKEVENT_ ##ev, c) + +static inline void __lockevent_add(enum lock_events event, int inc) +{ + __this_cpu_add(lockevents[event], inc); +} + +#define lockevent_add(ev, c) __lockevent_add(LOCKEVENT_ ##ev, c) + +#else /* CONFIG_LOCK_EVENT_COUNTS */ + +#define lockevent_inc(ev) +#define lockevent_add(ev, c) +#define lockevent_cond_inc(ev, c) + +#endif /* CONFIG_LOCK_EVENT_COUNTS */ +#endif /* __LOCKING_LOCK_EVENTS_H */ diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h new file mode 100644 index 000000000000..ad7668cfc9da --- /dev/null +++ b/kernel/locking/lock_events_list.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Waiman Long <longman@redhat.com> + */ + +#ifndef LOCK_EVENT +#define LOCK_EVENT(name) LOCKEVENT_ ## name, +#endif + +#ifdef CONFIG_QUEUED_SPINLOCKS +#ifdef CONFIG_PARAVIRT_SPINLOCKS +/* + * Locking events for PV qspinlock. + */ +LOCK_EVENT(pv_hash_hops) /* Average # of hops per hashing operation */ +LOCK_EVENT(pv_kick_unlock) /* # of vCPU kicks issued at unlock time */ +LOCK_EVENT(pv_kick_wake) /* # of vCPU kicks for pv_latency_wake */ +LOCK_EVENT(pv_latency_kick) /* Average latency (ns) of vCPU kick */ +LOCK_EVENT(pv_latency_wake) /* Average latency (ns) of kick-to-wakeup */ +LOCK_EVENT(pv_lock_stealing) /* # of lock stealing operations */ +LOCK_EVENT(pv_spurious_wakeup) /* # of spurious wakeups in non-head vCPUs */ +LOCK_EVENT(pv_wait_again) /* # of wait's after queue head vCPU kick */ +LOCK_EVENT(pv_wait_early) /* # of early vCPU wait's */ +LOCK_EVENT(pv_wait_head) /* # of vCPU wait's at the queue head */ +LOCK_EVENT(pv_wait_node) /* # of vCPU wait's at non-head queue node */ +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +/* + * Locking events for qspinlock + * + * Subtracting lock_use_node[234] from lock_slowpath will give you + * lock_use_node1. + */ +LOCK_EVENT(lock_pending) /* # of locking ops via pending code */ +LOCK_EVENT(lock_slowpath) /* # of locking ops via MCS lock queue */ +LOCK_EVENT(lock_use_node2) /* # of locking ops that use 2nd percpu node */ +LOCK_EVENT(lock_use_node3) /* # of locking ops that use 3rd percpu node */ +LOCK_EVENT(lock_use_node4) /* # of locking ops that use 4th percpu node */ +LOCK_EVENT(lock_no_node) /* # of locking ops w/o using percpu node */ +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +/* + * Locking events for rwsem + */ +LOCK_EVENT(rwsem_sleep_reader) /* # of reader sleeps */ +LOCK_EVENT(rwsem_sleep_writer) /* # of writer sleeps */ +LOCK_EVENT(rwsem_wake_reader) /* # of reader wakeups */ +LOCK_EVENT(rwsem_wake_writer) /* # of writer wakeups */ +LOCK_EVENT(rwsem_opt_wlock) /* # of write locks opt-spin acquired */ +LOCK_EVENT(rwsem_opt_fail) /* # of failed opt-spinnings */ +LOCK_EVENT(rwsem_rlock) /* # of read locks acquired */ +LOCK_EVENT(rwsem_rlock_fast) /* # of fast read locks acquired */ +LOCK_EVENT(rwsem_rlock_fail) /* # of failed read lock acquisitions */ +LOCK_EVENT(rwsem_rtrylock) /* # of read trylock calls */ +LOCK_EVENT(rwsem_wlock) /* # of write locks acquired */ +LOCK_EVENT(rwsem_wlock_fail) /* # of failed write lock acquisitions */ +LOCK_EVENT(rwsem_wtrylock) /* # of write trylock calls */ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 34cdcbedda49..d06190fa5082 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -434,29 +434,14 @@ static void print_lockdep_off(const char *bug_msg) #endif } -static int save_trace(struct stack_trace *trace) +static int save_trace(struct lock_trace *trace) { - trace->nr_entries = 0; - trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - trace->entries = stack_trace + nr_stack_trace_entries; - - trace->skip = 3; - - save_stack_trace(trace); - - /* - * Some daft arches put -1 at the end to indicate its a full trace. - * - * <rant> this is buggy anyway, since it takes a whole extra entry so a - * complete trace that maxes out the entries provided will be reported - * as incomplete, friggin useless </rant> - */ - if (trace->nr_entries != 0 && - trace->entries[trace->nr_entries-1] == ULONG_MAX) - trace->nr_entries--; - - trace->max_entries = trace->nr_entries; + unsigned long *entries = stack_trace + nr_stack_trace_entries; + unsigned int max_entries; + trace->offset = nr_stack_trace_entries; + max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; + trace->nr_entries = stack_trace_save(entries, max_entries, 3); nr_stack_trace_entries += trace->nr_entries; if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { @@ -516,11 +501,11 @@ static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit) { char c = '.'; - if (class->usage_mask & lock_flag(bit + 2)) + if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK)) c = '+'; if (class->usage_mask & lock_flag(bit)) { c = '-'; - if (class->usage_mask & lock_flag(bit + 2)) + if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK)) c = '?'; } @@ -649,6 +634,9 @@ static int static_obj(const void *obj) end = (unsigned long) &_end, addr = (unsigned long) obj; + if (arch_is_kernel_initmem_freed(addr)) + return 0; + /* * static variable? */ @@ -1207,7 +1195,7 @@ static struct lock_list *alloc_list_entry(void) static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, unsigned long ip, int distance, - struct stack_trace *trace) + struct lock_trace *trace) { struct lock_list *entry; /* @@ -1426,6 +1414,13 @@ static inline int __bfs_backwards(struct lock_list *src_entry, * checking. */ +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ + unsigned long *entries = stack_trace + trace->offset; + + stack_trace_print(entries, trace->nr_entries, spaces); +} + /* * Print a dependency chain entry (this is only done when a deadlock * has been detected): @@ -1438,8 +1433,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) printk("\n-> #%u", depth); print_lock_name(target->class); printk(KERN_CONT ":\n"); - print_stack_trace(&target->trace, 6); - + print_lock_trace(&target->trace, 6); return 0; } @@ -1533,10 +1527,9 @@ static inline int class_equal(struct lock_list *entry, void *data) } static noinline int print_circular_bug(struct lock_list *this, - struct lock_list *target, - struct held_lock *check_src, - struct held_lock *check_tgt, - struct stack_trace *trace) + struct lock_list *target, + struct held_lock *check_src, + struct held_lock *check_tgt) { struct task_struct *curr = current; struct lock_list *parent; @@ -1676,19 +1669,25 @@ check_redundant(struct lock_list *root, struct lock_class *target, } #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + +static inline int usage_accumulate(struct lock_list *entry, void *mask) +{ + *(unsigned long *)mask |= entry->class->usage_mask; + + return 0; +} + /* * Forwards and backwards subgraph searching, for the purposes of * proving that two subgraphs can be connected by a new dependency * without creating any illegal irq-safe -> irq-unsafe lock dependency. */ -static inline int usage_match(struct lock_list *entry, void *bit) +static inline int usage_match(struct lock_list *entry, void *mask) { - return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit); + return entry->class->usage_mask & *(unsigned long *)mask; } - - /* * Find a node in the forwards-direction dependency sub-graph starting * at @root->class that matches @bit. @@ -1700,14 +1699,14 @@ static inline int usage_match(struct lock_list *entry, void *bit) * Return <0 on error. */ static int -find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit, +find_usage_forwards(struct lock_list *root, unsigned long usage_mask, struct lock_list **target_entry) { int result; debug_atomic_inc(nr_find_usage_forwards_checks); - result = __bfs_forwards(root, (void *)bit, usage_match, target_entry); + result = __bfs_forwards(root, &usage_mask, usage_match, target_entry); return result; } @@ -1723,14 +1722,14 @@ find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit, * Return <0 on error. */ static int -find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit, +find_usage_backwards(struct lock_list *root, unsigned long usage_mask, struct lock_list **target_entry) { int result; debug_atomic_inc(nr_find_usage_backwards_checks); - result = __bfs_backwards(root, (void *)bit, usage_match, target_entry); + result = __bfs_backwards(root, &usage_mask, usage_match, target_entry); return result; } @@ -1752,7 +1751,7 @@ static void print_lock_class_header(struct lock_class *class, int depth) len += printk("%*s %s", depth, "", usage_str[bit]); len += printk(KERN_CONT " at:\n"); - print_stack_trace(class->usage_traces + bit, len); + print_lock_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); @@ -1777,7 +1776,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, do { print_lock_class_header(entry->class, depth); printk("%*s ... acquired at:\n", depth, ""); - print_stack_trace(&entry->trace, 2); + print_lock_trace(&entry->trace, 2); printk("\n"); if (depth == 0 && (entry != root)) { @@ -1890,14 +1889,14 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock_name(backwards_entry->class); pr_warn("\n... which became %s-irq-safe at:\n", irqclass); - print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); + print_lock_trace(backwards_entry->class->usage_traces + bit1, 1); pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); pr_warn("..."); - print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); + print_lock_trace(forwards_entry->class->usage_traces + bit2, 1); pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, @@ -1922,39 +1921,6 @@ print_bad_irq_dependency(struct task_struct *curr, return 0; } -static int -check_usage(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, enum lock_usage_bit bit_backwards, - enum lock_usage_bit bit_forwards, const char *irqclass) -{ - int ret; - struct lock_list this, that; - struct lock_list *uninitialized_var(target_entry); - struct lock_list *uninitialized_var(target_entry1); - - this.parent = NULL; - - this.class = hlock_class(prev); - ret = find_usage_backwards(&this, bit_backwards, &target_entry); - if (ret < 0) - return print_bfs_bug(ret); - if (ret == 1) - return ret; - - that.parent = NULL; - that.class = hlock_class(next); - ret = find_usage_forwards(&that, bit_forwards, &target_entry1); - if (ret < 0) - return print_bfs_bug(ret); - if (ret == 1) - return ret; - - return print_bad_irq_dependency(curr, &this, &that, - target_entry, target_entry1, - prev, next, - bit_backwards, bit_forwards, irqclass); -} - static const char *state_names[] = { #define LOCKDEP_STATE(__STATE) \ __stringify(__STATE), @@ -1971,9 +1937,19 @@ static const char *state_rnames[] = { static inline const char *state_name(enum lock_usage_bit bit) { - return (bit & LOCK_USAGE_READ_MASK) ? state_rnames[bit >> 2] : state_names[bit >> 2]; + if (bit & LOCK_USAGE_READ_MASK) + return state_rnames[bit >> LOCK_USAGE_DIR_MASK]; + else + return state_names[bit >> LOCK_USAGE_DIR_MASK]; } +/* + * The bit number is encoded like: + * + * bit0: 0 exclusive, 1 read lock + * bit1: 0 used in irq, 1 irq enabled + * bit2-n: state + */ static int exclusive_bit(int new_bit) { int state = new_bit & LOCK_USAGE_STATE_MASK; @@ -1985,45 +1961,160 @@ static int exclusive_bit(int new_bit) return state | (dir ^ LOCK_USAGE_DIR_MASK); } +/* + * Observe that when given a bitmask where each bitnr is encoded as above, a + * right shift of the mask transforms the individual bitnrs as -1 and + * conversely, a left shift transforms into +1 for the individual bitnrs. + * + * So for all bits whose number have LOCK_ENABLED_* set (bitnr1 == 1), we can + * create the mask with those bit numbers using LOCK_USED_IN_* (bitnr1 == 0) + * instead by subtracting the bit number by 2, or shifting the mask right by 2. + * + * Similarly, bitnr1 == 0 becomes bitnr1 == 1 by adding 2, or shifting left 2. + * + * So split the mask (note that LOCKF_ENABLED_IRQ_ALL|LOCKF_USED_IN_IRQ_ALL is + * all bits set) and recompose with bitnr1 flipped. + */ +static unsigned long invert_dir_mask(unsigned long mask) +{ + unsigned long excl = 0; + + /* Invert dir */ + excl |= (mask & LOCKF_ENABLED_IRQ_ALL) >> LOCK_USAGE_DIR_MASK; + excl |= (mask & LOCKF_USED_IN_IRQ_ALL) << LOCK_USAGE_DIR_MASK; + + return excl; +} + +/* + * As above, we clear bitnr0 (LOCK_*_READ off) with bitmask ops. First, for all + * bits with bitnr0 set (LOCK_*_READ), add those with bitnr0 cleared (LOCK_*). + * And then mask out all bitnr0. + */ +static unsigned long exclusive_mask(unsigned long mask) +{ + unsigned long excl = invert_dir_mask(mask); + + /* Strip read */ + excl |= (excl & LOCKF_IRQ_READ) >> LOCK_USAGE_READ_MASK; + excl &= ~LOCKF_IRQ_READ; + + return excl; +} + +/* + * Retrieve the _possible_ original mask to which @mask is + * exclusive. Ie: this is the opposite of exclusive_mask(). + * Note that 2 possible original bits can match an exclusive + * bit: one has LOCK_USAGE_READ_MASK set, the other has it + * cleared. So both are returned for each exclusive bit. + */ +static unsigned long original_mask(unsigned long mask) +{ + unsigned long excl = invert_dir_mask(mask); + + /* Include read in existing usages */ + excl |= (excl & LOCKF_IRQ) << LOCK_USAGE_READ_MASK; + + return excl; +} + +/* + * Find the first pair of bit match between an original + * usage mask and an exclusive usage mask. + */ +static int find_exclusive_match(unsigned long mask, + unsigned long excl_mask, + enum lock_usage_bit *bitp, + enum lock_usage_bit *excl_bitp) +{ + int bit, excl; + + for_each_set_bit(bit, &mask, LOCK_USED) { + excl = exclusive_bit(bit); + if (excl_mask & lock_flag(excl)) { + *bitp = bit; + *excl_bitp = excl; + return 0; + } + } + return -1; +} + +/* + * Prove that the new dependency does not connect a hardirq-safe(-read) + * lock with a hardirq-unsafe lock - to achieve this we search + * the backwards-subgraph starting at <prev>, and the + * forwards-subgraph starting at <next>: + */ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, enum lock_usage_bit bit) + struct held_lock *next) { + unsigned long usage_mask = 0, forward_mask, backward_mask; + enum lock_usage_bit forward_bit = 0, backward_bit = 0; + struct lock_list *uninitialized_var(target_entry1); + struct lock_list *uninitialized_var(target_entry); + struct lock_list this, that; + int ret; + /* - * Prove that the new dependency does not connect a hardirq-safe - * lock with a hardirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at <prev>, and the - * forwards-subgraph starting at <next>: + * Step 1: gather all hard/soft IRQs usages backward in an + * accumulated usage mask. */ - if (!check_usage(curr, prev, next, bit, - exclusive_bit(bit), state_name(bit))) - return 0; + this.parent = NULL; + this.class = hlock_class(prev); + + ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL); + if (ret < 0) + return print_bfs_bug(ret); - bit++; /* _READ */ + usage_mask &= LOCKF_USED_IN_IRQ_ALL; + if (!usage_mask) + return 1; /* - * Prove that the new dependency does not connect a hardirq-safe-read - * lock with a hardirq-unsafe lock - to achieve this we search - * the backwards-subgraph starting at <prev>, and the - * forwards-subgraph starting at <next>: + * Step 2: find exclusive uses forward that match the previous + * backward accumulated mask. */ - if (!check_usage(curr, prev, next, bit, - exclusive_bit(bit), state_name(bit))) - return 0; + forward_mask = exclusive_mask(usage_mask); - return 1; -} + that.parent = NULL; + that.class = hlock_class(next); -static int -check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next) -{ -#define LOCKDEP_STATE(__STATE) \ - if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE)) \ - return 0; -#include "lockdep_states.h" -#undef LOCKDEP_STATE + ret = find_usage_forwards(&that, forward_mask, &target_entry1); + if (ret < 0) + return print_bfs_bug(ret); + if (ret == 1) + return ret; - return 1; + /* + * Step 3: we found a bad match! Now retrieve a lock from the backward + * list whose usage mask matches the exclusive usage mask from the + * lock found on the forward list. + */ + backward_mask = original_mask(target_entry1->class->usage_mask); + + ret = find_usage_backwards(&this, backward_mask, &target_entry); + if (ret < 0) + return print_bfs_bug(ret); + if (DEBUG_LOCKS_WARN_ON(ret == 1)) + return 1; + + /* + * Step 4: narrow down to a pair of incompatible usage bits + * and report it. + */ + ret = find_exclusive_match(target_entry->class->usage_mask, + target_entry1->class->usage_mask, + &backward_bit, &forward_bit); + if (DEBUG_LOCKS_WARN_ON(ret == -1)) + return 1; + + return print_bad_irq_dependency(curr, &this, &that, + target_entry, target_entry1, + prev, next, + backward_bit, forward_bit, + state_name(backward_bit)); } static void inc_chains(void) @@ -2040,9 +2131,8 @@ static void inc_chains(void) #else -static inline int -check_prev_add_irq(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next) +static inline int check_irq_usage(struct task_struct *curr, + struct held_lock *prev, struct held_lock *next) { return 1; } @@ -2170,8 +2260,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, struct stack_trace *trace, - int (*save)(struct stack_trace *trace)) + struct held_lock *next, int distance, struct lock_trace *trace) { struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; @@ -2209,20 +2298,20 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); if (unlikely(!ret)) { - if (!trace->entries) { + if (!trace->nr_entries) { /* - * If @save fails here, the printing might trigger - * a WARN but because of the !nr_entries it should - * not do bad things. + * If save_trace fails here, the printing might + * trigger a WARN but because of the !nr_entries it + * should not do bad things. */ - save(trace); + save_trace(trace); } - return print_circular_bug(&this, target_entry, next, prev, trace); + return print_circular_bug(&this, target_entry, next, prev); } else if (unlikely(ret < 0)) return print_bfs_bug(ret); - if (!check_prev_add_irq(curr, prev, next)) + if (!check_irq_usage(curr, prev, next)) return 0; /* @@ -2265,7 +2354,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (!trace->entries && !save(trace)) + if (!trace->nr_entries && !save_trace(trace)) return 0; /* @@ -2297,14 +2386,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { + struct lock_trace trace = { .nr_entries = 0 }; int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace = { - .nr_entries = 0, - .max_entries = 0, - .entries = NULL, - .skip = 0, - }; /* * Debugging checks. @@ -2330,7 +2414,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) * added: */ if (hlock->read != 2 && hlock->check) { - int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace); + int ret = check_prev_add(curr, hlock, next, distance, + &trace); if (!ret) return 0; @@ -2731,6 +2816,10 @@ static inline int validate_chain(struct task_struct *curr, { return 1; } + +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ +} #endif /* @@ -2784,6 +2873,12 @@ static void check_chain_key(struct task_struct *curr) #endif } +static int mark_lock(struct task_struct *curr, struct held_lock *this, + enum lock_usage_bit new_bit); + +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) + + static void print_usage_bug_scenario(struct held_lock *lock) { @@ -2827,7 +2922,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); - print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); + print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); pr_warn("\nother info that might help us debug this:\n"); @@ -2853,10 +2948,6 @@ valid_state(struct task_struct *curr, struct held_lock *this, return 1; } -static int mark_lock(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit); - -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * print irq inversion bug: @@ -2936,7 +3027,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this, root.parent = NULL; root.class = hlock_class(this); - ret = find_usage_forwards(&root, bit, &target_entry); + ret = find_usage_forwards(&root, lock_flag(bit), &target_entry); if (ret < 0) return print_bfs_bug(ret); if (ret == 1) @@ -2960,7 +3051,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, root.parent = NULL; root.class = hlock_class(this); - ret = find_usage_backwards(&root, bit, &target_entry); + ret = find_usage_backwards(&root, lock_flag(bit), &target_entry); if (ret < 0) return print_bfs_bug(ret); if (ret == 1) @@ -3015,7 +3106,7 @@ static int (*state_verbose_f[])(struct lock_class *class) = { static inline int state_verbose(enum lock_usage_bit bit, struct lock_class *class) { - return state_verbose_f[bit >> 2](class); + return state_verbose_f[bit >> LOCK_USAGE_DIR_MASK](class); } typedef int (*check_usage_f)(struct task_struct *, struct held_lock *, @@ -3157,7 +3248,7 @@ void lockdep_hardirqs_on(unsigned long ip) /* * See the fine text that goes along with this variable definition. */ - if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled))) + if (DEBUG_LOCKS_WARN_ON(early_boot_irqs_disabled)) return; /* @@ -4689,8 +4780,8 @@ static void free_zapped_rcu(struct rcu_head *ch) return; raw_local_irq_save(flags); - if (!graph_lock()) - goto out_irq; + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; /* closed head */ pf = delayed_free.pf + (delayed_free.index ^ 1); @@ -4702,8 +4793,8 @@ static void free_zapped_rcu(struct rcu_head *ch) */ call_rcu_zapped(delayed_free.pf + delayed_free.index); - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); } @@ -4744,21 +4835,17 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) { struct pending_free *pf; unsigned long flags; - int locked; init_data_structures_once(); raw_local_irq_save(flags); - locked = graph_lock(); - if (!locked) - goto out_irq; - + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; pf = get_pending_free(); __lockdep_free_key_range(pf, start, size); call_rcu_zapped(pf); - - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); /* diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index d4c197425f68..150ec3f0c5b5 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -42,13 +42,35 @@ enum { __LOCKF(USED) }; -#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ) -#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ) +#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE | +static const unsigned long LOCKF_ENABLED_IRQ = +#include "lockdep_states.h" + 0; +#undef LOCKDEP_STATE + +#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE | +static const unsigned long LOCKF_USED_IN_IRQ = +#include "lockdep_states.h" + 0; +#undef LOCKDEP_STATE + +#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE##_READ | +static const unsigned long LOCKF_ENABLED_IRQ_READ = +#include "lockdep_states.h" + 0; +#undef LOCKDEP_STATE + +#define LOCKDEP_STATE(__STATE) LOCKF_USED_IN_##__STATE##_READ | +static const unsigned long LOCKF_USED_IN_IRQ_READ = +#include "lockdep_states.h" + 0; +#undef LOCKDEP_STATE + +#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ) +#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ) -#define LOCKF_ENABLED_IRQ_READ \ - (LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ) -#define LOCKF_USED_IN_IRQ_READ \ - (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) +#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ) +#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ) /* * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text, diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index ad40a2617063..80a463d31a8d 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -829,7 +829,9 @@ static void lock_torture_cleanup(void) "End of test: SUCCESS"); kfree(cxt.lwsa); + cxt.lwsa = NULL; kfree(cxt.lrsa); + cxt.lrsa = NULL; end: torture_cleanup_end(); diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 883cf1b92d90..f17dad99eec8 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -7,6 +7,8 @@ #include <linux/sched.h> #include <linux/errno.h> +#include "rwsem.h" + int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, const char *name, struct lock_class_key *rwsem_key) { diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 5e9247dc2515..e14b32c69639 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -395,7 +395,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * 0,1,0 -> 0,0,1 */ clear_pending_set_locked(lock); - qstat_inc(qstat_lock_pending, true); + lockevent_inc(lock_pending); return; /* @@ -403,7 +403,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * queuing. */ queue: - qstat_inc(qstat_lock_slowpath, true); + lockevent_inc(lock_slowpath); pv_queue: node = this_cpu_ptr(&qnodes[0].mcs); idx = node->count++; @@ -419,7 +419,7 @@ pv_queue: * simple enough. */ if (unlikely(idx >= MAX_NODES)) { - qstat_inc(qstat_lock_no_node, true); + lockevent_inc(lock_no_node); while (!queued_spin_trylock(lock)) cpu_relax(); goto release; @@ -430,7 +430,7 @@ pv_queue: /* * Keep counts of non-zero index values: */ - qstat_inc(qstat_lock_use_node2 + idx - 1, idx); + lockevent_cond_inc(lock_use_node2 + idx - 1, idx); /* * Ensure that we increment the head node->count before initialising diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 8f36c27c1794..89bab079e7a4 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -89,7 +89,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock) if (!(val & _Q_LOCKED_PENDING_MASK) && (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) { - qstat_inc(qstat_pv_lock_stealing, true); + lockevent_inc(pv_lock_stealing); return true; } if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK)) @@ -219,7 +219,7 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node) hopcnt++; if (!cmpxchg(&he->lock, NULL, lock)) { WRITE_ONCE(he->node, node); - qstat_hop(hopcnt); + lockevent_pv_hop(hopcnt); return &he->lock; } } @@ -320,8 +320,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) smp_store_mb(pn->state, vcpu_halted); if (!READ_ONCE(node->locked)) { - qstat_inc(qstat_pv_wait_node, true); - qstat_inc(qstat_pv_wait_early, wait_early); + lockevent_inc(pv_wait_node); + lockevent_cond_inc(pv_wait_early, wait_early); pv_wait(&pn->state, vcpu_halted); } @@ -339,7 +339,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) * So it is better to spin for a while in the hope that the * MCS lock will be released soon. */ - qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked)); + lockevent_cond_inc(pv_spurious_wakeup, + !READ_ONCE(node->locked)); } /* @@ -416,7 +417,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) /* * Tracking # of slowpath locking operations */ - qstat_inc(qstat_lock_slowpath, true); + lockevent_inc(lock_slowpath); for (;; waitcnt++) { /* @@ -464,8 +465,8 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) } } WRITE_ONCE(pn->state, vcpu_hashed); - qstat_inc(qstat_pv_wait_head, true); - qstat_inc(qstat_pv_wait_again, waitcnt); + lockevent_inc(pv_wait_head); + lockevent_cond_inc(pv_wait_again, waitcnt); pv_wait(&lock->locked, _Q_SLOW_VAL); /* @@ -528,7 +529,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) * vCPU is harmless other than the additional latency in completing * the unlock. */ - qstat_inc(qstat_pv_kick_unlock, true); + lockevent_inc(pv_kick_unlock); pv_kick(node->cpu); } diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index d73f85388d5c..54152670ff24 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -9,262 +9,105 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Waiman Long <waiman.long@hpe.com> + * Authors: Waiman Long <longman@redhat.com> */ -/* - * When queued spinlock statistical counters are enabled, the following - * debugfs files will be created for reporting the counter values: - * - * <debugfs>/qlockstat/ - * pv_hash_hops - average # of hops per hashing operation - * pv_kick_unlock - # of vCPU kicks issued at unlock time - * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake - * pv_latency_kick - average latency (ns) of vCPU kick operation - * pv_latency_wake - average latency (ns) from vCPU kick to wakeup - * pv_lock_stealing - # of lock stealing operations - * pv_spurious_wakeup - # of spurious wakeups in non-head vCPUs - * pv_wait_again - # of wait's after a queue head vCPU kick - * pv_wait_early - # of early vCPU wait's - * pv_wait_head - # of vCPU wait's at the queue head - * pv_wait_node - # of vCPU wait's at a non-head queue node - * lock_pending - # of locking operations via pending code - * lock_slowpath - # of locking operations via MCS lock queue - * lock_use_node2 - # of locking operations that use 2nd per-CPU node - * lock_use_node3 - # of locking operations that use 3rd per-CPU node - * lock_use_node4 - # of locking operations that use 4th per-CPU node - * lock_no_node - # of locking operations without using per-CPU node - * - * Subtracting lock_use_node[234] from lock_slowpath will give you - * lock_use_node1. - * - * Writing to the "reset_counters" file will reset all the above counter - * values. - * - * These statistical counters are implemented as per-cpu variables which are - * summed and computed whenever the corresponding debugfs files are read. This - * minimizes added overhead making the counters usable even in a production - * environment. - * - * There may be slight difference between pv_kick_wake and pv_kick_unlock. - */ -enum qlock_stats { - qstat_pv_hash_hops, - qstat_pv_kick_unlock, - qstat_pv_kick_wake, - qstat_pv_latency_kick, - qstat_pv_latency_wake, - qstat_pv_lock_stealing, - qstat_pv_spurious_wakeup, - qstat_pv_wait_again, - qstat_pv_wait_early, - qstat_pv_wait_head, - qstat_pv_wait_node, - qstat_lock_pending, - qstat_lock_slowpath, - qstat_lock_use_node2, - qstat_lock_use_node3, - qstat_lock_use_node4, - qstat_lock_no_node, - qstat_num, /* Total number of statistical counters */ - qstat_reset_cnts = qstat_num, -}; +#include "lock_events.h" -#ifdef CONFIG_QUEUED_LOCK_STAT +#ifdef CONFIG_LOCK_EVENT_COUNTS +#ifdef CONFIG_PARAVIRT_SPINLOCKS /* - * Collect pvqspinlock statistics + * Collect pvqspinlock locking event counts */ -#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/fs.h> -static const char * const qstat_names[qstat_num + 1] = { - [qstat_pv_hash_hops] = "pv_hash_hops", - [qstat_pv_kick_unlock] = "pv_kick_unlock", - [qstat_pv_kick_wake] = "pv_kick_wake", - [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", - [qstat_pv_latency_kick] = "pv_latency_kick", - [qstat_pv_latency_wake] = "pv_latency_wake", - [qstat_pv_lock_stealing] = "pv_lock_stealing", - [qstat_pv_wait_again] = "pv_wait_again", - [qstat_pv_wait_early] = "pv_wait_early", - [qstat_pv_wait_head] = "pv_wait_head", - [qstat_pv_wait_node] = "pv_wait_node", - [qstat_lock_pending] = "lock_pending", - [qstat_lock_slowpath] = "lock_slowpath", - [qstat_lock_use_node2] = "lock_use_node2", - [qstat_lock_use_node3] = "lock_use_node3", - [qstat_lock_use_node4] = "lock_use_node4", - [qstat_lock_no_node] = "lock_no_node", - [qstat_reset_cnts] = "reset_counters", -}; +#define EVENT_COUNT(ev) lockevents[LOCKEVENT_ ## ev] /* - * Per-cpu counters + * PV specific per-cpu counter */ -static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]); static DEFINE_PER_CPU(u64, pv_kick_time); /* - * Function to read and return the qlock statistical counter values + * Function to read and return the PV qspinlock counts. * * The following counters are handled specially: - * 1. qstat_pv_latency_kick + * 1. pv_latency_kick * Average kick latency (ns) = pv_latency_kick/pv_kick_unlock - * 2. qstat_pv_latency_wake + * 2. pv_latency_wake * Average wake latency (ns) = pv_latency_wake/pv_kick_wake - * 3. qstat_pv_hash_hops + * 3. pv_hash_hops * Average hops/hash = pv_hash_hops/pv_kick_unlock */ -static ssize_t qstat_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +ssize_t lockevent_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) { char buf[64]; - int cpu, counter, len; - u64 stat = 0, kicks = 0; + int cpu, id, len; + u64 sum = 0, kicks = 0; /* * Get the counter ID stored in file->f_inode->i_private */ - counter = (long)file_inode(file)->i_private; + id = (long)file_inode(file)->i_private; - if (counter >= qstat_num) + if (id >= lockevent_num) return -EBADF; for_each_possible_cpu(cpu) { - stat += per_cpu(qstats[counter], cpu); + sum += per_cpu(lockevents[id], cpu); /* - * Need to sum additional counter for some of them + * Need to sum additional counters for some of them */ - switch (counter) { + switch (id) { - case qstat_pv_latency_kick: - case qstat_pv_hash_hops: - kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu); + case LOCKEVENT_pv_latency_kick: + case LOCKEVENT_pv_hash_hops: + kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu); break; - case qstat_pv_latency_wake: - kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu); + case LOCKEVENT_pv_latency_wake: + kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu); break; } } - if (counter == qstat_pv_hash_hops) { + if (id == LOCKEVENT_pv_hash_hops) { u64 frac = 0; if (kicks) { - frac = 100ULL * do_div(stat, kicks); + frac = 100ULL * do_div(sum, kicks); frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); } /* * Return a X.XX decimal number */ - len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac); + len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", + sum, frac); } else { /* * Round to the nearest ns */ - if ((counter == qstat_pv_latency_kick) || - (counter == qstat_pv_latency_wake)) { + if ((id == LOCKEVENT_pv_latency_kick) || + (id == LOCKEVENT_pv_latency_wake)) { if (kicks) - stat = DIV_ROUND_CLOSEST_ULL(stat, kicks); + sum = DIV_ROUND_CLOSEST_ULL(sum, kicks); } - len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat); + len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum); } return simple_read_from_buffer(user_buf, count, ppos, buf, len); } /* - * Function to handle write request - * - * When counter = reset_cnts, reset all the counter values. - * Since the counter updates aren't atomic, the resetting is done twice - * to make sure that the counters are very likely to be all cleared. - */ -static ssize_t qstat_write(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) -{ - int cpu; - - /* - * Get the counter ID stored in file->f_inode->i_private - */ - if ((long)file_inode(file)->i_private != qstat_reset_cnts) - return count; - - for_each_possible_cpu(cpu) { - int i; - unsigned long *ptr = per_cpu_ptr(qstats, cpu); - - for (i = 0 ; i < qstat_num; i++) - WRITE_ONCE(ptr[i], 0); - } - return count; -} - -/* - * Debugfs data structures - */ -static const struct file_operations fops_qstat = { - .read = qstat_read, - .write = qstat_write, - .llseek = default_llseek, -}; - -/* - * Initialize debugfs for the qspinlock statistical counters - */ -static int __init init_qspinlock_stat(void) -{ - struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL); - int i; - - if (!d_qstat) - goto out; - - /* - * Create the debugfs files - * - * As reading from and writing to the stat files can be slow, only - * root is allowed to do the read/write to limit impact to system - * performance. - */ - for (i = 0; i < qstat_num; i++) - if (!debugfs_create_file(qstat_names[i], 0400, d_qstat, - (void *)(long)i, &fops_qstat)) - goto fail_undo; - - if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, - (void *)(long)qstat_reset_cnts, &fops_qstat)) - goto fail_undo; - - return 0; -fail_undo: - debugfs_remove_recursive(d_qstat); -out: - pr_warn("Could not create 'qlockstat' debugfs entries\n"); - return -ENOMEM; -} -fs_initcall(init_qspinlock_stat); - -/* - * Increment the PV qspinlock statistical counters - */ -static inline void qstat_inc(enum qlock_stats stat, bool cond) -{ - if (cond) - this_cpu_inc(qstats[stat]); -} - -/* * PV hash hop count */ -static inline void qstat_hop(int hopcnt) +static inline void lockevent_pv_hop(int hopcnt) { - this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt); + this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt); } /* @@ -276,7 +119,7 @@ static inline void __pv_kick(int cpu) per_cpu(pv_kick_time, cpu) = start; pv_kick(cpu); - this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start); + this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start); } /* @@ -289,18 +132,19 @@ static inline void __pv_wait(u8 *ptr, u8 val) *pkick_time = 0; pv_wait(ptr, val); if (*pkick_time) { - this_cpu_add(qstats[qstat_pv_latency_wake], + this_cpu_add(EVENT_COUNT(pv_latency_wake), sched_clock() - *pkick_time); - qstat_inc(qstat_pv_kick_wake, true); + lockevent_inc(pv_kick_wake); } } #define pv_kick(c) __pv_kick(c) #define pv_wait(p, v) __pv_wait(p, v) -#else /* CONFIG_QUEUED_LOCK_STAT */ +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#else /* CONFIG_LOCK_EVENT_COUNTS */ -static inline void qstat_inc(enum qlock_stats stat, bool cond) { } -static inline void qstat_hop(int hopcnt) { } +static inline void lockevent_pv_hop(int hopcnt) { } -#endif /* CONFIG_QUEUED_LOCK_STAT */ +#endif /* CONFIG_LOCK_EVENT_COUNTS */ diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c deleted file mode 100644 index a7ffb2a96ede..000000000000 --- a/kernel/locking/rwsem-spinlock.c +++ /dev/null @@ -1,339 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* rwsem-spinlock.c: R/W semaphores: contention handling functions for - * generic spinlock implementation - * - * Copyright (c) 2001 David Howells (dhowells@redhat.com). - * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> - * - Derived also from comments by Linus - */ -#include <linux/rwsem.h> -#include <linux/sched/signal.h> -#include <linux/sched/debug.h> -#include <linux/export.h> - -enum rwsem_waiter_type { - RWSEM_WAITING_FOR_WRITE, - RWSEM_WAITING_FOR_READ -}; - -struct rwsem_waiter { - struct list_head list; - struct task_struct *task; - enum rwsem_waiter_type type; -}; - -int rwsem_is_locked(struct rw_semaphore *sem) -{ - int ret = 1; - unsigned long flags; - - if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) { - ret = (sem->count != 0); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - } - return ret; -} -EXPORT_SYMBOL(rwsem_is_locked); - -/* - * initialise the semaphore - */ -void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key) -{ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - /* - * Make sure we are not reinitializing a held semaphore: - */ - debug_check_no_locks_freed((void *)sem, sizeof(*sem)); - lockdep_init_map(&sem->dep_map, name, key, 0); -#endif - sem->count = 0; - raw_spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} -EXPORT_SYMBOL(__init_rwsem); - -/* - * handle the lock release when processes blocked on it that can now run - * - if we come here, then: - * - the 'active count' _reached_ zero - * - the 'waiting count' is non-zero - * - the spinlock must be held by the caller - * - woken process blocks are discarded from the list after having task zeroed - * - writers are only woken if wakewrite is non-zero - */ -static inline struct rw_semaphore * -__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) -{ - struct rwsem_waiter *waiter; - struct task_struct *tsk; - int woken; - - waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - - if (waiter->type == RWSEM_WAITING_FOR_WRITE) { - if (wakewrite) - /* Wake up a writer. Note that we do not grant it the - * lock - it will have to acquire it when it runs. */ - wake_up_process(waiter->task); - goto out; - } - - /* grant an infinite number of read locks to the front of the queue */ - woken = 0; - do { - struct list_head *next = waiter->list.next; - - list_del(&waiter->list); - tsk = waiter->task; - /* - * Make sure we do not wakeup the next reader before - * setting the nil condition to grant the next reader; - * otherwise we could miss the wakeup on the other - * side and end up sleeping again. See the pairing - * in rwsem_down_read_failed(). - */ - smp_mb(); - waiter->task = NULL; - wake_up_process(tsk); - put_task_struct(tsk); - woken++; - if (next == &sem->wait_list) - break; - waiter = list_entry(next, struct rwsem_waiter, list); - } while (waiter->type != RWSEM_WAITING_FOR_WRITE); - - sem->count += woken; - - out: - return sem; -} - -/* - * wake a single writer - */ -static inline struct rw_semaphore * -__rwsem_wake_one_writer(struct rw_semaphore *sem) -{ - struct rwsem_waiter *waiter; - - waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - wake_up_process(waiter->task); - - return sem; -} - -/* - * get a read lock on the semaphore - */ -int __sched __down_read_common(struct rw_semaphore *sem, int state) -{ - struct rwsem_waiter waiter; - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count >= 0 && list_empty(&sem->wait_list)) { - /* granted */ - sem->count++; - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - goto out; - } - - /* set up my own style of waitqueue */ - waiter.task = current; - waiter.type = RWSEM_WAITING_FOR_READ; - get_task_struct(current); - - list_add_tail(&waiter.list, &sem->wait_list); - - /* wait to be given the lock */ - for (;;) { - if (!waiter.task) - break; - if (signal_pending_state(state, current)) - goto out_nolock; - set_current_state(state); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - schedule(); - raw_spin_lock_irqsave(&sem->wait_lock, flags); - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - out: - return 0; - -out_nolock: - /* - * We didn't take the lock, so that there is a writer, which - * is owner or the first waiter of the sem. If it's a waiter, - * it will be woken by current owner. Not need to wake anybody. - */ - list_del(&waiter.list); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - return -EINTR; -} - -void __sched __down_read(struct rw_semaphore *sem) -{ - __down_read_common(sem, TASK_UNINTERRUPTIBLE); -} - -int __sched __down_read_killable(struct rw_semaphore *sem) -{ - return __down_read_common(sem, TASK_KILLABLE); -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -int __down_read_trylock(struct rw_semaphore *sem) -{ - unsigned long flags; - int ret = 0; - - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count >= 0 && list_empty(&sem->wait_list)) { - /* granted */ - sem->count++; - ret = 1; - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; -} - -/* - * get a write lock on the semaphore - */ -int __sched __down_write_common(struct rw_semaphore *sem, int state) -{ - struct rwsem_waiter waiter; - unsigned long flags; - int ret = 0; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - /* set up my own style of waitqueue */ - waiter.task = current; - waiter.type = RWSEM_WAITING_FOR_WRITE; - list_add_tail(&waiter.list, &sem->wait_list); - - /* wait for someone to release the lock */ - for (;;) { - /* - * That is the key to support write lock stealing: allows the - * task already on CPU to get the lock soon rather than put - * itself into sleep and waiting for system woke it or someone - * else in the head of the wait list up. - */ - if (sem->count == 0) - break; - if (signal_pending_state(state, current)) - goto out_nolock; - - set_current_state(state); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - schedule(); - raw_spin_lock_irqsave(&sem->wait_lock, flags); - } - /* got the lock */ - sem->count = -1; - list_del(&waiter.list); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; - -out_nolock: - list_del(&waiter.list); - if (!list_empty(&sem->wait_list) && sem->count >= 0) - __rwsem_do_wake(sem, 0); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return -EINTR; -} - -void __sched __down_write(struct rw_semaphore *sem) -{ - __down_write_common(sem, TASK_UNINTERRUPTIBLE); -} - -int __sched __down_write_killable(struct rw_semaphore *sem) -{ - return __down_write_common(sem, TASK_KILLABLE); -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -int __down_write_trylock(struct rw_semaphore *sem) -{ - unsigned long flags; - int ret = 0; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count == 0) { - /* got the lock */ - sem->count = -1; - ret = 1; - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; -} - -/* - * release a read lock on the semaphore - */ -void __up_read(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (--sem->count == 0 && !list_empty(&sem->wait_list)) - sem = __rwsem_wake_one_writer(sem); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - -/* - * release a write lock on the semaphore - */ -void __up_write(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - sem->count = 0; - if (!list_empty(&sem->wait_list)) - sem = __rwsem_do_wake(sem, 1); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - -/* - * downgrade a write lock into a read lock - * - just wake up any readers at the front of the queue - */ -void __downgrade_write(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - sem->count = 1; - if (!list_empty(&sem->wait_list)) - sem = __rwsem_do_wake(sem, 0); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index fbe96341beee..6b3ee9948bf1 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -147,6 +147,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, * will notice the queued writer. */ wake_q_add(wake_q, waiter->task); + lockevent_inc(rwsem_wake_writer); } return; @@ -176,9 +177,8 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, goto try_reader_grant; } /* - * It is not really necessary to set it to reader-owned here, - * but it gives the spinners an early indication that the - * readers now have the lock. + * Set it to reader-owned to give spinners an early + * indication that readers now have the lock. */ __rwsem_set_reader_owned(sem, waiter->task); } @@ -215,6 +215,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, } adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; + lockevent_cond_inc(rwsem_wake_reader, woken); if (list_empty(&sem->wait_list)) { /* hit end of list above */ adjustment -= RWSEM_WAITING_BIAS; @@ -225,92 +226,6 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, } /* - * Wait for the read lock to be granted - */ -static inline struct rw_semaphore __sched * -__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state) -{ - long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; - struct rwsem_waiter waiter; - DEFINE_WAKE_Q(wake_q); - - waiter.task = current; - waiter.type = RWSEM_WAITING_FOR_READ; - - raw_spin_lock_irq(&sem->wait_lock); - if (list_empty(&sem->wait_list)) { - /* - * In case the wait queue is empty and the lock isn't owned - * by a writer, this reader can exit the slowpath and return - * immediately as its RWSEM_ACTIVE_READ_BIAS has already - * been set in the count. - */ - if (atomic_long_read(&sem->count) >= 0) { - raw_spin_unlock_irq(&sem->wait_lock); - return sem; - } - adjustment += RWSEM_WAITING_BIAS; - } - list_add_tail(&waiter.list, &sem->wait_list); - - /* we're now waiting on the lock, but no longer actively locking */ - count = atomic_long_add_return(adjustment, &sem->count); - - /* - * If there are no active locks, wake the front queued process(es). - * - * If there are no writers and we are first in the queue, - * wake our own waiter to join the existing active readers ! - */ - if (count == RWSEM_WAITING_BIAS || - (count > RWSEM_WAITING_BIAS && - adjustment != -RWSEM_ACTIVE_READ_BIAS)) - __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); - - raw_spin_unlock_irq(&sem->wait_lock); - wake_up_q(&wake_q); - - /* wait to be given the lock */ - while (true) { - set_current_state(state); - if (!waiter.task) - break; - if (signal_pending_state(state, current)) { - raw_spin_lock_irq(&sem->wait_lock); - if (waiter.task) - goto out_nolock; - raw_spin_unlock_irq(&sem->wait_lock); - break; - } - schedule(); - } - - __set_current_state(TASK_RUNNING); - return sem; -out_nolock: - list_del(&waiter.list); - if (list_empty(&sem->wait_list)) - atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count); - raw_spin_unlock_irq(&sem->wait_lock); - __set_current_state(TASK_RUNNING); - return ERR_PTR(-EINTR); -} - -__visible struct rw_semaphore * __sched -rwsem_down_read_failed(struct rw_semaphore *sem) -{ - return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(rwsem_down_read_failed); - -__visible struct rw_semaphore * __sched -rwsem_down_read_failed_killable(struct rw_semaphore *sem) -{ - return __rwsem_down_read_failed_common(sem, TASK_KILLABLE); -} -EXPORT_SYMBOL(rwsem_down_read_failed_killable); - -/* * This function must be called with the sem->wait_lock held to prevent * race conditions between checking the rwsem wait list and setting the * sem->count accordingly. @@ -346,21 +261,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) */ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) { - long old, count = atomic_long_read(&sem->count); - - while (true) { - if (!(count == 0 || count == RWSEM_WAITING_BIAS)) - return false; + long count = atomic_long_read(&sem->count); - old = atomic_long_cmpxchg_acquire(&sem->count, count, - count + RWSEM_ACTIVE_WRITE_BIAS); - if (old == count) { + while (!count || count == RWSEM_WAITING_BIAS) { + if (atomic_long_try_cmpxchg_acquire(&sem->count, &count, + count + RWSEM_ACTIVE_WRITE_BIAS)) { rwsem_set_owner(sem); + lockevent_inc(rwsem_opt_wlock); return true; } - - count = old; } + return false; } static inline bool owner_on_cpu(struct task_struct *owner) @@ -481,6 +392,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) osq_unlock(&sem->osq); done: preempt_enable(); + lockevent_cond_inc(rwsem_opt_fail, !taken); return taken; } @@ -505,6 +417,97 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem) #endif /* + * Wait for the read lock to be granted + */ +static inline struct rw_semaphore __sched * +__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state) +{ + long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; + struct rwsem_waiter waiter; + DEFINE_WAKE_Q(wake_q); + + waiter.task = current; + waiter.type = RWSEM_WAITING_FOR_READ; + + raw_spin_lock_irq(&sem->wait_lock); + if (list_empty(&sem->wait_list)) { + /* + * In case the wait queue is empty and the lock isn't owned + * by a writer, this reader can exit the slowpath and return + * immediately as its RWSEM_ACTIVE_READ_BIAS has already + * been set in the count. + */ + if (atomic_long_read(&sem->count) >= 0) { + raw_spin_unlock_irq(&sem->wait_lock); + rwsem_set_reader_owned(sem); + lockevent_inc(rwsem_rlock_fast); + return sem; + } + adjustment += RWSEM_WAITING_BIAS; + } + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + count = atomic_long_add_return(adjustment, &sem->count); + + /* + * If there are no active locks, wake the front queued process(es). + * + * If there are no writers and we are first in the queue, + * wake our own waiter to join the existing active readers ! + */ + if (count == RWSEM_WAITING_BIAS || + (count > RWSEM_WAITING_BIAS && + adjustment != -RWSEM_ACTIVE_READ_BIAS)) + __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); + + raw_spin_unlock_irq(&sem->wait_lock); + wake_up_q(&wake_q); + + /* wait to be given the lock */ + while (true) { + set_current_state(state); + if (!waiter.task) + break; + if (signal_pending_state(state, current)) { + raw_spin_lock_irq(&sem->wait_lock); + if (waiter.task) + goto out_nolock; + raw_spin_unlock_irq(&sem->wait_lock); + break; + } + schedule(); + lockevent_inc(rwsem_sleep_reader); + } + + __set_current_state(TASK_RUNNING); + lockevent_inc(rwsem_rlock); + return sem; +out_nolock: + list_del(&waiter.list); + if (list_empty(&sem->wait_list)) + atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count); + raw_spin_unlock_irq(&sem->wait_lock); + __set_current_state(TASK_RUNNING); + lockevent_inc(rwsem_rlock_fail); + return ERR_PTR(-EINTR); +} + +__visible struct rw_semaphore * __sched +rwsem_down_read_failed(struct rw_semaphore *sem) +{ + return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(rwsem_down_read_failed); + +__visible struct rw_semaphore * __sched +rwsem_down_read_failed_killable(struct rw_semaphore *sem) +{ + return __rwsem_down_read_failed_common(sem, TASK_KILLABLE); +} +EXPORT_SYMBOL(rwsem_down_read_failed_killable); + +/* * Wait until we successfully acquire the write lock */ static inline struct rw_semaphore * @@ -580,6 +583,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) goto out_nolock; schedule(); + lockevent_inc(rwsem_sleep_writer); set_current_state(state); } while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK); @@ -588,6 +592,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) __set_current_state(TASK_RUNNING); list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); + lockevent_inc(rwsem_wlock); return ret; @@ -601,6 +606,7 @@ out_nolock: __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); + lockevent_inc(rwsem_wlock_fail); return ERR_PTR(-EINTR); } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index e586f0d03ad3..ccbf18f560ff 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -24,7 +24,6 @@ void __sched down_read(struct rw_semaphore *sem) rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_read_trylock, __down_read); - rwsem_set_reader_owned(sem); } EXPORT_SYMBOL(down_read); @@ -39,7 +38,6 @@ int __sched down_read_killable(struct rw_semaphore *sem) return -EINTR; } - rwsem_set_reader_owned(sem); return 0; } @@ -52,10 +50,8 @@ int down_read_trylock(struct rw_semaphore *sem) { int ret = __down_read_trylock(sem); - if (ret == 1) { + if (ret == 1) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); - rwsem_set_reader_owned(sem); - } return ret; } @@ -70,7 +66,6 @@ void __sched down_write(struct rw_semaphore *sem) rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); - rwsem_set_owner(sem); } EXPORT_SYMBOL(down_write); @@ -88,7 +83,6 @@ int __sched down_write_killable(struct rw_semaphore *sem) return -EINTR; } - rwsem_set_owner(sem); return 0; } @@ -101,10 +95,8 @@ int down_write_trylock(struct rw_semaphore *sem) { int ret = __down_write_trylock(sem); - if (ret == 1) { + if (ret == 1) rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_); - rwsem_set_owner(sem); - } return ret; } @@ -117,9 +109,7 @@ EXPORT_SYMBOL(down_write_trylock); void up_read(struct rw_semaphore *sem) { rwsem_release(&sem->dep_map, 1, _RET_IP_); - DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED)); - rwsem_clear_reader_owned(sem); __up_read(sem); } @@ -131,9 +121,7 @@ EXPORT_SYMBOL(up_read); void up_write(struct rw_semaphore *sem) { rwsem_release(&sem->dep_map, 1, _RET_IP_); - DEBUG_RWSEMS_WARN_ON(sem->owner != current); - rwsem_clear_owner(sem); __up_write(sem); } @@ -145,9 +133,7 @@ EXPORT_SYMBOL(up_write); void downgrade_write(struct rw_semaphore *sem) { lock_downgrade(&sem->dep_map, _RET_IP_); - DEBUG_RWSEMS_WARN_ON(sem->owner != current); - rwsem_set_reader_owned(sem); __downgrade_write(sem); } @@ -161,7 +147,6 @@ void down_read_nested(struct rw_semaphore *sem, int subclass) rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_read_trylock, __down_read); - rwsem_set_reader_owned(sem); } EXPORT_SYMBOL(down_read_nested); @@ -172,7 +157,6 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest) rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); - rwsem_set_owner(sem); } EXPORT_SYMBOL(_down_write_nest_lock); @@ -193,7 +177,6 @@ void down_write_nested(struct rw_semaphore *sem, int subclass) rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); LOCK_CONTENDED(sem, __down_write_trylock, __down_write); - rwsem_set_owner(sem); } EXPORT_SYMBOL(down_write_nested); @@ -208,7 +191,6 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass) return -EINTR; } - rwsem_set_owner(sem); return 0; } @@ -216,7 +198,8 @@ EXPORT_SYMBOL(down_write_killable_nested); void up_read_non_owner(struct rw_semaphore *sem) { - DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED)); + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED), + sem); __up_read(sem); } diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index bad2bca0268b..64877f5294e3 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -23,15 +23,44 @@ * is involved. Ideally we would like to track all the readers that own * a rwsem, but the overhead is simply too big. */ +#include "lock_events.h" + #define RWSEM_READER_OWNED (1UL << 0) #define RWSEM_ANONYMOUSLY_OWNED (1UL << 1) #ifdef CONFIG_DEBUG_RWSEMS -# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c) +# define DEBUG_RWSEMS_WARN_ON(c, sem) do { \ + if (!debug_locks_silent && \ + WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\ + #c, atomic_long_read(&(sem)->count), \ + (long)((sem)->owner), (long)current, \ + list_empty(&(sem)->wait_list) ? "" : "not ")) \ + debug_locks_off(); \ + } while (0) +#else +# define DEBUG_RWSEMS_WARN_ON(c, sem) +#endif + +/* + * R/W semaphores originally for PPC using the stuff in lib/rwsem.c. + * Adapted largely from include/asm-i386/rwsem.h + * by Paul Mackerras <paulus@samba.org>. + */ + +/* + * the semaphore definition + */ +#ifdef CONFIG_64BIT +# define RWSEM_ACTIVE_MASK 0xffffffffL #else -# define DEBUG_RWSEMS_WARN_ON(c) +# define RWSEM_ACTIVE_MASK 0x0000ffffL #endif +#define RWSEM_ACTIVE_BIAS 0x00000001L +#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) +#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS +#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + #ifdef CONFIG_RWSEM_SPIN_ON_OWNER /* * All writes to owner are protected by WRITE_ONCE() to make sure that @@ -132,3 +161,144 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) { } #endif + +extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); + +/* + * lock for reading + */ +static inline void __down_read(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { + rwsem_down_read_failed(sem); + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & + RWSEM_READER_OWNED), sem); + } else { + rwsem_set_reader_owned(sem); + } +} + +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { + if (IS_ERR(rwsem_down_read_failed_killable(sem))) + return -EINTR; + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & + RWSEM_READER_OWNED), sem); + } else { + rwsem_set_reader_owned(sem); + } + return 0; +} + +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + /* + * Optimize for the case when the rwsem is not locked at all. + */ + long tmp = RWSEM_UNLOCKED_VALUE; + + lockevent_inc(rwsem_rtrylock); + do { + if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, + tmp + RWSEM_ACTIVE_READ_BIAS)) { + rwsem_set_reader_owned(sem); + return 1; + } + } while (tmp >= 0); + return 0; +} + +/* + * lock for writing + */ +static inline void __down_write(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + rwsem_down_write_failed(sem); + rwsem_set_owner(sem); +} + +static inline int __down_write_killable(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + rwsem_set_owner(sem); + return 0; +} + +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + long tmp; + + lockevent_inc(rwsem_wtrylock); + tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); + if (tmp == RWSEM_UNLOCKED_VALUE) { + rwsem_set_owner(sem); + return true; + } + return false; +} + +/* + * unlock after reading + */ +static inline void __up_read(struct rw_semaphore *sem) +{ + long tmp; + + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED), + sem); + rwsem_clear_reader_owned(sem); + tmp = atomic_long_dec_return_release(&sem->count); + if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) + rwsem_wake(sem); +} + +/* + * unlock after writing + */ +static inline void __up_write(struct rw_semaphore *sem) +{ + DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem); + rwsem_clear_owner(sem); + if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count) < 0)) + rwsem_wake(sem); +} + +/* + * downgrade write lock to read lock + */ +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + long tmp; + + /* + * When downgrading from exclusive to shared ownership, + * anything inside the write-locked region cannot leak + * into the read side. In contrast, anything in the + * read-locked region is ok to be re-ordered into the + * write side. As such, rely on RELEASE semantics. + */ + DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem); + tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count); + rwsem_set_reader_owned(sem); + if (tmp < 0) + rwsem_downgrade_wake(sem); +} diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 936f3d14dd6b..0ff08380f531 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -22,6 +22,13 @@ #include <linux/debug_locks.h> #include <linux/export.h> +#ifdef CONFIG_MMIOWB +#ifndef arch_mmiowb_state +DEFINE_PER_CPU(struct mmiowb_state, __mmiowb_state); +EXPORT_PER_CPU_SYMBOL(__mmiowb_state); +#endif +#endif + /* * If lockdep is enabled then we use the non-preemption spin-ops * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 9aa0fccd5d43..399669f7eba8 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock) { debug_spin_lock_before(lock); arch_spin_lock(&lock->raw_lock); + mmiowb_spin_lock(); debug_spin_lock_after(lock); } @@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&lock->raw_lock); - if (ret) + if (ret) { + mmiowb_spin_lock(); debug_spin_lock_after(lock); + } #ifndef CONFIG_SMP /* * Must not happen on UP: @@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock) void do_raw_spin_unlock(raw_spinlock_t *lock) { + mmiowb_spin_unlock(); debug_spin_unlock(lock); arch_spin_unlock(&lock->raw_lock); } diff --git a/kernel/module.c b/kernel/module.c index 0b9aa8ab89f0..a9e1e7f2c224 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex); EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); +/* Work queue for freeing init sections in success case */ +static struct work_struct init_free_wq; +static struct llist_head init_free_list; + #ifdef CONFIG_MODULES_TREE_LOOKUP /* @@ -286,6 +290,11 @@ bool is_module_sig_enforced(void) } EXPORT_SYMBOL(is_module_sig_enforced); +void set_module_sig_enforced(void) +{ + sig_enforce = true; +} + /* Block module loading/unloading? */ int modules_disabled = 0; core_param(nomodule, modules_disabled, bint, 0); @@ -1949,9 +1958,16 @@ void module_enable_ro(const struct module *mod, bool after_init) if (!rodata_enabled) return; + set_vm_flush_reset_perms(mod->core_layout.base); + set_vm_flush_reset_perms(mod->init_layout.base); frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->core_layout, set_memory_x); + frob_rodata(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_ro); if (after_init) @@ -1967,15 +1983,6 @@ static void module_enable_nx(const struct module *mod) frob_writable_data(&mod->init_layout, set_memory_nx); } -static void module_disable_nx(const struct module *mod) -{ - frob_rodata(&mod->core_layout, set_memory_x); - frob_ro_after_init(&mod->core_layout, set_memory_x); - frob_writable_data(&mod->core_layout, set_memory_x); - frob_rodata(&mod->init_layout, set_memory_x); - frob_writable_data(&mod->init_layout, set_memory_x); -} - /* Iterate through all modules and set each module's text as RW */ void set_all_modules_text_rw(void) { @@ -2019,23 +2026,8 @@ void set_all_modules_text_ro(void) } mutex_unlock(&module_mutex); } - -static void disable_ro_nx(const struct module_layout *layout) -{ - if (rodata_enabled) { - frob_text(layout, set_memory_rw); - frob_rodata(layout, set_memory_rw); - frob_ro_after_init(layout, set_memory_rw); - } - frob_rodata(layout, set_memory_x); - frob_ro_after_init(layout, set_memory_x); - frob_writable_data(layout, set_memory_x); -} - #else -static void disable_ro_nx(const struct module_layout *layout) { } static void module_enable_nx(const struct module *mod) { } -static void module_disable_nx(const struct module *mod) { } #endif #ifdef CONFIG_LIVEPATCH @@ -2115,6 +2107,11 @@ static void free_module_elf(struct module *mod) void __weak module_memfree(void *module_region) { + /* + * This memory may be RO, and freeing RO memory in an interrupt is not + * supported by vmalloc. + */ + WARN_ON(in_interrupt()); vfree(module_region); } @@ -2166,7 +2163,6 @@ static void free_module(struct module *mod) mutex_unlock(&module_mutex); /* This may be empty, but that's OK */ - disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); module_memfree(mod->init_layout.base); kfree(mod->args); @@ -2176,7 +2172,6 @@ static void free_module(struct module *mod) lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ - disable_ro_nx(&mod->core_layout); module_memfree(mod->core_layout.base); } @@ -3415,16 +3410,33 @@ static void do_mod_ctors(struct module *mod) /* For freeing module_init on success, in case kallsyms traversing */ struct mod_initfree { - struct rcu_head rcu; + struct llist_node node; void *module_init; }; -static void do_free_init(struct rcu_head *head) +static void do_free_init(struct work_struct *w) +{ + struct llist_node *pos, *n, *list; + struct mod_initfree *initfree; + + list = llist_del_all(&init_free_list); + + synchronize_rcu(); + + llist_for_each_safe(pos, n, list) { + initfree = container_of(pos, struct mod_initfree, node); + module_memfree(initfree->module_init); + kfree(initfree); + } +} + +static int __init modules_wq_init(void) { - struct mod_initfree *m = container_of(head, struct mod_initfree, rcu); - module_memfree(m->module_init); - kfree(m); + INIT_WORK(&init_free_wq, do_free_init); + init_llist_head(&init_free_list); + return 0; } +module_init(modules_wq_init); /* * This is where the real work happens. @@ -3502,7 +3514,6 @@ static noinline int do_init_module(struct module *mod) #endif module_enable_ro(mod, true); mod_tree_remove_init(mod); - disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); mod->init_layout.base = NULL; mod->init_layout.size = 0; @@ -3513,14 +3524,18 @@ static noinline int do_init_module(struct module *mod) * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we * call synchronize_rcu(), but we don't want to slow down the success - * path, so use actual RCU here. + * path. module_memfree() cannot be called in an interrupt, so do the + * work and call synchronize_rcu() in a work queue. + * * Note that module_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to * be cleaned up needs to sync with the queued work - ie * rcu_barrier() */ - call_rcu(&freeinit->rcu, do_free_init); + if (llist_add(&freeinit->node, &init_free_list)) + schedule_work(&init_free_wq); + mutex_unlock(&module_mutex); wake_up_all(&module_wq); @@ -3817,10 +3832,6 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); - /* we can't deallocate the module until we clear memory protection */ - module_disable_ro(mod); - module_disable_nx(mod); - ddebug_cleanup: ftrace_release_mod(mod); dynamic_debug_remove(mod, info->debug); diff --git a/kernel/padata.c b/kernel/padata.c index 3e2633ae3bca..2d2fddbb7a4c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -957,6 +957,7 @@ static struct attribute *padata_default_attrs[] = { ¶llel_cpumask_attr.attr, NULL, }; +ATTRIBUTE_GROUPS(padata_default); static ssize_t padata_sysfs_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -995,7 +996,7 @@ static const struct sysfs_ops padata_sysfs_ops = { static struct kobj_type padata_attr_type = { .sysfs_ops = &padata_sysfs_ops, - .default_attrs = padata_default_attrs, + .default_groups = padata_default_groups, .release = padata_sysfs_release, }; diff --git a/kernel/panic.c b/kernel/panic.c index 0ae0d7332f12..c1fcaad337b7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -318,12 +318,7 @@ void panic(const char *fmt, ...) } #endif #if defined(CONFIG_S390) - { - unsigned long caller; - - caller = (unsigned long)__builtin_return_address(0); - disabled_wait(caller); - } + disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); local_irq_enable(); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index f8fe57d1022e..9bbaaab14b36 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -114,6 +114,15 @@ config PM_SLEEP_SMP depends on PM_SLEEP select HOTPLUG_CPU +config PM_SLEEP_SMP_NONZERO_CPU + def_bool y + depends on PM_SLEEP_SMP + depends on ARCH_SUSPEND_NONZERO_CPU + ---help--- + If an arch can suspend (for suspend, hibernate, kexec, etc) on a + non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This + will allow nohz_full mask to include CPU0. + config PM_AUTOSLEEP bool "Opportunistic sleep" depends on PM_SLEEP diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index abef759de7c8..c8c272df7154 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -14,7 +14,6 @@ #include <linux/export.h> #include <linux/suspend.h> -#include <linux/syscalls.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> @@ -281,7 +280,7 @@ static int create_image(int platform_mode) if (error || hibernation_test(TEST_PLATFORM)) goto Platform_finish; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error || hibernation_test(TEST_CPUS)) goto Enable_cpus; @@ -323,7 +322,7 @@ static int create_image(int platform_mode) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_finish: platform_finish(platform_mode); @@ -417,7 +416,7 @@ int hibernation_snapshot(int platform_mode) int __weak hibernate_resume_nonboot_cpu_disable(void) { - return disable_nonboot_cpus(); + return suspend_disable_secondary_cpus(); } /** @@ -486,7 +485,7 @@ static int resume_target_kernel(bool platform_mode) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Cleanup: platform_restore_cleanup(platform_mode); @@ -564,7 +563,7 @@ int hibernation_platform_enter(void) if (error) goto Platform_finish; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; @@ -586,7 +585,7 @@ int hibernation_platform_enter(void) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_finish: hibernation_ops->finish(); @@ -709,9 +708,7 @@ int hibernate(void) goto Exit; } - pr_info("Syncing filesystems ... \n"); - ksys_sync(); - pr_info("done.\n"); + ksys_sync_helper(); error = freeze_processes(); if (error) diff --git a/kernel/power/main.c b/kernel/power/main.c index 98e76cad128b..4f43e724f6eb 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -16,6 +16,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/suspend.h> +#include <linux/syscalls.h> #include "power.h" @@ -51,6 +52,19 @@ void unlock_system_sleep(void) } EXPORT_SYMBOL_GPL(unlock_system_sleep); +void ksys_sync_helper(void) +{ + ktime_t start; + long elapsed_msecs; + + start = ktime_get(); + ksys_sync(); + elapsed_msecs = ktime_to_ms(ktime_sub(ktime_get(), start)); + pr_info("Filesystems sync: %ld.%03ld seconds\n", + elapsed_msecs / MSEC_PER_SEC, elapsed_msecs % MSEC_PER_SEC); +} +EXPORT_SYMBOL_GPL(ksys_sync_helper); + /* Routines for PM-transition notifications */ static BLOCKING_NOTIFIER_HEAD(pm_chain_head); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f08a1e4ee1d4..bc9558ab1e5b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src) * safe_copy_page - Copy a page in a safe way. * * Check if the page we are going to copy is marked as present in the kernel - * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set - * and in that case kernel_page_present() always returns 'true'). + * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or + * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present() + * always returns 'true'. */ static void safe_copy_page(void *dst, struct page *s_page) { diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 0bd595a0b610..ef908c134b34 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -17,7 +17,6 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/cpuidle.h> -#include <linux/syscalls.h> #include <linux/gfp.h> #include <linux/io.h> #include <linux/kernel.h> @@ -428,7 +427,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (suspend_test(TEST_PLATFORM)) goto Platform_wake; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error || suspend_test(TEST_CPUS)) goto Enable_cpus; @@ -458,7 +457,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) BUG_ON(irqs_disabled()); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_wake: platform_resume_noirq(state); @@ -568,13 +567,11 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_TO_IDLE) s2idle_begin(); -#ifndef CONFIG_SUSPEND_SKIP_SYNC - trace_suspend_resume(TPS("sync_filesystems"), 0, true); - pr_info("Syncing filesystems ... "); - ksys_sync(); - pr_cont("done.\n"); - trace_suspend_resume(TPS("sync_filesystems"), 0, false); -#endif + if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) { + trace_suspend_resume(TPS("sync_filesystems"), 0, true); + ksys_sync_helper(); + trace_suspend_resume(TPS("sync_filesystems"), 0, false); + } pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); pm_suspend_clear_flags(); diff --git a/kernel/power/user.c b/kernel/power/user.c index 2d8b60a3c86b..cb24e840a3e6 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -10,7 +10,6 @@ */ #include <linux/suspend.h> -#include <linux/syscalls.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> @@ -228,9 +227,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (data->frozen) break; - printk("Syncing filesystems ... "); - ksys_sync(); - printk("done.\n"); + ksys_sync_helper(); error = freeze_processes(); if (error) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 6b7654b8001f..02ca827b8fac 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -65,6 +65,7 @@ int console_printk[4] = { CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; +EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 771e93f9c43f..6f357f4fc859 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -29,6 +29,7 @@ #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> +#include <linux/sched/signal.h> /* * Access another process' address space via ptrace. @@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; - case PTRACE_GETSIGMASK: + case PTRACE_GETSIGMASK: { + sigset_t *mask; + if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } - if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + if (test_tsk_restore_sigmask(child)) + mask = &child->saved_sigmask; + else + mask = &child->blocked; + + if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; + } case PTRACE_SETSIGMASK: { sigset_t new_set; @@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request, child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); + clear_tsk_restore_sigmask(child); + ret = 0; break; } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index acee72c0b24b..4b58c907b4b7 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -233,6 +233,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) #ifdef CONFIG_RCU_STALL_COMMON extern int rcu_cpu_stall_suppress; +extern int rcu_cpu_stall_timeout; int rcu_jiffies_till_stall_check(void); #define rcu_ftrace_dump_stall_suppress() \ diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index c29761152874..7a6890b23c5f 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -494,6 +494,10 @@ rcu_perf_cleanup(void) if (torture_cleanup_begin()) return; + if (!cur_ops) { + torture_cleanup_end(); + return; + } if (reader_tasks) { for (i = 0; i < nrealreaders; i++) @@ -614,6 +618,7 @@ rcu_perf_init(void) pr_cont("\n"); WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST)); firsterr = -EINVAL; + cur_ops = NULL; goto unwind; } if (cur_ops->init) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index f14d1b18a74f..efaa5b3f4d3f 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -299,7 +299,6 @@ struct rcu_torture_ops { int irq_capable; int can_boost; int extendables; - int ext_irq_conflict; const char *name; }; @@ -592,12 +591,7 @@ static void srcu_torture_init(void) static void srcu_torture_cleanup(void) { - static DEFINE_TORTURE_RANDOM(rand); - - if (torture_random(&rand) & 0x800) - cleanup_srcu_struct(&srcu_ctld); - else - cleanup_srcu_struct_quiesced(&srcu_ctld); + cleanup_srcu_struct(&srcu_ctld); srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */ } @@ -1160,7 +1154,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) unsigned long randmask2 = randmask1 >> 3; WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); - /* Most of the time lots of bits, half the time only one bit. */ + /* Mostly only one bit (need preemption!), sometimes lots of bits. */ if (!(randmask1 & 0x7)) mask = mask & randmask2; else @@ -1170,10 +1164,6 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) || (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH)))) mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH; - if ((mask & RCUTORTURE_RDR_IRQ) && - !(mask & cur_ops->ext_irq_conflict) && - (oldmask & cur_ops->ext_irq_conflict)) - mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */ return mask ?: RCUTORTURE_RDR_RCU; } @@ -1848,7 +1838,7 @@ static int rcutorture_oom_notify(struct notifier_block *self, WARN(1, "%s invoked upon OOM during forward-progress testing.\n", __func__); rcu_torture_fwd_cb_hist(); - rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2)); + rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2); WRITE_ONCE(rcu_fwd_emergency_stop, true); smp_mb(); /* Emergency stop before free and wait to avoid hangs. */ pr_info("%s: Freed %lu RCU callbacks.\n", @@ -2094,6 +2084,10 @@ rcu_torture_cleanup(void) cur_ops->cb_barrier(); return; } + if (!cur_ops) { + torture_cleanup_end(); + return; + } rcu_torture_barrier_cleanup(); torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); @@ -2267,6 +2261,7 @@ rcu_torture_init(void) pr_cont("\n"); WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST)); firsterr = -EINVAL; + cur_ops = NULL; goto unwind; } if (cur_ops->fqs == NULL && fqs_duration != 0) { diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 5d4a39a6505a..44d6606b8325 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -76,19 +76,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); * Must invoke this after you are finished using a given srcu_struct that * was initialized via init_srcu_struct(), else you leak memory. */ -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) +void cleanup_srcu_struct(struct srcu_struct *ssp) { WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]); - if (quiesced) - WARN_ON(work_pending(&ssp->srcu_work)); - else - flush_work(&ssp->srcu_work); + flush_work(&ssp->srcu_work); WARN_ON(ssp->srcu_gp_running); WARN_ON(ssp->srcu_gp_waiting); WARN_ON(ssp->srcu_cb_head); WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail); } -EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* * Removes the count for the old reader from the appropriate element of diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index a60b8ba9e1ac..9b761e546de8 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -360,8 +360,14 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp) return SRCU_INTERVAL; } -/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */ -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) +/** + * cleanup_srcu_struct - deconstruct a sleep-RCU structure + * @ssp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. + */ +void cleanup_srcu_struct(struct srcu_struct *ssp) { int cpu; @@ -369,24 +375,14 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) return; /* Just leak it! */ if (WARN_ON(srcu_readers_active(ssp))) return; /* Just leak it! */ - if (quiesced) { - if (WARN_ON(delayed_work_pending(&ssp->work))) - return; /* Just leak it! */ - } else { - flush_delayed_work(&ssp->work); - } + flush_delayed_work(&ssp->work); for_each_possible_cpu(cpu) { struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu); - if (quiesced) { - if (WARN_ON(timer_pending(&sdp->delay_work))) - return; /* Just leak it! */ - if (WARN_ON(work_pending(&sdp->work))) - return; /* Just leak it! */ - } else { - del_timer_sync(&sdp->delay_work); - flush_work(&sdp->work); - } + del_timer_sync(&sdp->delay_work); + flush_work(&sdp->work); + if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist))) + return; /* Forgot srcu_barrier(), so just leak it! */ } if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(ssp))) { @@ -397,7 +393,7 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) free_percpu(ssp->sda); ssp->sda = NULL; } -EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* * Counts the new reader in the appropriate per-CPU element of the diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 911bd9076d43..477b4eb44af5 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -52,7 +52,7 @@ void rcu_qs(void) local_irq_save(flags); if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) { rcu_ctrlblk.donetail = rcu_ctrlblk.curtail; - raise_softirq(RCU_SOFTIRQ); + raise_softirq_irqoff(RCU_SOFTIRQ); } local_irq_restore(flags); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index acd6ccf56faf..b4d88a594785 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -102,11 +102,6 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; /* Number of rcu_nodes at specified level. */ int num_rcu_lvl[] = NUM_RCU_LVL_INIT; int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ -/* panic() on RCU Stall sysctl. */ -int sysctl_panic_on_rcu_stall __read_mostly; -/* Commandeer a sysrq key to dump RCU's tree. */ -static bool sysrq_rcu; -module_param(sysrq_rcu, bool, 0444); /* * The rcu_scheduler_active variable is initialized to the value @@ -149,7 +144,7 @@ static void sync_sched_exp_online_cleanup(int cpu); /* rcuc/rcub kthread realtime priority */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; -module_param(kthread_prio, int, 0644); +module_param(kthread_prio, int, 0444); /* Delay in jiffies for grace-period initialization delays, debug only. */ @@ -406,7 +401,7 @@ static bool rcu_kick_kthreads; */ static ulong jiffies_till_sched_qs = ULONG_MAX; module_param(jiffies_till_sched_qs, ulong, 0444); -static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */ +static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */ module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */ /* @@ -424,6 +419,7 @@ static void adjust_jiffies_till_sched_qs(void) WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs); return; } + /* Otherwise, set to third fqs scan, but bound below on large system. */ j = READ_ONCE(jiffies_till_first_fqs) + 2 * READ_ONCE(jiffies_till_next_fqs); if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV) @@ -513,74 +509,6 @@ static const char *gp_state_getname(short gs) } /* - * Show the state of the grace-period kthreads. - */ -void show_rcu_gp_kthreads(void) -{ - int cpu; - unsigned long j; - unsigned long ja; - unsigned long jr; - unsigned long jw; - struct rcu_data *rdp; - struct rcu_node *rnp; - - j = jiffies; - ja = j - READ_ONCE(rcu_state.gp_activity); - jr = j - READ_ONCE(rcu_state.gp_req_activity); - jw = j - READ_ONCE(rcu_state.gp_wake_time); - pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n", - rcu_state.name, gp_state_getname(rcu_state.gp_state), - rcu_state.gp_state, - rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL, - ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq), - (long)READ_ONCE(rcu_state.gp_seq), - (long)READ_ONCE(rcu_get_root()->gp_seq_needed), - READ_ONCE(rcu_state.gp_flags)); - rcu_for_each_node_breadth_first(rnp) { - if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed)) - continue; - pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n", - rnp->grplo, rnp->grphi, (long)rnp->gp_seq, - (long)rnp->gp_seq_needed); - if (!rcu_is_leaf_node(rnp)) - continue; - for_each_leaf_node_possible_cpu(rnp, cpu) { - rdp = per_cpu_ptr(&rcu_data, cpu); - if (rdp->gpwrap || - ULONG_CMP_GE(rcu_state.gp_seq, - rdp->gp_seq_needed)) - continue; - pr_info("\tcpu %d ->gp_seq_needed %ld\n", - cpu, (long)rdp->gp_seq_needed); - } - } - /* sched_show_task(rcu_state.gp_kthread); */ -} -EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); - -/* Dump grace-period-request information due to commandeered sysrq. */ -static void sysrq_show_rcu(int key) -{ - show_rcu_gp_kthreads(); -} - -static struct sysrq_key_op sysrq_rcudump_op = { - .handler = sysrq_show_rcu, - .help_msg = "show-rcu(y)", - .action_msg = "Show RCU tree", - .enable_mask = SYSRQ_ENABLE_DUMP, -}; - -static int __init rcu_sysrq_init(void) -{ - if (sysrq_rcu) - return register_sysrq_key('y', &sysrq_rcudump_op); - return 0; -} -early_initcall(rcu_sysrq_init); - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, @@ -1034,27 +962,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) } /* - * Handler for the irq_work request posted when a grace period has - * gone on for too long, but not yet long enough for an RCU CPU - * stall warning. Set state appropriately, but just complain if - * there is unexpected state on entry. - */ -static void rcu_iw_handler(struct irq_work *iwp) -{ - struct rcu_data *rdp; - struct rcu_node *rnp; - - rdp = container_of(iwp, struct rcu_data, rcu_iw); - rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp); - if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { - rdp->rcu_iw_gp_seq = rnp->gp_seq; - rdp->rcu_iw_pending = false; - } - raw_spin_unlock_rcu_node(rnp); -} - -/* * Return true if the specified CPU has passed through a quiescent * state by virtue of being in or having passed through an dynticks * idle state since the last call to dyntick_save_progress_counter() @@ -1167,295 +1074,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 0; } -static void record_gp_stall_check_time(void) -{ - unsigned long j = jiffies; - unsigned long j1; - - rcu_state.gp_start = j; - j1 = rcu_jiffies_till_stall_check(); - /* Record ->gp_start before ->jiffies_stall. */ - smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */ - rcu_state.jiffies_resched = j + j1 / 2; - rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs); -} - -/* - * Complain about starvation of grace-period kthread. - */ -static void rcu_check_gp_kthread_starvation(void) -{ - struct task_struct *gpk = rcu_state.gp_kthread; - unsigned long j; - - j = jiffies - READ_ONCE(rcu_state.gp_activity); - if (j > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", - rcu_state.name, j, - (long)rcu_seq_current(&rcu_state.gp_seq), - READ_ONCE(rcu_state.gp_flags), - gp_state_getname(rcu_state.gp_state), rcu_state.gp_state, - gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1); - if (gpk) { - pr_err("RCU grace-period kthread stack dump:\n"); - sched_show_task(gpk); - wake_up_process(gpk); - } - } -} - -/* - * Dump stacks of all tasks running on stalled CPUs. First try using - * NMIs, but fall back to manual remote stack tracing on architectures - * that don't support NMI-based stack dumps. The NMI-triggered stack - * traces are more accurate because they are printed by the target CPU. - */ -static void rcu_dump_cpu_stacks(void) -{ - int cpu; - unsigned long flags; - struct rcu_node *rnp; - - rcu_for_each_leaf_node(rnp) { - raw_spin_lock_irqsave_rcu_node(rnp, flags); - for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) - if (!trigger_single_cpu_backtrace(cpu)) - dump_cpu_task(cpu); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } -} - -/* - * If too much time has passed in the current grace period, and if - * so configured, go kick the relevant kthreads. - */ -static void rcu_stall_kick_kthreads(void) -{ - unsigned long j; - - if (!rcu_kick_kthreads) - return; - j = READ_ONCE(rcu_state.jiffies_kick_kthreads); - if (time_after(jiffies, j) && rcu_state.gp_kthread && - (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) { - WARN_ONCE(1, "Kicking %s grace-period kthread\n", - rcu_state.name); - rcu_ftrace_dump(DUMP_ALL); - wake_up_process(rcu_state.gp_kthread); - WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ); - } -} - -static void panic_on_rcu_stall(void) -{ - if (sysctl_panic_on_rcu_stall) - panic("RCU Stall\n"); -} - -static void print_other_cpu_stall(unsigned long gp_seq) -{ - int cpu; - unsigned long flags; - unsigned long gpa; - unsigned long j; - int ndetected = 0; - struct rcu_node *rnp = rcu_get_root(); - long totqlen = 0; - - /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(); - if (rcu_cpu_stall_suppress) - return; - - /* - * OK, time to rat on our buddy... - * See Documentation/RCU/stallwarn.txt for info on how to debug - * RCU CPU stall warnings. - */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name); - print_cpu_stall_info_begin(); - rcu_for_each_leaf_node(rnp) { - raw_spin_lock_irqsave_rcu_node(rnp, flags); - ndetected += rcu_print_task_stall(rnp); - if (rnp->qsmask != 0) { - for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { - print_cpu_stall_info(cpu); - ndetected++; - } - } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } - - print_cpu_stall_info_end(); - for_each_possible_cpu(cpu) - totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", - smp_processor_id(), (long)(jiffies - rcu_state.gp_start), - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); - if (ndetected) { - rcu_dump_cpu_stacks(); - - /* Complain about tasks blocking the grace period. */ - rcu_print_detail_task_stall(); - } else { - if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) { - pr_err("INFO: Stall ended before state dump start\n"); - } else { - j = jiffies; - gpa = READ_ONCE(rcu_state.gp_activity); - pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", - rcu_state.name, j - gpa, j, gpa, - READ_ONCE(jiffies_till_next_fqs), - rcu_get_root()->qsmask); - /* In this case, the current CPU might be at fault. */ - sched_show_task(current); - } - } - /* Rewrite if needed in case of slow consoles. */ - if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) - WRITE_ONCE(rcu_state.jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - - rcu_check_gp_kthread_starvation(); - - panic_on_rcu_stall(); - - rcu_force_quiescent_state(); /* Kick them all. */ -} - -static void print_cpu_stall(void) -{ - int cpu; - unsigned long flags; - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - struct rcu_node *rnp = rcu_get_root(); - long totqlen = 0; - - /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(); - if (rcu_cpu_stall_suppress) - return; - - /* - * OK, time to rat on ourselves... - * See Documentation/RCU/stallwarn.txt for info on how to debug - * RCU CPU stall warnings. - */ - pr_err("INFO: %s self-detected stall on CPU", rcu_state.name); - print_cpu_stall_info_begin(); - raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); - print_cpu_stall_info(smp_processor_id()); - raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); - print_cpu_stall_info_end(); - for_each_possible_cpu(cpu) - totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n", - jiffies - rcu_state.gp_start, - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); - - rcu_check_gp_kthread_starvation(); - - rcu_dump_cpu_stacks(); - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - /* Rewrite if needed in case of slow consoles. */ - if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) - WRITE_ONCE(rcu_state.jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - - panic_on_rcu_stall(); - - /* - * Attempt to revive the RCU machinery by forcing a context switch. - * - * A context switch would normally allow the RCU state machine to make - * progress and it could be we're stuck in kernel space without context - * switches for an entirely unreasonable amount of time. - */ - set_tsk_need_resched(current); - set_preempt_need_resched(); -} - -static void check_cpu_stall(struct rcu_data *rdp) -{ - unsigned long gs1; - unsigned long gs2; - unsigned long gps; - unsigned long j; - unsigned long jn; - unsigned long js; - struct rcu_node *rnp; - - if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) || - !rcu_gp_in_progress()) - return; - rcu_stall_kick_kthreads(); - j = jiffies; - - /* - * Lots of memory barriers to reject false positives. - * - * The idea is to pick up rcu_state.gp_seq, then - * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally - * another copy of rcu_state.gp_seq. These values are updated in - * the opposite order with memory barriers (or equivalent) during - * grace-period initialization and cleanup. Now, a false positive - * can occur if we get an new value of rcu_state.gp_start and a old - * value of rcu_state.jiffies_stall. But given the memory barriers, - * the only way that this can happen is if one grace period ends - * and another starts between these two fetches. This is detected - * by comparing the second fetch of rcu_state.gp_seq with the - * previous fetch from rcu_state.gp_seq. - * - * Given this check, comparisons of jiffies, rcu_state.jiffies_stall, - * and rcu_state.gp_start suffice to forestall false positives. - */ - gs1 = READ_ONCE(rcu_state.gp_seq); - smp_rmb(); /* Pick up ->gp_seq first... */ - js = READ_ONCE(rcu_state.jiffies_stall); - smp_rmb(); /* ...then ->jiffies_stall before the rest... */ - gps = READ_ONCE(rcu_state.gp_start); - smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ - gs2 = READ_ONCE(rcu_state.gp_seq); - if (gs1 != gs2 || - ULONG_CMP_LT(j, js) || - ULONG_CMP_GE(gps, js)) - return; /* No stall or GP completed since entering function. */ - rnp = rdp->mynode; - jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; - if (rcu_gp_in_progress() && - (READ_ONCE(rnp->qsmask) & rdp->grpmask) && - cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { - - /* We haven't checked in, so go dump stack. */ - print_cpu_stall(); - - } else if (rcu_gp_in_progress() && - ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && - cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { - - /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(gs2); - } -} - -/** - * rcu_cpu_stall_reset - prevent further stall warnings in current grace period - * - * Set the stall-warning timeout way off into the future, thus preventing - * any RCU CPU stall-warning messages from appearing in the current set of - * RCU grace periods. - * - * The caller must disable hard irqs. - */ -void rcu_cpu_stall_reset(void) -{ - WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2); -} - /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long gp_seq_req, const char *s) @@ -1585,7 +1203,7 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) static void rcu_gp_kthread_wake(void) { if ((current == rcu_state.gp_kthread && - !in_interrupt() && !in_serving_softirq()) || + !in_irq() && !in_serving_softirq()) || !READ_ONCE(rcu_state.gp_flags) || !rcu_state.gp_kthread) return; @@ -2295,11 +1913,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) return; } mask = rdp->grpmask; + rdp->core_needs_qs = false; if ((rnp->qsmask & mask) == 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } else { - rdp->core_needs_qs = false; - /* * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. @@ -2548,11 +2165,11 @@ void rcu_sched_clock_irq(int user) } /* - * Scan the leaf rcu_node structures, processing dyntick state for any that - * have not yet encountered a quiescent state, using the function specified. - * Also initiate boosting for any threads blocked on the root rcu_node. - * - * The caller must have suppressed start of new grace periods. + * Scan the leaf rcu_node structures. For each structure on which all + * CPUs have reported a quiescent state and on which there are tasks + * blocking the current grace period, initiate RCU priority boosting. + * Otherwise, invoke the specified function to check dyntick state for + * each CPU that has not yet reported a quiescent state. */ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) { @@ -2635,101 +2252,6 @@ void rcu_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); -/* - * This function checks for grace-period requests that fail to motivate - * RCU to come out of its idle mode. - */ -void -rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp, - const unsigned long gpssdelay) -{ - unsigned long flags; - unsigned long j; - struct rcu_node *rnp_root = rcu_get_root(); - static atomic_t warned = ATOMIC_INIT(0); - - if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() || - ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) - return; - j = jiffies; /* Expensive access, and in common case don't get here. */ - if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || - time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || - atomic_read(&warned)) - return; - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - j = jiffies; - if (rcu_gp_in_progress() || - ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || - time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || - time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || - atomic_read(&warned)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - /* Hold onto the leaf lock to make others see warned==1. */ - - if (rnp_root != rnp) - raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ - j = jiffies; - if (rcu_gp_in_progress() || - ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || - time_before(j, rcu_state.gp_req_activity + gpssdelay) || - time_before(j, rcu_state.gp_activity + gpssdelay) || - atomic_xchg(&warned, 1)) { - raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - WARN_ON(1); - if (rnp_root != rnp) - raw_spin_unlock_rcu_node(rnp_root); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - show_rcu_gp_kthreads(); -} - -/* - * Do a forward-progress check for rcutorture. This is normally invoked - * due to an OOM event. The argument "j" gives the time period during - * which rcutorture would like progress to have been made. - */ -void rcu_fwd_progress_check(unsigned long j) -{ - unsigned long cbs; - int cpu; - unsigned long max_cbs = 0; - int max_cpu = -1; - struct rcu_data *rdp; - - if (rcu_gp_in_progress()) { - pr_info("%s: GP age %lu jiffies\n", - __func__, jiffies - rcu_state.gp_start); - show_rcu_gp_kthreads(); - } else { - pr_info("%s: Last GP end %lu jiffies ago\n", - __func__, jiffies - rcu_state.gp_end); - preempt_disable(); - rdp = this_cpu_ptr(&rcu_data); - rcu_check_gp_start_stall(rdp->mynode, rdp, j); - preempt_enable(); - } - for_each_possible_cpu(cpu) { - cbs = rcu_get_n_cbs_cpu(cpu); - if (!cbs) - continue; - if (max_cpu < 0) - pr_info("%s: callbacks", __func__); - pr_cont(" %d: %lu", cpu, cbs); - if (cbs <= max_cbs) - continue; - max_cbs = cbs; - max_cpu = cpu; - } - if (max_cpu >= 0) - pr_cont("\n"); -} -EXPORT_SYMBOL_GPL(rcu_fwd_progress_check); - /* Perform RCU core processing work for the current CPU. */ static __latent_entropy void rcu_core(struct softirq_action *unused) { @@ -2870,7 +2392,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) * Use rcu:rcu_callback trace event to find the previous * time callback was passed to __call_rcu(). */ - WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pF()!!!\n", + WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n", head, head->func); WRITE_ONCE(head->func, rcu_leak_callback); return; @@ -3559,13 +3081,11 @@ static int rcu_pm_notify(struct notifier_block *self, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: - if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ - rcu_expedite_gp(); + rcu_expedite_gp(); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: - if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ - rcu_unexpedite_gp(); + rcu_unexpedite_gp(); break; default: break; @@ -3742,8 +3262,7 @@ static void __init rcu_init_geometry(void) jiffies_till_first_fqs = d; if (jiffies_till_next_fqs == ULONG_MAX) jiffies_till_next_fqs = d; - if (jiffies_till_sched_qs == ULONG_MAX) - adjust_jiffies_till_sched_qs(); + adjust_jiffies_till_sched_qs(); /* If the compile-time values are accurate, just leave. */ if (rcu_fanout_leaf == RCU_FANOUT_LEAF && @@ -3858,5 +3377,6 @@ void __init rcu_init(void) srcu_init(); } +#include "tree_stall.h" #include "tree_exp.h" #include "tree_plugin.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index bb4f995f2d3f..e253d11af3c4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -393,15 +393,13 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name; int rcu_dynticks_snap(struct rcu_data *rdp); -/* Forward declarations for rcutree_plugin.h */ +/* Forward declarations for tree_plugin.h */ static void rcu_bootup_announce(void); static void rcu_qs(void); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_print_detail_task_stall(void); -static int rcu_print_task_stall(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); @@ -418,9 +416,6 @@ static void rcu_prepare_for_idle(void); static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static bool rcu_preempt_need_deferred_qs(struct task_struct *t); static void rcu_preempt_deferred_qs(struct task_struct *t); -static void print_cpu_stall_info_begin(void); -static void print_cpu_stall_info(int cpu); -static void print_cpu_stall_info_end(void); static void zero_cpu_stall_ticks(struct rcu_data *rdp); static bool rcu_nocb_cpu_needs_barrier(int cpu); static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); @@ -445,3 +440,10 @@ static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(void); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); + +/* Forward declarations for tree_stall.h */ +static void record_gp_stall_check_time(void); +static void rcu_iw_handler(struct irq_work *iwp); +static void check_cpu_stall(struct rcu_data *rdp); +static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp, + const unsigned long gpssdelay); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 4c2a0189e748..9c990df880d1 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -10,6 +10,7 @@ #include <linux/lockdep.h> static void rcu_exp_handler(void *unused); +static int rcu_print_task_exp_stall(struct rcu_node *rnp); /* * Record the start of an expedited grace period. @@ -633,7 +634,7 @@ static void rcu_exp_handler(void *unused) raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmask & rdp->grpmask) { rdp->deferred_qs = true; - WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true); + t->rcu_read_unlock_special.b.exp_hint = true; } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; @@ -648,7 +649,7 @@ static void rcu_exp_handler(void *unused) * * If the CPU is fully enabled (or if some buggy RCU-preempt * read-side critical section is being used from idle), just - * invoke rcu_preempt_defer_qs() to immediately report the + * invoke rcu_preempt_deferred_qs() to immediately report the * quiescent state. We cannot use rcu_read_unlock_special() * because we are in an interrupt handler, which will cause that * function to take an early exit without doing anything. @@ -670,6 +671,27 @@ static void sync_sched_exp_online_cleanup(int cpu) { } +/* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, printing out the tid of each that is blocking the current + * expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + struct task_struct *t; + int ndetected = 0; + + if (!rnp->exp_tasks) + return 0; + t = list_entry(rnp->exp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + pr_cont(" P%d", t->pid); + ndetected++; + } + return ndetected; +} + #else /* #ifdef CONFIG_PREEMPT_RCU */ /* Invoked on each online non-idle CPU for expedited quiescent state. */ @@ -709,6 +731,16 @@ static void sync_sched_exp_online_cleanup(int cpu) WARN_ON_ONCE(ret); } +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections that are + * blocking the current expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + return 0; +} + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /** diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 97dba50f6fb2..1102765f91fd 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -285,7 +285,7 @@ static void rcu_qs(void) TPS("cpuqs")); __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */ - current->rcu_read_unlock_special.b.need_qs = false; + WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false); } } @@ -643,100 +643,6 @@ static void rcu_read_unlock_special(struct task_struct *t) } /* - * Dump detailed information for all tasks blocking the current RCU - * grace period on the specified rcu_node structure. - */ -static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) -{ - unsigned long flags; - struct task_struct *t; - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (!rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - t = list_entry(rnp->gp_tasks->prev, - struct task_struct, rcu_node_entry); - list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { - /* - * We could be printing a lot while holding a spinlock. - * Avoid triggering hard lockup. - */ - touch_nmi_watchdog(); - sched_show_task(t); - } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); -} - -/* - * Dump detailed information for all tasks blocking the current RCU - * grace period. - */ -static void rcu_print_detail_task_stall(void) -{ - struct rcu_node *rnp = rcu_get_root(); - - rcu_print_detail_task_stall_rnp(rnp); - rcu_for_each_leaf_node(rnp) - rcu_print_detail_task_stall_rnp(rnp); -} - -static void rcu_print_task_stall_begin(struct rcu_node *rnp) -{ - pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", - rnp->level, rnp->grplo, rnp->grphi); -} - -static void rcu_print_task_stall_end(void) -{ - pr_cont("\n"); -} - -/* - * Scan the current list of tasks blocked within RCU read-side critical - * sections, printing out the tid of each. - */ -static int rcu_print_task_stall(struct rcu_node *rnp) -{ - struct task_struct *t; - int ndetected = 0; - - if (!rcu_preempt_blocked_readers_cgp(rnp)) - return 0; - rcu_print_task_stall_begin(rnp); - t = list_entry(rnp->gp_tasks->prev, - struct task_struct, rcu_node_entry); - list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { - pr_cont(" P%d", t->pid); - ndetected++; - } - rcu_print_task_stall_end(); - return ndetected; -} - -/* - * Scan the current list of tasks blocked within RCU read-side critical - * sections, printing out the tid of each that is blocking the current - * expedited grace period. - */ -static int rcu_print_task_exp_stall(struct rcu_node *rnp) -{ - struct task_struct *t; - int ndetected = 0; - - if (!rnp->exp_tasks) - return 0; - t = list_entry(rnp->exp_tasks->prev, - struct task_struct, rcu_node_entry); - list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { - pr_cont(" P%d", t->pid); - ndetected++; - } - return ndetected; -} - -/* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be @@ -804,19 +710,25 @@ static void rcu_flavor_sched_clock_irq(int user) /* * Check for a task exiting while in a preemptible-RCU read-side - * critical section, clean up if so. No need to issue warnings, - * as debug_check_no_locks_held() already does this if lockdep - * is enabled. + * critical section, clean up if so. No need to issue warnings, as + * debug_check_no_locks_held() already does this if lockdep is enabled. + * Besides, if this function does anything other than just immediately + * return, there was a bug of some sort. Spewing warnings from this + * function is like as not to simply obscure important prior warnings. */ void exit_rcu(void) { struct task_struct *t = current; - if (likely(list_empty(¤t->rcu_node_entry))) + if (unlikely(!list_empty(¤t->rcu_node_entry))) { + t->rcu_read_lock_nesting = 1; + barrier(); + WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true); + } else if (unlikely(t->rcu_read_lock_nesting)) { + t->rcu_read_lock_nesting = 1; + } else { return; - t->rcu_read_lock_nesting = 1; - barrier(); - t->rcu_read_unlock_special.b.blocked = true; + } __rcu_read_unlock(); rcu_preempt_deferred_qs(current); } @@ -980,33 +892,6 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) static void rcu_preempt_deferred_qs(struct task_struct *t) { } /* - * Because preemptible RCU does not exist, we never have to check for - * tasks blocked within RCU read-side critical sections. - */ -static void rcu_print_detail_task_stall(void) -{ -} - -/* - * Because preemptible RCU does not exist, we never have to check for - * tasks blocked within RCU read-side critical sections. - */ -static int rcu_print_task_stall(struct rcu_node *rnp) -{ - return 0; -} - -/* - * Because preemptible RCU does not exist, we never have to check for - * tasks blocked within RCU read-side critical sections that are - * blocking the current expedited grace period. - */ -static int rcu_print_task_exp_stall(struct rcu_node *rnp) -{ - return 0; -} - -/* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. @@ -1185,8 +1070,6 @@ static int rcu_boost_kthread(void *arg) static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { - struct task_struct *t; - raw_lockdep_assert_held_rcu_node(rnp); if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -1200,9 +1083,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (rnp->exp_tasks == NULL) rnp->boost_tasks = rnp->gp_tasks; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - t = rnp->boost_kthread_task; - if (t) - rcu_wake_cond(t, rnp->boost_kthread_status); + rcu_wake_cond(rnp->boost_kthread_task, + rnp->boost_kthread_status); } else { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -1649,98 +1531,6 @@ static void rcu_cleanup_after_idle(void) #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ -#ifdef CONFIG_RCU_FAST_NO_HZ - -static void print_cpu_stall_fast_no_hz(char *cp, int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - - sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c", - rdp->last_accelerate & 0xffff, jiffies & 0xffff, - ".l"[rdp->all_lazy], - ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)], - ".D"[!rdp->tick_nohz_enabled_snap]); -} - -#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ - -static void print_cpu_stall_fast_no_hz(char *cp, int cpu) -{ - *cp = '\0'; -} - -#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ - -/* Initiate the stall-info list. */ -static void print_cpu_stall_info_begin(void) -{ - pr_cont("\n"); -} - -/* - * Print out diagnostic information for the specified stalled CPU. - * - * If the specified CPU is aware of the current RCU grace period, then - * print the number of scheduling clock interrupts the CPU has taken - * during the time that it has been aware. Otherwise, print the number - * of RCU grace periods that this CPU is ignorant of, for example, "1" - * if the CPU was aware of the previous grace period. - * - * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. - */ -static void print_cpu_stall_info(int cpu) -{ - unsigned long delta; - char fast_no_hz[72]; - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - char *ticks_title; - unsigned long ticks_value; - - /* - * We could be printing a lot while holding a spinlock. Avoid - * triggering hard lockup. - */ - touch_nmi_watchdog(); - - ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq); - if (ticks_value) { - ticks_title = "GPs behind"; - } else { - ticks_title = "ticks this GP"; - ticks_value = rdp->ticks_this_gp; - } - print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); - pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", - cpu, - "O."[!!cpu_online(cpu)], - "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], - "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], - !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' : - rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : - "!."[!delta], - ticks_value, ticks_title, - rcu_dynticks_snap(rdp) & 0xfff, - rdp->dynticks_nesting, rdp->dynticks_nmi_nesting, - rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), - READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, - fast_no_hz); -} - -/* Terminate the stall-info list. */ -static void print_cpu_stall_info_end(void) -{ - pr_err("\t"); -} - -/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */ -static void zero_cpu_stall_ticks(struct rcu_data *rdp) -{ - rdp->ticks_this_gp = 0; - rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id()); - WRITE_ONCE(rdp->last_fqs_resched, jiffies); -} - #ifdef CONFIG_RCU_NOCB_CPU /* @@ -1766,11 +1556,22 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp) */ -/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */ +/* + * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. + * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a + * comma-separated list of CPUs and/or CPU ranges. If an invalid list is + * given, a warning is emitted and all CPUs are offloaded. + */ static int __init rcu_nocb_setup(char *str) { alloc_bootmem_cpumask_var(&rcu_nocb_mask); - cpulist_parse(str, rcu_nocb_mask); + if (!strcasecmp(str, "all")) + cpumask_setall(rcu_nocb_mask); + else + if (cpulist_parse(str, rcu_nocb_mask)) { + pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n"); + cpumask_setall(rcu_nocb_mask); + } return 1; } __setup("rcu_nocbs=", rcu_nocb_setup); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h new file mode 100644 index 000000000000..f65a73a97323 --- /dev/null +++ b/kernel/rcu/tree_stall.h @@ -0,0 +1,709 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * RCU CPU stall warnings for normal RCU grace periods + * + * Copyright IBM Corporation, 2019 + * + * Author: Paul E. McKenney <paulmck@linux.ibm.com> + */ + +////////////////////////////////////////////////////////////////////////////// +// +// Controlling CPU stall warnings, including delay calculation. + +/* panic() on RCU Stall sysctl. */ +int sysctl_panic_on_rcu_stall __read_mostly; + +#ifdef CONFIG_PROVE_RCU +#define RCU_STALL_DELAY_DELTA (5 * HZ) +#else +#define RCU_STALL_DELAY_DELTA 0 +#endif + +/* Limit-check stall timeouts specified at boottime and runtime. */ +int rcu_jiffies_till_stall_check(void) +{ + int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout); + + /* + * Limit check must be consistent with the Kconfig limits + * for CONFIG_RCU_CPU_STALL_TIMEOUT. + */ + if (till_stall_check < 3) { + WRITE_ONCE(rcu_cpu_stall_timeout, 3); + till_stall_check = 3; + } else if (till_stall_check > 300) { + WRITE_ONCE(rcu_cpu_stall_timeout, 300); + till_stall_check = 300; + } + return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; +} +EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check); + +/* Don't do RCU CPU stall warnings during long sysrq printouts. */ +void rcu_sysrq_start(void) +{ + if (!rcu_cpu_stall_suppress) + rcu_cpu_stall_suppress = 2; +} + +void rcu_sysrq_end(void) +{ + if (rcu_cpu_stall_suppress == 2) + rcu_cpu_stall_suppress = 0; +} + +/* Don't print RCU CPU stall warnings during a kernel panic. */ +static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) +{ + rcu_cpu_stall_suppress = 1; + return NOTIFY_DONE; +} + +static struct notifier_block rcu_panic_block = { + .notifier_call = rcu_panic, +}; + +static int __init check_cpu_stall_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); + return 0; +} +early_initcall(check_cpu_stall_init); + +/* If so specified via sysctl, panic, yielding cleaner stall-warning output. */ +static void panic_on_rcu_stall(void) +{ + if (sysctl_panic_on_rcu_stall) + panic("RCU Stall\n"); +} + +/** + * rcu_cpu_stall_reset - prevent further stall warnings in current grace period + * + * Set the stall-warning timeout way off into the future, thus preventing + * any RCU CPU stall-warning messages from appearing in the current set of + * RCU grace periods. + * + * The caller must disable hard irqs. + */ +void rcu_cpu_stall_reset(void) +{ + WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2); +} + +////////////////////////////////////////////////////////////////////////////// +// +// Interaction with RCU grace periods + +/* Start of new grace period, so record stall time (and forcing times). */ +static void record_gp_stall_check_time(void) +{ + unsigned long j = jiffies; + unsigned long j1; + + rcu_state.gp_start = j; + j1 = rcu_jiffies_till_stall_check(); + /* Record ->gp_start before ->jiffies_stall. */ + smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */ + rcu_state.jiffies_resched = j + j1 / 2; + rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs); +} + +/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */ +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ + rdp->ticks_this_gp = 0; + rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id()); + WRITE_ONCE(rdp->last_fqs_resched, jiffies); +} + +/* + * If too much time has passed in the current grace period, and if + * so configured, go kick the relevant kthreads. + */ +static void rcu_stall_kick_kthreads(void) +{ + unsigned long j; + + if (!rcu_kick_kthreads) + return; + j = READ_ONCE(rcu_state.jiffies_kick_kthreads); + if (time_after(jiffies, j) && rcu_state.gp_kthread && + (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) { + WARN_ONCE(1, "Kicking %s grace-period kthread\n", + rcu_state.name); + rcu_ftrace_dump(DUMP_ALL); + wake_up_process(rcu_state.gp_kthread); + WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ); + } +} + +/* + * Handler for the irq_work request posted about halfway into the RCU CPU + * stall timeout, and used to detect excessive irq disabling. Set state + * appropriately, but just complain if there is unexpected state on entry. + */ +static void rcu_iw_handler(struct irq_work *iwp) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + + rdp = container_of(iwp, struct rcu_data, rcu_iw); + rnp = rdp->mynode; + raw_spin_lock_rcu_node(rnp); + if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { + rdp->rcu_iw_gp_seq = rnp->gp_seq; + rdp->rcu_iw_pending = false; + } + raw_spin_unlock_rcu_node(rnp); +} + +////////////////////////////////////////////////////////////////////////////// +// +// Printing RCU CPU stall warnings + +#ifdef CONFIG_PREEMPT + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period on the specified rcu_node structure. + */ +static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ + unsigned long flags; + struct task_struct *t; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (!rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + t = list_entry(rnp->gp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + /* + * We could be printing a lot while holding a spinlock. + * Avoid triggering hard lockup. + */ + touch_nmi_watchdog(); + sched_show_task(t); + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +/* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, printing out the tid of each. + */ +static int rcu_print_task_stall(struct rcu_node *rnp) +{ + struct task_struct *t; + int ndetected = 0; + + if (!rcu_preempt_blocked_readers_cgp(rnp)) + return 0; + pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", + rnp->level, rnp->grplo, rnp->grphi); + t = list_entry(rnp->gp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + pr_cont(" P%d", t->pid); + ndetected++; + } + pr_cont("\n"); + return ndetected; +} + +#else /* #ifdef CONFIG_PREEMPT */ + +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ +} + +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static int rcu_print_task_stall(struct rcu_node *rnp) +{ + return 0; +} +#endif /* #else #ifdef CONFIG_PREEMPT */ + +/* + * Dump stacks of all tasks running on stalled CPUs. First try using + * NMIs, but fall back to manual remote stack tracing on architectures + * that don't support NMI-based stack dumps. The NMI-triggered stack + * traces are more accurate because they are printed by the target CPU. + */ +static void rcu_dump_cpu_stacks(void) +{ + int cpu; + unsigned long flags; + struct rcu_node *rnp; + + rcu_for_each_leaf_node(rnp) { + raw_spin_lock_irqsave_rcu_node(rnp, flags); + for_each_leaf_node_possible_cpu(rnp, cpu) + if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) + if (!trigger_single_cpu_backtrace(cpu)) + dump_cpu_task(cpu); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } +} + +#ifdef CONFIG_RCU_FAST_NO_HZ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + + sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c", + rdp->last_accelerate & 0xffff, jiffies & 0xffff, + ".l"[rdp->all_lazy], + ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)], + ".D"[!!rdp->tick_nohz_enabled_snap]); +} + +#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + *cp = '\0'; +} + +#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ + +/* + * Print out diagnostic information for the specified stalled CPU. + * + * If the specified CPU is aware of the current RCU grace period, then + * print the number of scheduling clock interrupts the CPU has taken + * during the time that it has been aware. Otherwise, print the number + * of RCU grace periods that this CPU is ignorant of, for example, "1" + * if the CPU was aware of the previous grace period. + * + * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. + */ +static void print_cpu_stall_info(int cpu) +{ + unsigned long delta; + char fast_no_hz[72]; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + char *ticks_title; + unsigned long ticks_value; + + /* + * We could be printing a lot while holding a spinlock. Avoid + * triggering hard lockup. + */ + touch_nmi_watchdog(); + + ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq); + if (ticks_value) { + ticks_title = "GPs behind"; + } else { + ticks_title = "ticks this GP"; + ticks_value = rdp->ticks_this_gp; + } + print_cpu_stall_fast_no_hz(fast_no_hz, cpu); + delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", + cpu, + "O."[!!cpu_online(cpu)], + "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], + "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], + !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' : + rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : + "!."[!delta], + ticks_value, ticks_title, + rcu_dynticks_snap(rdp) & 0xfff, + rdp->dynticks_nesting, rdp->dynticks_nmi_nesting, + rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), + READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, + fast_no_hz); +} + +/* Complain about starvation of grace-period kthread. */ +static void rcu_check_gp_kthread_starvation(void) +{ + struct task_struct *gpk = rcu_state.gp_kthread; + unsigned long j; + + j = jiffies - READ_ONCE(rcu_state.gp_activity); + if (j > 2 * HZ) { + pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", + rcu_state.name, j, + (long)rcu_seq_current(&rcu_state.gp_seq), + READ_ONCE(rcu_state.gp_flags), + gp_state_getname(rcu_state.gp_state), rcu_state.gp_state, + gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1); + if (gpk) { + pr_err("RCU grace-period kthread stack dump:\n"); + sched_show_task(gpk); + wake_up_process(gpk); + } + } +} + +static void print_other_cpu_stall(unsigned long gp_seq) +{ + int cpu; + unsigned long flags; + unsigned long gpa; + unsigned long j; + int ndetected = 0; + struct rcu_node *rnp; + long totqlen = 0; + + /* Kick and suppress, if so configured. */ + rcu_stall_kick_kthreads(); + if (rcu_cpu_stall_suppress) + return; + + /* + * OK, time to rat on our buddy... + * See Documentation/RCU/stallwarn.txt for info on how to debug + * RCU CPU stall warnings. + */ + pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); + rcu_for_each_leaf_node(rnp) { + raw_spin_lock_irqsave_rcu_node(rnp, flags); + ndetected += rcu_print_task_stall(rnp); + if (rnp->qsmask != 0) { + for_each_leaf_node_possible_cpu(rnp, cpu) + if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { + print_cpu_stall_info(cpu); + ndetected++; + } + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + + for_each_possible_cpu(cpu) + totqlen += rcu_get_n_cbs_cpu(cpu); + pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", + smp_processor_id(), (long)(jiffies - rcu_state.gp_start), + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + if (ndetected) { + rcu_dump_cpu_stacks(); + + /* Complain about tasks blocking the grace period. */ + rcu_for_each_leaf_node(rnp) + rcu_print_detail_task_stall_rnp(rnp); + } else { + if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) { + pr_err("INFO: Stall ended before state dump start\n"); + } else { + j = jiffies; + gpa = READ_ONCE(rcu_state.gp_activity); + pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", + rcu_state.name, j - gpa, j, gpa, + READ_ONCE(jiffies_till_next_fqs), + rcu_get_root()->qsmask); + /* In this case, the current CPU might be at fault. */ + sched_show_task(current); + } + } + /* Rewrite if needed in case of slow consoles. */ + if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) + WRITE_ONCE(rcu_state.jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); + + rcu_check_gp_kthread_starvation(); + + panic_on_rcu_stall(); + + rcu_force_quiescent_state(); /* Kick them all. */ +} + +static void print_cpu_stall(void) +{ + int cpu; + unsigned long flags; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + struct rcu_node *rnp = rcu_get_root(); + long totqlen = 0; + + /* Kick and suppress, if so configured. */ + rcu_stall_kick_kthreads(); + if (rcu_cpu_stall_suppress) + return; + + /* + * OK, time to rat on ourselves... + * See Documentation/RCU/stallwarn.txt for info on how to debug + * RCU CPU stall warnings. + */ + pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); + raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); + print_cpu_stall_info(smp_processor_id()); + raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); + for_each_possible_cpu(cpu) + totqlen += rcu_get_n_cbs_cpu(cpu); + pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n", + jiffies - rcu_state.gp_start, + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + + rcu_check_gp_kthread_starvation(); + + rcu_dump_cpu_stacks(); + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + /* Rewrite if needed in case of slow consoles. */ + if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) + WRITE_ONCE(rcu_state.jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + panic_on_rcu_stall(); + + /* + * Attempt to revive the RCU machinery by forcing a context switch. + * + * A context switch would normally allow the RCU state machine to make + * progress and it could be we're stuck in kernel space without context + * switches for an entirely unreasonable amount of time. + */ + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + +static void check_cpu_stall(struct rcu_data *rdp) +{ + unsigned long gs1; + unsigned long gs2; + unsigned long gps; + unsigned long j; + unsigned long jn; + unsigned long js; + struct rcu_node *rnp; + + if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) || + !rcu_gp_in_progress()) + return; + rcu_stall_kick_kthreads(); + j = jiffies; + + /* + * Lots of memory barriers to reject false positives. + * + * The idea is to pick up rcu_state.gp_seq, then + * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally + * another copy of rcu_state.gp_seq. These values are updated in + * the opposite order with memory barriers (or equivalent) during + * grace-period initialization and cleanup. Now, a false positive + * can occur if we get an new value of rcu_state.gp_start and a old + * value of rcu_state.jiffies_stall. But given the memory barriers, + * the only way that this can happen is if one grace period ends + * and another starts between these two fetches. This is detected + * by comparing the second fetch of rcu_state.gp_seq with the + * previous fetch from rcu_state.gp_seq. + * + * Given this check, comparisons of jiffies, rcu_state.jiffies_stall, + * and rcu_state.gp_start suffice to forestall false positives. + */ + gs1 = READ_ONCE(rcu_state.gp_seq); + smp_rmb(); /* Pick up ->gp_seq first... */ + js = READ_ONCE(rcu_state.jiffies_stall); + smp_rmb(); /* ...then ->jiffies_stall before the rest... */ + gps = READ_ONCE(rcu_state.gp_start); + smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ + gs2 = READ_ONCE(rcu_state.gp_seq); + if (gs1 != gs2 || + ULONG_CMP_LT(j, js) || + ULONG_CMP_GE(gps, js)) + return; /* No stall or GP completed since entering function. */ + rnp = rdp->mynode; + jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; + if (rcu_gp_in_progress() && + (READ_ONCE(rnp->qsmask) & rdp->grpmask) && + cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { + + /* We haven't checked in, so go dump stack. */ + print_cpu_stall(); + + } else if (rcu_gp_in_progress() && + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && + cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { + + /* They had a few time units to dump stack, so complain. */ + print_other_cpu_stall(gs2); + } +} + +////////////////////////////////////////////////////////////////////////////// +// +// RCU forward-progress mechanisms, including of callback invocation. + + +/* + * Show the state of the grace-period kthreads. + */ +void show_rcu_gp_kthreads(void) +{ + int cpu; + unsigned long j; + unsigned long ja; + unsigned long jr; + unsigned long jw; + struct rcu_data *rdp; + struct rcu_node *rnp; + + j = jiffies; + ja = j - READ_ONCE(rcu_state.gp_activity); + jr = j - READ_ONCE(rcu_state.gp_req_activity); + jw = j - READ_ONCE(rcu_state.gp_wake_time); + pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n", + rcu_state.name, gp_state_getname(rcu_state.gp_state), + rcu_state.gp_state, + rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL, + ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq), + (long)READ_ONCE(rcu_state.gp_seq), + (long)READ_ONCE(rcu_get_root()->gp_seq_needed), + READ_ONCE(rcu_state.gp_flags)); + rcu_for_each_node_breadth_first(rnp) { + if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed)) + continue; + pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n", + rnp->grplo, rnp->grphi, (long)rnp->gp_seq, + (long)rnp->gp_seq_needed); + if (!rcu_is_leaf_node(rnp)) + continue; + for_each_leaf_node_possible_cpu(rnp, cpu) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->gpwrap || + ULONG_CMP_GE(rcu_state.gp_seq, + rdp->gp_seq_needed)) + continue; + pr_info("\tcpu %d ->gp_seq_needed %ld\n", + cpu, (long)rdp->gp_seq_needed); + } + } + /* sched_show_task(rcu_state.gp_kthread); */ +} +EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); + +/* + * This function checks for grace-period requests that fail to motivate + * RCU to come out of its idle mode. + */ +static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp, + const unsigned long gpssdelay) +{ + unsigned long flags; + unsigned long j; + struct rcu_node *rnp_root = rcu_get_root(); + static atomic_t warned = ATOMIC_INIT(0); + + if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) + return; + j = jiffies; /* Expensive access, and in common case don't get here. */ + if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || + atomic_read(&warned)) + return; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + j = jiffies; + if (rcu_gp_in_progress() || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || + atomic_read(&warned)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + /* Hold onto the leaf lock to make others see warned==1. */ + + if (rnp_root != rnp) + raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + j = jiffies; + if (rcu_gp_in_progress() || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, rcu_state.gp_req_activity + gpssdelay) || + time_before(j, rcu_state.gp_activity + gpssdelay) || + atomic_xchg(&warned, 1)) { + raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + WARN_ON(1); + if (rnp_root != rnp) + raw_spin_unlock_rcu_node(rnp_root); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + show_rcu_gp_kthreads(); +} + +/* + * Do a forward-progress check for rcutorture. This is normally invoked + * due to an OOM event. The argument "j" gives the time period during + * which rcutorture would like progress to have been made. + */ +void rcu_fwd_progress_check(unsigned long j) +{ + unsigned long cbs; + int cpu; + unsigned long max_cbs = 0; + int max_cpu = -1; + struct rcu_data *rdp; + + if (rcu_gp_in_progress()) { + pr_info("%s: GP age %lu jiffies\n", + __func__, jiffies - rcu_state.gp_start); + show_rcu_gp_kthreads(); + } else { + pr_info("%s: Last GP end %lu jiffies ago\n", + __func__, jiffies - rcu_state.gp_end); + preempt_disable(); + rdp = this_cpu_ptr(&rcu_data); + rcu_check_gp_start_stall(rdp->mynode, rdp, j); + preempt_enable(); + } + for_each_possible_cpu(cpu) { + cbs = rcu_get_n_cbs_cpu(cpu); + if (!cbs) + continue; + if (max_cpu < 0) + pr_info("%s: callbacks", __func__); + pr_cont(" %d: %lu", cpu, cbs); + if (cbs <= max_cbs) + continue; + max_cbs = cbs; + max_cpu = cpu; + } + if (max_cpu >= 0) + pr_cont("\n"); +} +EXPORT_SYMBOL_GPL(rcu_fwd_progress_check); + +/* Commandeer a sysrq key to dump RCU's tree. */ +static bool sysrq_rcu; +module_param(sysrq_rcu, bool, 0444); + +/* Dump grace-period-request information due to commandeered sysrq. */ +static void sysrq_show_rcu(int key) +{ + show_rcu_gp_kthreads(); +} + +static struct sysrq_key_op sysrq_rcudump_op = { + .handler = sysrq_show_rcu, + .help_msg = "show-rcu(y)", + .action_msg = "Show RCU tree", + .enable_mask = SYSRQ_ENABLE_DUMP, +}; + +static int __init rcu_sysrq_init(void) +{ + if (sysrq_rcu) + return register_sysrq_key('y', &sysrq_rcudump_op); + return 0; +} +early_initcall(rcu_sysrq_init); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index cbaa976c5945..c3bf44ba42e5 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -424,68 +424,11 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); #endif #ifdef CONFIG_RCU_STALL_COMMON - -#ifdef CONFIG_PROVE_RCU -#define RCU_STALL_DELAY_DELTA (5 * HZ) -#else -#define RCU_STALL_DELAY_DELTA 0 -#endif - int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); -static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; - module_param(rcu_cpu_stall_suppress, int, 0644); +int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_timeout, int, 0644); - -int rcu_jiffies_till_stall_check(void) -{ - int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout); - - /* - * Limit check must be consistent with the Kconfig limits - * for CONFIG_RCU_CPU_STALL_TIMEOUT. - */ - if (till_stall_check < 3) { - WRITE_ONCE(rcu_cpu_stall_timeout, 3); - till_stall_check = 3; - } else if (till_stall_check > 300) { - WRITE_ONCE(rcu_cpu_stall_timeout, 300); - till_stall_check = 300; - } - return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; -} -EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check); - -void rcu_sysrq_start(void) -{ - if (!rcu_cpu_stall_suppress) - rcu_cpu_stall_suppress = 2; -} - -void rcu_sysrq_end(void) -{ - if (rcu_cpu_stall_suppress == 2) - rcu_cpu_stall_suppress = 0; -} - -static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) -{ - rcu_cpu_stall_suppress = 1; - return NOTIFY_DONE; -} - -static struct notifier_block rcu_panic_block = { - .notifier_call = rcu_panic, -}; - -static int __init check_cpu_stall_init(void) -{ - atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); - return 0; -} -early_initcall(check_cpu_stall_init); - #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_TASKS_RCU diff --git a/kernel/resource.c b/kernel/resource.c index e81b17b53fa5..8c15f846e8ef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -382,7 +382,7 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, int (*func)(struct resource *, void *)) { struct resource res; - int ret = -1; + int ret = -EINVAL; while (start < end && !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) { @@ -452,6 +452,9 @@ int walk_mem_res(u64 start, u64 end, void *arg, * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. * It is to be used only for System RAM. + * + * This will find System RAM ranges that are children of top-level resources + * in addition to top-level System RAM resources. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) @@ -460,14 +463,14 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, unsigned long flags; struct resource res; unsigned long pfn, end_pfn; - int ret = -1; + int ret = -EINVAL; start = (u64) start_pfn << PAGE_SHIFT; end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; while (start < end && !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, - true, &res)) { + false, &res)) { pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) @@ -517,21 +520,20 @@ EXPORT_SYMBOL_GPL(page_is_ram); int region_intersects(resource_size_t start, size_t size, unsigned long flags, unsigned long desc) { - resource_size_t end = start + size - 1; + struct resource res; int type = 0; int other = 0; struct resource *p; + res.start = start; + res.end = start + size - 1; + read_lock(&resource_lock); for (p = iomem_resource.child; p ; p = p->sibling) { bool is_type = (((p->flags & flags) == flags) && ((desc == IORES_DESC_NONE) || (desc == p->desc))); - if (start >= p->start && start <= p->end) - is_type ? type++ : other++; - if (end >= p->start && end <= p->end) - is_type ? type++ : other++; - if (p->start >= start && p->end <= end) + if (resource_overlaps(p, &res)) is_type ? type++ : other++; } read_unlock(&resource_lock); @@ -1128,6 +1130,15 @@ struct resource * __request_region(struct resource *parent, conflict = __request_resource(parent, res); if (!conflict) break; + /* + * mm/hmm.c reserves physical addresses which then + * become unavailable to other users. Conflicts are + * not expected. Warn to aid debugging if encountered. + */ + if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { + pr_warn("Unaddressable device %s %pR conflicts with %pR", + conflict->name, conflict, res); + } if (conflict != parent) { if (!(conflict->flags & IORESOURCE_BUSY)) { parent = conflict; diff --git a/kernel/rseq.c b/kernel/rseq.c index 25e9a7b60eba..9424ee90589e 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -254,8 +254,7 @@ static int rseq_ip_fixup(struct pt_regs *regs) * - signal delivery, * and return to user-space. * - * This is how we can ensure that the entire rseq critical section, - * consisting of both the C part and the assembly instruction sequence, + * This is how we can ensure that the entire rseq critical section * will issue the commit instruction only if executed atomically with * respect to other threads scheduled on the same CPU, and with respect * to signal handlers. @@ -314,7 +313,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; - if (current->rseq_len != rseq_len) + if (rseq_len != sizeof(*rseq)) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; @@ -322,7 +321,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, if (ret) return ret; current->rseq = NULL; - current->rseq_len = 0; current->rseq_sig = 0; return 0; } @@ -336,7 +334,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, * the provided address differs from the prior * one. */ - if (current->rseq != rseq || current->rseq_len != rseq_len) + if (current->rseq != rseq || rseq_len != sizeof(*rseq)) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; @@ -354,7 +352,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, if (!access_ok(rseq, rseq_len)) return -EFAULT; current->rseq = rseq; - current->rseq_len = rseq_len; current->rseq_sig = sig; /* * If rseq was previously inactive, and has just been diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ead464a0f2e5..102dfcf0a29a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -792,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags) rq->nr_uninterruptible--; enqueue_task(rq, p, flags); + + p->on_rq = TASK_ON_RQ_QUEUED; } void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { + p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING; + if (task_contributes_to_load(p)) rq->nr_uninterruptible++; @@ -920,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p) } /* - * Per-CPU kthreads are allowed to run on !actie && online CPUs, see + * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_rq(). */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) @@ -1151,7 +1155,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, p, &rf); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); - tlb_migrate_finish(p->mm); return 0; } else if (task_on_rq_queued(p)) { /* @@ -1237,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) rq_pin_lock(src_rq, &srf); rq_pin_lock(dst_rq, &drf); - p->on_rq = TASK_ON_RQ_MIGRATING; deactivate_task(src_rq, p, 0); set_task_cpu(p, cpu); activate_task(dst_rq, p, 0); - p->on_rq = TASK_ON_RQ_QUEUED; check_preempt_curr(dst_rq, p, 0); rq_unpin_lock(dst_rq, &drf); @@ -1681,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) __schedstat_inc(p->se.statistics.nr_wakeups_sync); } -static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) -{ - activate_task(rq, p, en_flags); - p->on_rq = TASK_ON_RQ_QUEUED; - - /* If a worker is waking up, notify the workqueue: */ - if (p->flags & PF_WQ_WORKER) - wq_worker_waking_up(p, cpu_of(rq)); -} - /* * Mark the task runnable and perform wakeup-preemption. */ @@ -1742,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, en_flags |= ENQUEUE_MIGRATED; #endif - ttwu_activate(rq, p, en_flags); + activate_task(rq, p, en_flags); ttwu_do_wakeup(rq, p, wake_flags, rf); } @@ -2107,56 +2098,6 @@ out: } /** - * try_to_wake_up_local - try to wake up a local task with rq lock held - * @p: the thread to be awakened - * @rf: request-queue flags for pinning - * - * Put @p on the run-queue if it's not already there. The caller must - * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. - */ -static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) -{ - struct rq *rq = task_rq(p); - - if (WARN_ON_ONCE(rq != this_rq()) || - WARN_ON_ONCE(p == current)) - return; - - lockdep_assert_held(&rq->lock); - - if (!raw_spin_trylock(&p->pi_lock)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet picked a replacement task. - */ - rq_unlock(rq, rf); - raw_spin_lock(&p->pi_lock); - rq_relock(rq, rf); - } - - if (!(p->state & TASK_NORMAL)) - goto out; - - trace_sched_waking(p); - - if (!task_on_rq_queued(p)) { - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&rq->nr_iowait); - } - ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); - } - - ttwu_do_wakeup(rq, p, 0, rf); - ttwu_stat(p, smp_processor_id(), 0); -out: - raw_spin_unlock(&p->pi_lock); -} - -/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -2467,7 +2408,6 @@ void wake_up_new_task(struct task_struct *p) post_init_entity_util_avg(p); activate_task(rq, p, ENQUEUE_NOCLOCK); - p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP @@ -3466,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt) prev->state = TASK_RUNNING; } else { deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); - prev->on_rq = 0; if (prev->in_iowait) { atomic_inc(&rq->nr_iowait); delayacct_blkio_start(); } - - /* - * If a worker went to sleep, notify and ask workqueue - * whether it wants to wake up a task to maintain - * concurrency. - */ - if (prev->flags & PF_WQ_WORKER) { - struct task_struct *to_wakeup; - - to_wakeup = wq_worker_sleeping(prev); - if (to_wakeup) - try_to_wake_up_local(to_wakeup, &rf); - } } switch_count = &prev->nvcsw; } @@ -3544,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk) { if (!tsk->state || tsk_is_pi_blocked(tsk)) return; + + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + * As this function is called inside the schedule() context, + * we disable preemption to avoid it calling schedule() again + * in the possible wakeup of a kworker. + */ + if (tsk->flags & PF_WQ_WORKER) { + preempt_disable(); + wq_worker_sleeping(tsk); + preempt_enable_no_resched(); + } + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. @@ -3552,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } +static void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + asmlinkage __visible void __sched schedule(void) { struct task_struct *tsk = current; @@ -3562,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void) __schedule(false); sched_preempt_enable_no_resched(); } while (need_resched()); + sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); @@ -5918,7 +5865,7 @@ void __init sched_init_smp(void) static int __init migration_init(void) { - sched_rq_cpu_starting(smp_processor_id()); + sched_cpu_starting(smp_processor_id()); return 0; } early_initcall(migration_init); @@ -6559,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) { + if (shareval > scale_load_down(ULONG_MAX)) + shareval = MAX_SHARES; return sched_group_set_shares(css_tg(css), scale_load(shareval)); } @@ -6574,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, static DEFINE_MUTEX(cfs_constraints_mutex); const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ -const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ +static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); @@ -6654,20 +6603,22 @@ out_unlock: return ret; } -int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) +static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) { u64 quota, period; period = ktime_to_ns(tg->cfs_bandwidth.period); if (cfs_quota_us < 0) quota = RUNTIME_INF; - else + else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC) quota = (u64)cfs_quota_us * NSEC_PER_USEC; + else + return -EINVAL; return tg_set_cfs_bandwidth(tg, period, quota); } -long tg_get_cfs_quota(struct task_group *tg) +static long tg_get_cfs_quota(struct task_group *tg) { u64 quota_us; @@ -6680,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg) return quota_us; } -int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) +static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) { u64 quota, period; + if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC) + return -EINVAL; + period = (u64)cfs_period_us * NSEC_PER_USEC; quota = tg->cfs_bandwidth.quota; return tg_set_cfs_bandwidth(tg, period, quota); } -long tg_get_cfs_period(struct task_group *tg) +static long tg_get_cfs_period(struct task_group *tg) { u64 cfs_period_us; @@ -6998,7 +6952,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf, { char tok[21]; /* U64_MAX */ - if (!sscanf(buf, "%s %llu", tok, periodp)) + if (sscanf(buf, "%20s %llu", tok, periodp) < 1) return -EINVAL; *periodp *= NSEC_PER_USEC; diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index 835671f0f917..b5dcd1d83c7f 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -7,7 +7,7 @@ */ #include "sched.h" -DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); +DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); /** * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer. diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 2efe629425be..962cf343f798 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -13,6 +13,8 @@ #include <linux/sched/cpufreq.h> #include <trace/events/power.h> +#define IOWAIT_BOOST_MIN (SCHED_CAPACITY_SCALE / 8) + struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; @@ -48,7 +50,6 @@ struct sugov_cpu { bool iowait_boost_pending; unsigned int iowait_boost; - unsigned int iowait_boost_max; u64 last_update; unsigned long bw_dl; @@ -291,8 +292,8 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) * * The IO wait boost of a task is disabled after a tick since the last update * of a CPU. If a new IO wait boost is requested after more then a tick, then - * we enable the boost starting from the minimum frequency, which improves - * energy efficiency by ignoring sporadic wakeups from IO. + * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy + * efficiency by ignoring sporadic wakeups from IO. */ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, bool set_iowait_boost) @@ -303,8 +304,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, if (delta_ns <= TICK_NSEC) return false; - sg_cpu->iowait_boost = set_iowait_boost - ? sg_cpu->sg_policy->policy->min : 0; + sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0; sg_cpu->iowait_boost_pending = set_iowait_boost; return true; @@ -318,8 +318,9 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time, * * Each time a task wakes up after an IO operation, the CPU utilization can be * boosted to a certain utilization which doubles at each "frequent and - * successive" wakeup from IO, ranging from the utilization of the minimum - * OPP to the utilization of the maximum OPP. + * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization + * of the maximum OPP. + * * To keep doubling, an IO boost has to be requested at least once per tick, * otherwise we restart from the utilization of the minimum OPP. */ @@ -344,14 +345,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, /* Double the boost at each request */ if (sg_cpu->iowait_boost) { - sg_cpu->iowait_boost <<= 1; - if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max) - sg_cpu->iowait_boost = sg_cpu->iowait_boost_max; + sg_cpu->iowait_boost = + min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE); return; } /* First wakeup after IO: start with minimum boost */ - sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min; + sg_cpu->iowait_boost = IOWAIT_BOOST_MIN; } /** @@ -373,47 +373,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, - unsigned long *util, unsigned long *max) +static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + unsigned long util, unsigned long max) { - unsigned int boost_util, boost_max; + unsigned long boost; /* No boost currently required */ if (!sg_cpu->iowait_boost) - return; + return util; /* Reset boost if the CPU appears to have been idle enough */ if (sugov_iowait_reset(sg_cpu, time, false)) - return; + return util; - /* - * An IO waiting task has just woken up: - * allow to further double the boost value - */ - if (sg_cpu->iowait_boost_pending) { - sg_cpu->iowait_boost_pending = false; - } else { + if (!sg_cpu->iowait_boost_pending) { /* - * Otherwise: reduce the boost value and disable it when we - * reach the minimum. + * No boost pending; reduce the boost value. */ sg_cpu->iowait_boost >>= 1; - if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) { + if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) { sg_cpu->iowait_boost = 0; - return; + return util; } } + sg_cpu->iowait_boost_pending = false; + /* - * Apply the current boost value: a CPU is boosted only if its current - * utilization is smaller then the current IO boost level. + * @util is already in capacity scale; convert iowait_boost + * into the same scale so we can compare. */ - boost_util = sg_cpu->iowait_boost; - boost_max = sg_cpu->iowait_boost_max; - if (*util * boost_max < *max * boost_util) { - *util = boost_util; - *max = boost_max; - } + boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT; + return max(boost, util); } #ifdef CONFIG_NO_HZ_COMMON @@ -460,7 +451,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, util = sugov_get_util(sg_cpu); max = sg_cpu->max; - sugov_iowait_apply(sg_cpu, time, &util, &max); + util = sugov_iowait_apply(sg_cpu, time, util, max); next_f = get_next_freq(sg_policy, util, max); /* * Do not reduce the frequency if the CPU has not been idle @@ -500,7 +491,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); + j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max); if (j_util * max > j_max * util) { util = j_util; @@ -609,13 +600,14 @@ rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf, size_t count static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us); -static struct attribute *sugov_attributes[] = { +static struct attribute *sugov_attrs[] = { &rate_limit_us.attr, NULL }; +ATTRIBUTE_GROUPS(sugov); static struct kobj_type sugov_tunables_ktype = { - .default_attrs = sugov_attributes, + .default_groups = sugov_groups, .sysfs_ops = &governor_sysfs_ops, }; @@ -782,6 +774,7 @@ out: return 0; fail: + kobject_put(&tunables->attr_set.kobj); policy->governor_data = NULL; sugov_tunables_free(tunables); @@ -837,7 +830,6 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; } for_each_cpu(cpu, policy->cpus) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6a73e41a2016..43901fa3f269 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p) if (dl_entity_is_special(dl_se)) return; - WARN_ON(hrtimer_active(&dl_se->inactive_timer)); WARN_ON(dl_se->dl_non_contending); zerolag_time = dl_se->deadline - @@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p) * If the "0-lag time" already passed, decrease the active * utilization now, instead of starting a timer */ - if (zerolag_time < 0) { + if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { if (dl_task(p)) sub_running_bw(dl_se, dl_rq); if (!dl_task(p) || p->state == TASK_DEAD) { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 8039d62ae36e..678bfb9bd87f 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -702,7 +702,7 @@ do { \ static const char *sched_tunable_scaling_names[] = { "none", - "logaritmic", + "logarithmic", "linear" }; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ea74d43924b2..f35930f5e528 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2007,6 +2007,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) if (p->last_task_numa_placement) { delta = runtime - p->last_sum_exec_runtime; *period = now - p->last_task_numa_placement; + + /* Avoid time going backwards, prevent potential divide error: */ + if (unlikely((s64)*period < 0)) + *period = 0; } else { delta = p->se.avg.load_sum; *period = LOAD_AVG_MAX; @@ -2593,7 +2597,7 @@ out: /* * Drive the periodic memory faults.. */ -void task_tick_numa(struct rq *rq, struct task_struct *curr) +static void task_tick_numa(struct rq *rq, struct task_struct *curr) { struct callback_head *work = &curr->numa_work; u64 period, now; @@ -3567,7 +3571,7 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) * Synchronize entity load avg of dequeued entity without locking * the previous rq. */ -void sync_entity_load_avg(struct sched_entity *se) +static void sync_entity_load_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 last_update_time; @@ -3580,7 +3584,7 @@ void sync_entity_load_avg(struct sched_entity *se) * Task first catches up with cfs_rq, and then subtract * itself from the cfs_rq (task must be off the queue now). */ -void remove_entity_load_avg(struct sched_entity *se) +static void remove_entity_load_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); unsigned long flags; @@ -4885,6 +4889,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4898,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4906,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) @@ -5116,7 +5145,6 @@ static inline void hrtick_update(struct rq *rq) #ifdef CONFIG_SMP static inline unsigned long cpu_util(int cpu); -static unsigned long capacity_of(int cpu); static inline bool cpu_overutilized(int cpu) { @@ -7492,7 +7520,6 @@ static void detach_task(struct task_struct *p, struct lb_env *env) { lockdep_assert_held(&env->src_rq->lock); - p->on_rq = TASK_ON_RQ_MIGRATING; deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, env->dst_cpu); } @@ -7628,7 +7655,6 @@ static void attach_task(struct rq *rq, struct task_struct *p) BUG_ON(task_rq(p) != rq); activate_task(rq, p, ENQUEUE_NOCLOCK); - p->on_rq = TASK_ON_RQ_QUEUED; check_preempt_curr(rq, p, 0); } @@ -7784,10 +7810,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) if (cfs_rq->last_h_load_update == now) return; - cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -7797,7 +7823,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) cfs_rq->last_h_load_update = now; } - while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1); @@ -8060,6 +8086,18 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) } /* + * Check whether a rq has a misfit task and if it looks like we can actually + * help that task: we can migrate the task to a CPU of higher capacity, or + * the task's current CPU is heavily pressured. + */ +static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) +{ + return rq->misfit_task_load && + (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity || + check_cpu_capacity(rq, sd)); +} + +/* * Group imbalance indicates (and tries to solve) the problem where balancing * groups is inadequate due to ->cpus_allowed constraints. * @@ -9510,22 +9548,26 @@ static inline int on_null_domain(struct rq *rq) * - When one of the busy CPUs notice that there may be an idle rebalancing * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. + * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set + * anywhere yet. */ static inline int find_new_ilb(void) { - int ilb = cpumask_first(nohz.idle_cpus_mask); + int ilb; - if (ilb < nr_cpu_ids && idle_cpu(ilb)) - return ilb; + for_each_cpu_and(ilb, nohz.idle_cpus_mask, + housekeeping_cpumask(HK_FLAG_MISC)) { + if (idle_cpu(ilb)) + return ilb; + } return nr_cpu_ids; } /* - * Kick a CPU to do the nohz balancing, if it is time for it. We pick the - * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle - * CPU (if there is one). + * Kick a CPU to do the nohz balancing, if it is time for it. We pick any + * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one). */ static void kick_ilb(unsigned int flags) { @@ -9586,35 +9628,21 @@ static void nohz_balancer_kick(struct rq *rq) if (time_before(now, nohz.next_balance)) goto out; - if (rq->nr_running >= 2 || rq->misfit_task_load) { + if (rq->nr_running >= 2) { flags = NOHZ_KICK_MASK; goto out; } rcu_read_lock(); - sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - if (sds) { - /* - * If there is an imbalance between LLC domains (IOW we could - * increase the overall cache use), we need some less-loaded LLC - * domain to pull some load. Likewise, we may need to spread - * load within the current LLC domain (e.g. packed SMT cores but - * other CPUs are idle). We can't really know from here how busy - * the others are - so just get a nohz balance going if it looks - * like this LLC domain has tasks we could move. - */ - nr_busy = atomic_read(&sds->nr_busy_cpus); - if (nr_busy > 1) { - flags = NOHZ_KICK_MASK; - goto unlock; - } - - } sd = rcu_dereference(rq->sd); if (sd) { - if ((rq->cfs.h_nr_running >= 1) && - check_cpu_capacity(rq, sd)) { + /* + * If there's a CFS task and the current CPU has reduced + * capacity; kick the ILB to see if there's a better CPU to run + * on. + */ + if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) { flags = NOHZ_KICK_MASK; goto unlock; } @@ -9622,6 +9650,11 @@ static void nohz_balancer_kick(struct rq *rq) sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { + /* + * When ASYM_PACKING; see if there's a more preferred CPU + * currently idle; in which case, kick the ILB to move tasks + * around. + */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { if (sched_asym_prefer(i, cpu)) { flags = NOHZ_KICK_MASK; @@ -9629,6 +9662,45 @@ static void nohz_balancer_kick(struct rq *rq) } } } + + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu)); + if (sd) { + /* + * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU + * to run the misfit task on. + */ + if (check_misfit_status(rq, sd)) { + flags = NOHZ_KICK_MASK; + goto unlock; + } + + /* + * For asymmetric systems, we do not want to nicely balance + * cache use, instead we want to embrace asymmetry and only + * ensure tasks have enough CPU capacity. + * + * Skip the LLC logic because it's not relevant in that case. + */ + goto unlock; + } + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) { + /* + * If there is an imbalance between LLC domains (IOW we could + * increase the overall cache use), we need some less-loaded LLC + * domain to pull some load. Likewise, we may need to spread + * load within the current LLC domain (e.g. packed SMT cores but + * other CPUs are idle). We can't really know from here how busy + * the others are - so just get a nohz balance going if it looks + * like this LLC domain has tasks we could move. + */ + nr_busy = atomic_read(&sds->nr_busy_cpus); + if (nr_busy > 1) { + flags = NOHZ_KICK_MASK; + goto unlock; + } + } unlock: rcu_read_unlock(); out: diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index b02d148e7672..687302051a27 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -65,6 +65,7 @@ void __init housekeeping_init(void) static int __init housekeeping_setup(char *str, enum hk_flags flags) { cpumask_var_t non_housekeeping_mask; + cpumask_var_t tmp; int err; alloc_bootmem_cpumask_var(&non_housekeeping_mask); @@ -75,16 +76,23 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags) return 0; } + alloc_bootmem_cpumask_var(&tmp); if (!housekeeping_flags) { alloc_bootmem_cpumask_var(&housekeeping_mask); cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask); - if (cpumask_empty(housekeeping_mask)) + + cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask); + if (cpumask_empty(tmp)) { + pr_warn("Housekeeping: must include one present CPU, " + "using boot CPU:%d\n", smp_processor_id()); __cpumask_set_cpu(smp_processor_id(), housekeeping_mask); + __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); + } } else { - cpumask_var_t tmp; - - alloc_bootmem_cpumask_var(&tmp); + cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask); + if (cpumask_empty(tmp)) + __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask); if (!cpumask_equal(tmp, housekeeping_mask)) { pr_warn("Housekeeping: nohz_full= must match isolcpus=\n"); @@ -92,8 +100,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags) free_bootmem_cpumask_var(non_housekeeping_mask); return 0; } - free_bootmem_cpumask_var(tmp); } + free_bootmem_cpumask_var(tmp); if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) { if (IS_ENABLED(CONFIG_NO_HZ_FULL)) { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 90fa23d36565..1e6b909dca36 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2555,6 +2555,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; if (rt_runtime_us < 0) rt_runtime = RUNTIME_INF; + else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC) + return -EINVAL; return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } @@ -2575,6 +2577,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) { u64 rt_runtime, rt_period; + if (rt_period_us > U64_MAX / NSEC_PER_USEC) + return -EINVAL; + rt_period = rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index efa686eeff26..b52ed1ada0be 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -780,7 +780,7 @@ struct root_domain { * NULL-terminated list of performance domains intersecting with the * CPUs of the rd. Protected by RCU. */ - struct perf_domain *pd; + struct perf_domain __rcu *pd; }; extern struct root_domain def_root_domain; @@ -869,8 +869,8 @@ struct rq { atomic_t nr_iowait; #ifdef CONFIG_SMP - struct root_domain *rd; - struct sched_domain *sd; + struct root_domain *rd; + struct sched_domain __rcu *sd; unsigned long cpu_capacity; unsigned long cpu_capacity_orig; @@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) return sd; } -DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc); DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); -DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DECLARE_PER_CPU(struct sched_domain *, sd_numa); -DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing); -DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); +DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { @@ -2185,7 +2185,7 @@ static inline u64 irq_time_read(int cpu) #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ #ifdef CONFIG_CPU_FREQ -DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); +DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); /** * cpufreq_update_util - Take a note about CPU utilization changes. diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index ab7f371a3a17..f53f89df837d 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd) * the cpumask of the domain), this allows us to quickly tell if * two CPUs are in the same cache domain, see cpus_share_cache(). */ -DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); -DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing); -DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); +DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) @@ -1059,6 +1059,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd) struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); struct sched_domain *child = sd->child; struct sched_group *sg; + bool already_visited; if (child) cpu = cpumask_first(sched_domain_span(child)); @@ -1066,9 +1067,14 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd) sg = *per_cpu_ptr(sdd->sg, cpu); sg->sgc = *per_cpu_ptr(sdd->sgc, cpu); - /* For claim_allocations: */ - atomic_inc(&sg->ref); - atomic_inc(&sg->sgc->ref); + /* Increase refcounts for claim_allocations: */ + already_visited = atomic_inc_return(&sg->ref) > 1; + /* sgc visits should follow a similar trend as sg */ + WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1)); + + /* If we have already visited that group, it's already initialized. */ + if (already_visited) + return sg; if (child) { cpumask_copy(sched_group_span(sg), sched_domain_span(child)); @@ -1087,8 +1093,8 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd) /* * build_sched_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_capacity to 0. + * covered by the given span, will set each group's ->cpumask correctly, + * and will initialize their ->sgc. * * Assumes the sched_domain tree is fully constructed */ @@ -2075,9 +2081,8 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) } /* - * Set up scheduler domains and groups. Callers must hold the hotplug lock. - * For now this just excludes isolated CPUs, but could be used to - * exclude other special cases in the future. + * Set up scheduler domains and groups. For now this just excludes isolated + * CPUs, but could be used to exclude other special cases in the future. */ int sched_init_domains(const struct cpumask *cpu_map) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 54a0347ca812..811b4a86cdf6 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -148,8 +148,8 @@ static void populate_seccomp_data(struct seccomp_data *sd) unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); - sd->arch = syscall_get_arch(); - syscall_get_arguments(task, regs, 0, 6, args); + sd->arch = syscall_get_arch(task); + syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; @@ -331,7 +331,7 @@ static int is_ancestor(struct seccomp_filter *parent, * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was - * either not in the correct seccomp mode or it did not have an ancestral + * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */ static inline pid_t seccomp_can_sync_threads(void) @@ -502,7 +502,10 @@ out: * * Caller must be holding current->sighand->siglock lock. * - * Returns 0 on success, -ve on error. + * Returns 0 on success, -ve on error, or + * - in TSYNC mode: the pid of a thread which was either not in the correct + * seccomp mode or did not have an ancestral seccomp filter + * - in NEW_LISTENER mode: the fd of the new listener */ static long seccomp_attach_filter(unsigned int flags, struct seccomp_filter *filter) @@ -591,7 +594,7 @@ static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason info->si_code = SYS_SECCOMP; info->si_call_addr = (void __user *)KSTK_EIP(current); info->si_errno = reason; - info->si_arch = syscall_get_arch(); + info->si_arch = syscall_get_arch(current); info->si_syscall = syscall; } @@ -1258,6 +1261,16 @@ static long seccomp_set_mode_filter(unsigned int flags, if (flags & ~SECCOMP_FILTER_FLAG_MASK) return -EINVAL; + /* + * In the successful case, NEW_LISTENER returns the new listener fd. + * But in the failure case, TSYNC returns the thread that died. If you + * combine these two flags, there's no way to tell whether something + * succeeded or failed. So, let's disallow this combination. + */ + if ((flags & SECCOMP_FILTER_FLAG_TSYNC) && + (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER)) + return -EINVAL; + /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) @@ -1304,7 +1317,7 @@ out: mutex_unlock(¤t->signal->cred_guard_mutex); out_put_fd: if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { - if (ret < 0) { + if (ret) { listener_f->private_data = NULL; fput(listener_f); put_unused_fd(listener); diff --git a/kernel/signal.c b/kernel/signal.c index 5d53183e2705..cd83cc376767 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -19,7 +19,9 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> +#include <linux/file.h> #include <linux/fs.h> +#include <linux/proc_fs.h> #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/coredump.h> @@ -3487,6 +3489,16 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese, #endif #endif +static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info) +{ + clear_siginfo(info); + info->si_signo = sig; + info->si_errno = 0; + info->si_code = SI_USER; + info->si_pid = task_tgid_vnr(current); + info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); +} + /** * sys_kill - send a signal to a process * @pid: the PID of the process @@ -3496,16 +3508,126 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct kernel_siginfo info; - clear_siginfo(&info); - info.si_signo = sig; - info.si_errno = 0; - info.si_code = SI_USER; - info.si_pid = task_tgid_vnr(current); - info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + prepare_kill_siginfo(sig, &info); return kill_something_info(sig, &info, pid); } +/* + * Verify that the signaler and signalee either are in the same pid namespace + * or that the signaler's pid namespace is an ancestor of the signalee's pid + * namespace. + */ +static bool access_pidfd_pidns(struct pid *pid) +{ + struct pid_namespace *active = task_active_pid_ns(current); + struct pid_namespace *p = ns_of_pid(pid); + + for (;;) { + if (!p) + return false; + if (p == active) + break; + p = p->parent; + } + + return true; +} + +static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) +{ +#ifdef CONFIG_COMPAT + /* + * Avoid hooking up compat syscalls and instead handle necessary + * conversions here. Note, this is a stop-gap measure and should not be + * considered a generic solution. + */ + if (in_compat_syscall()) + return copy_siginfo_from_user32( + kinfo, (struct compat_siginfo __user *)info); +#endif + return copy_siginfo_from_user(kinfo, info); +} + +static struct pid *pidfd_to_pid(const struct file *file) +{ + if (file->f_op == &pidfd_fops) + return file->private_data; + + return tgid_pidfd_to_pid(file); +} + +/** + * sys_pidfd_send_signal - send a signal to a process through a task file + * descriptor + * @pidfd: the file descriptor of the process + * @sig: signal to be sent + * @info: the signal info + * @flags: future flags to be passed + * + * The syscall currently only signals via PIDTYPE_PID which covers + * kill(<positive-pid>, <signal>. It does not signal threads or process + * groups. + * In order to extend the syscall to threads and process groups the @flags + * argument should be used. In essence, the @flags argument will determine + * what is signaled and not the file descriptor itself. Put in other words, + * grouping is a property of the flags argument not a property of the file + * descriptor. + * + * Return: 0 on success, negative errno on failure + */ +SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, + siginfo_t __user *, info, unsigned int, flags) +{ + int ret; + struct fd f; + struct pid *pid; + kernel_siginfo_t kinfo; + + /* Enforce flags be set to 0 until we add an extension. */ + if (flags) + return -EINVAL; + + f = fdget(pidfd); + if (!f.file) + return -EBADF; + + /* Is this a pidfd? */ + pid = pidfd_to_pid(f.file); + if (IS_ERR(pid)) { + ret = PTR_ERR(pid); + goto err; + } + + ret = -EINVAL; + if (!access_pidfd_pidns(pid)) + goto err; + + if (info) { + ret = copy_siginfo_from_user_any(&kinfo, info); + if (unlikely(ret)) + goto err; + + ret = -EINVAL; + if (unlikely(sig != kinfo.si_signo)) + goto err; + + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; + if ((task_pid(current) != pid) && + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) + goto err; + } else { + prepare_kill_siginfo(sig, &kinfo); + } + + ret = kill_pid_info(sig, &kinfo, pid); + +err: + fdput(f); + return ret; +} + static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { diff --git a/kernel/softirq.c b/kernel/softirq.c index 10277429ed84..2c3382378d94 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -573,57 +573,6 @@ void tasklet_kill(struct tasklet_struct *t) } EXPORT_SYMBOL(tasklet_kill); -/* - * tasklet_hrtimer - */ - -/* - * The trampoline is called when the hrtimer expires. It schedules a tasklet - * to run __tasklet_hrtimer_trampoline() which in turn will call the intended - * hrtimer callback, but from softirq context. - */ -static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer) -{ - struct tasklet_hrtimer *ttimer = - container_of(timer, struct tasklet_hrtimer, timer); - - tasklet_hi_schedule(&ttimer->tasklet); - return HRTIMER_NORESTART; -} - -/* - * Helper function which calls the hrtimer callback from - * tasklet/softirq context - */ -static void __tasklet_hrtimer_trampoline(unsigned long data) -{ - struct tasklet_hrtimer *ttimer = (void *)data; - enum hrtimer_restart restart; - - restart = ttimer->function(&ttimer->timer); - if (restart != HRTIMER_NORESTART) - hrtimer_restart(&ttimer->timer); -} - -/** - * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks - * @ttimer: tasklet_hrtimer which is initialized - * @function: hrtimer callback function which gets called from softirq context - * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME) - * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL) - */ -void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode) -{ - hrtimer_init(&ttimer->timer, which_clock, mode); - ttimer->timer.function = __hrtimer_tasklet_trampoline; - tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline, - (unsigned long)ttimer); - ttimer->function = function; -} -EXPORT_SYMBOL_GPL(tasklet_hrtimer_init); - void __init softirq_init(void) { int cpu; diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index f8edee9c792d..27bafc1e271e 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -5,41 +5,56 @@ * * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ +#include <linux/sched/task_stack.h> +#include <linux/sched/debug.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> -void print_stack_trace(struct stack_trace *trace, int spaces) +/** + * stack_trace_print - Print the entries in the stack trace + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + */ +void stack_trace_print(unsigned long *entries, unsigned int nr_entries, + int spaces) { - int i; + unsigned int i; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return; - for (i = 0; i < trace->nr_entries; i++) - printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]); + for (i = 0; i < nr_entries; i++) + printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]); } -EXPORT_SYMBOL_GPL(print_stack_trace); +EXPORT_SYMBOL_GPL(stack_trace_print); -int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces) +/** + * stack_trace_snprint - Print the entries in the stack trace into a buffer + * @buf: Pointer to the print buffer + * @size: Size of the print buffer + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed. + */ +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces) { - int i; - int generated; - int total = 0; + unsigned int generated, i, total = 0; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return 0; - for (i = 0; i < trace->nr_entries; i++) { + for (i = 0; i < nr_entries && size; i++) { generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ', - (void *)trace->entries[i]); + (void *)entries[i]); total += generated; - - /* Assume that generated isn't a negative number */ if (generated >= size) { buf += size; size = 0; @@ -51,7 +66,176 @@ int snprint_stack_trace(char *buf, size_t size, return total; } -EXPORT_SYMBOL_GPL(snprint_stack_trace); +EXPORT_SYMBOL_GPL(stack_trace_snprint); + +#ifdef CONFIG_ARCH_STACKWALK + +struct stacktrace_cookie { + unsigned long *store; + unsigned int size; + unsigned int skip; + unsigned int len; +}; + +static bool stack_trace_consume_entry(void *cookie, unsigned long addr, + bool reliable) +{ + struct stacktrace_cookie *c = cookie; + + if (c->len >= c->size) + return false; + + if (c->skip > 0) { + c->skip--; + return true; + } + c->store[c->len++] = addr; + return c->len < c->size; +} + +static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr, + bool reliable) +{ + if (in_sched_functions(addr)) + return true; + return stack_trace_consume_entry(cookie, addr, reliable); +} + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + arch_stack_walk(consume_entry, &c, current, NULL); + return c.len; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + if (!try_get_task_stack(tsk)) + return 0; + + arch_stack_walk(consume_entry, &c, tsk, NULL); + put_task_stack(tsk); + return c.len; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr, + }; + + arch_stack_walk(consume_entry, &c, current, regs); + return c.len; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + int ret; + + /* + * If the task doesn't have a stack (e.g., a zombie), the stack is + * "reliably" empty. + */ + if (!try_get_task_stack(tsk)) + return 0; + + ret = arch_stack_walk_reliable(consume_entry, &c, tsk); + put_task_stack(tsk); + return ret; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + + /* Trace user stack if not a kernel thread */ + if (!current->mm) + return 0; + + arch_stack_walk_user(consume_entry, &c, task_pt_regs(current)); + return c.len; +} +#endif + +#else /* CONFIG_ARCH_STACKWALK */ /* * Architectures that do not implement save_stack_trace_*() @@ -77,3 +261,118 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n"); return -ENOSYS; } + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace(&trace); + return trace.nr_entries; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace_tsk(task, &trace); + return trace.nr_entries; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr, + }; + + save_stack_trace_regs(regs, &trace); + return trace.nr_entries; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + int ret = save_stack_trace_tsk_reliable(tsk, &trace); + + return ret ? ret : trace.nr_entries; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + + save_stack_trace_user(&trace); + return trace.nr_entries; +} +#endif /* CONFIG_USER_STACKTRACE_SUPPORT */ + +#endif /* !CONFIG_ARCH_STACKWALK */ diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 067cb83f37ea..7231fb5953fc 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -513,7 +513,7 @@ repeat: } preempt_count_dec(); WARN_ONCE(preempt_count(), - "cpu_stop: %pf(%p) leaked preempt count\n", fn, arg); + "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg); goto repeat; } } diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 51d7c6794bf1..4d9ae5ea6caf 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -167,8 +167,6 @@ COND_SYSCALL(syslog); /* kernel/sched/core.c */ -/* kernel/signal.c */ - /* kernel/sys.c */ COND_SYSCALL(setregid); COND_SYSCALL(setgid); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e5da394d1ca3..599510a3355e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -128,6 +128,7 @@ static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; +static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; @@ -1750,7 +1751,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, + .extra1 = &zero_ul, .extra2 = &long_max, }, { @@ -3325,6 +3326,11 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_do_large_bitmap(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} #endif /* CONFIG_PROC_SYSCTL */ @@ -3365,3 +3371,4 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); EXPORT_SYMBOL(proc_doulongvec_minmax); EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax); +EXPORT_SYMBOL(proc_do_large_bitmap); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4e62a4a8fa91..5f852b8f59f7 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -375,7 +375,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; - na = nla_nest_start(skb, aggr); + na = nla_nest_start_noflag(skb, aggr); if (!na) goto err; @@ -649,17 +649,41 @@ err: static const struct genl_ops taskstats_ops[] = { { .cmd = TASKSTATS_CMD_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = taskstats_user_cmd, - .policy = taskstats_cmd_get_policy, - .flags = GENL_ADMIN_PERM, + /* policy enforced later */ + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL, }, { .cmd = CGROUPSTATS_CMD_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = cgroupstats_user_cmd, - .policy = cgroupstats_cmd_get_policy, + /* policy enforced later */ + .flags = GENL_CMD_CAP_HASPOL, }, }; +static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + const struct nla_policy *policy = NULL; + + switch (ops->cmd) { + case TASKSTATS_CMD_GET: + policy = taskstats_cmd_get_policy; + break; + case CGROUPSTATS_CMD_GET: + policy = cgroupstats_cmd_get_policy; + break; + default: + return -EINVAL; + } + + return nlmsg_validate_deprecated(info->nlhdr, GENL_HDRLEN, + TASKSTATS_CMD_ATTR_MAX, policy, + info->extack); +} + static struct genl_family family __ro_after_init = { .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, @@ -667,6 +691,7 @@ static struct genl_family family __ro_after_init = { .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), + .pre_doit = taskstats_pre_doit, }; /* Needed early in initialization */ diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2c97e8c2d29f..0519a8805aab 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return ktime_sub(now, alarm->node.expires); + return ktime_sub(alarm->node.expires, now); } /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 5e77662dd2d9..f5490222e134 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -611,6 +611,22 @@ void clockevents_resume(void) } #ifdef CONFIG_HOTPLUG_CPU + +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +/** + * tick_offline_cpu - Take CPU out of the broadcast mechanism + * @cpu: The outgoing CPU + * + * Called on the outgoing CPU after it took itself offline. + */ +void tick_offline_cpu(unsigned int cpu) +{ + raw_spin_lock(&clockevents_lock); + tick_broadcast_offline(cpu); + raw_spin_unlock(&clockevents_lock); +} +# endif + /** * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ @@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu) raw_spin_lock_irqsave(&clockevents_lock, flags); - tick_shutdown_broadcast_oneshot(cpu); - tick_shutdown_broadcast(cpu); tick_shutdown(cpu); /* * Unregister the clock event devices which were diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index dc1b6f1929f9..d23b434c2ca7 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -63,7 +63,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) { - unsigned long seq; + unsigned int seq; u64 ret; do { @@ -89,7 +89,7 @@ struct clocksource * __init __weak clocksource_default_clock(void) return &clocksource_jiffies; } -struct clocksource refined_jiffies; +static struct clocksource refined_jiffies; int register_refined_jiffies(long cycles_per_second) { diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 92a90014a925..ac5555e25733 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -17,6 +17,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/rtc.h> +#include <linux/audit.h> #include "ntp_internal.h" #include "timekeeping_internal.h" @@ -709,7 +710,7 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc, * kernel time-keeping variables. used by xntpd. */ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, - s32 *time_tai) + s32 *time_tai, struct audit_ntp_data *ad) { int result; @@ -720,14 +721,29 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, /* adjtime() is independent from ntp_adjtime() */ time_adjust = txc->offset; ntp_update_frequency(); + + audit_ntp_set_old(ad, AUDIT_NTP_ADJUST, save_adjust); + audit_ntp_set_new(ad, AUDIT_NTP_ADJUST, time_adjust); } txc->offset = save_adjust; } else { - /* If there are input parameters, then process them: */ - if (txc->modes) + if (txc->modes) { + audit_ntp_set_old(ad, AUDIT_NTP_OFFSET, time_offset); + audit_ntp_set_old(ad, AUDIT_NTP_FREQ, time_freq); + audit_ntp_set_old(ad, AUDIT_NTP_STATUS, time_status); + audit_ntp_set_old(ad, AUDIT_NTP_TAI, *time_tai); + audit_ntp_set_old(ad, AUDIT_NTP_TICK, tick_usec); + process_adjtimex_modes(txc, time_tai); + audit_ntp_set_new(ad, AUDIT_NTP_OFFSET, time_offset); + audit_ntp_set_new(ad, AUDIT_NTP_FREQ, time_freq); + audit_ntp_set_new(ad, AUDIT_NTP_STATUS, time_status); + audit_ntp_set_new(ad, AUDIT_NTP_TAI, *time_tai); + audit_ntp_set_new(ad, AUDIT_NTP_TICK, tick_usec); + } + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); if (!(time_status & STA_NANO)) diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 40e6122e634e..908ecaa65fc3 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,8 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern int __do_adjtimex(struct __kernel_timex *txc, + const struct timespec64 *ts, + s32 *time_tai, struct audit_ntp_data *ad); extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 094b82ca95e5..142b07619918 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -94,7 +94,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) unsigned long long notrace sched_clock(void) { u64 cyc, res; - unsigned long seq; + unsigned int seq; struct clock_read_data *rd; do { @@ -231,7 +231,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); - pr_debug("Registered %pF as sched_clock source\n", read); + pr_debug("Registered %pS as sched_clock source\n", read); } void __init generic_sched_clock_init(void) @@ -267,12 +267,12 @@ void __init generic_sched_clock_init(void) */ static u64 notrace suspended_sched_clock_read(void) { - unsigned long seq = raw_read_seqcount(&cd.seq); + unsigned int seq = raw_read_seqcount(&cd.seq); return cd.read_data[seq & 1].epoch_cyc; } -static int sched_clock_suspend(void) +int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; @@ -283,7 +283,7 @@ static int sched_clock_suspend(void) return 0; } -static void sched_clock_resume(void) +void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index ee834d4fb814..e51778c312f1 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -36,10 +36,16 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); +# ifdef CONFIG_HOTPLUG_CPU +static void tick_broadcast_oneshot_offline(unsigned int cpu); +# endif #else static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } +# ifdef CONFIG_HOTPLUG_CPU +static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { } +# endif #endif /* @@ -433,27 +439,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) } #ifdef CONFIG_HOTPLUG_CPU -/* - * Remove a CPU from broadcasting - */ -void tick_shutdown_broadcast(unsigned int cpu) +static void tick_shutdown_broadcast(void) { - struct clock_event_device *bc; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - bc = tick_broadcast_device.evtdev; - cpumask_clear_cpu(cpu, tick_broadcast_mask); - cpumask_clear_cpu(cpu, tick_broadcast_on); + struct clock_event_device *bc = tick_broadcast_device.evtdev; if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) clockevents_shutdown(bc); } +} - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +/* + * Remove a CPU from broadcasting + */ +void tick_broadcast_offline(unsigned int cpu) +{ + raw_spin_lock(&tick_broadcast_lock); + cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); + tick_broadcast_oneshot_offline(cpu); + tick_shutdown_broadcast(); + raw_spin_unlock(&tick_broadcast_lock); } + #endif void tick_suspend_broadcast(void) @@ -801,13 +809,13 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) * either the CPU handling the broadcast * interrupt or we got woken by something else. * - * We are not longer in the broadcast mask, so + * We are no longer in the broadcast mask, so * if the cpu local expiry time is already * reached, we would reprogram the cpu local * timer with an already expired event. * * This can lead to a ping-pong when we return - * to idle and therefor rearm the broadcast + * to idle and therefore rearm the broadcast * timer before the cpu local timer was able * to fire. This happens because the forced * reprogramming makes sure that the event @@ -950,14 +958,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) } /* - * Remove a dead CPU from broadcasting + * Remove a dying CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int cpu) +static void tick_broadcast_oneshot_offline(unsigned int cpu) { - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! @@ -965,8 +969,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #endif diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 529143b4c8d2..59225b484e4e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -46,6 +46,14 @@ ktime_t tick_period; * procedure also covers cpu hotplug. */ int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; +#ifdef CONFIG_NO_HZ_FULL +/* + * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns + * tick_do_timer_cpu and it should be taken over by an eligible secondary + * when one comes online. + */ +static int tick_do_timer_boot_cpu __read_mostly = -1; +#endif /* * Debugging: see timer_list.c @@ -149,7 +157,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) !tick_broadcast_oneshot_active()) { clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { - unsigned long seq; + unsigned int seq; ktime_t next; do { @@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) } } +#ifdef CONFIG_NO_HZ_FULL +static void giveup_do_timer(void *info) +{ + int cpu = *(unsigned int *)info; + + WARN_ON(tick_do_timer_cpu != smp_processor_id()); + + tick_do_timer_cpu = cpu; +} + +static void tick_take_do_timer_from_boot(void) +{ + int cpu = smp_processor_id(); + int from = tick_do_timer_boot_cpu; + + if (from >= 0 && from != cpu) + smp_call_function_single(from, giveup_do_timer, &cpu, 1); +} +#endif + /* * Setup the tick device */ @@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - if (!tick_nohz_full_cpu(cpu)) - tick_do_timer_cpu = cpu; - else - tick_do_timer_cpu = TICK_DO_TIMER_NONE; + tick_do_timer_cpu = cpu; + tick_next_period = ktime_get(); tick_period = NSEC_PER_SEC / HZ; +#ifdef CONFIG_NO_HZ_FULL + /* + * The boot CPU may be nohz_full, in which case set + * tick_do_timer_boot_cpu so the first housekeeping + * secondary that comes up will take do_timer from + * us. + */ + if (tick_nohz_full_cpu(cpu)) + tick_do_timer_boot_cpu = cpu; + + } else if (tick_do_timer_boot_cpu != -1 && + !tick_nohz_full_cpu(cpu)) { + tick_take_do_timer_from_boot(); + tick_do_timer_boot_cpu = -1; + WARN_ON(tick_do_timer_cpu != cpu); +#endif } /* @@ -487,6 +529,7 @@ void tick_freeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); system_state = SYSTEM_SUSPEND; + sched_clock_suspend(); timekeeping_suspend(); } else { tick_suspend_local(); @@ -510,6 +553,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_resume(); + sched_clock_resume(); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index e277284c2831..7b2496136729 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_shutdown_broadcast(unsigned int cpu); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); extern bool tick_resume_check_broadcast(void); @@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev) static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_shutdown_broadcast(unsigned int cpu) { } static inline void tick_suspend_broadcast(void) { } static inline void tick_resume_broadcast(void) { } static inline bool tick_resume_check_broadcast(void) { return false; } @@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } /* Functions related to oneshot broadcasting */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_broadcast_offline(unsigned int cpu); +#else +static inline void tick_broadcast_offline(unsigned int cpu) { } +#endif + /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6fa52cd6df0b..f4ee1a3428ae 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -121,10 +121,16 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * jiffies_lock. + * + * If nohz_full is enabled, this should not happen because the + * tick_do_timer_cpu never relinquishes. */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE) - && !tick_nohz_full_cpu(cpu)) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { +#ifdef CONFIG_NO_HZ_FULL + WARN_ON(tick_nohz_full_running); +#endif tick_do_timer_cpu = cpu; + } #endif /* Check, if the jiffies need an update */ @@ -395,8 +401,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask) static int tick_nohz_cpu_down(unsigned int cpu) { /* - * The boot CPU handles housekeeping duty (unbound timers, - * workqueues, timekeeping, ...) on behalf of full dynticks + * The tick_do_timer_cpu CPU handles housekeeping duty (unbound + * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) @@ -423,12 +429,15 @@ void __init tick_nohz_init(void) return; } - cpu = smp_processor_id(); + if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && + !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { + cpu = smp_processor_id(); - if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { - pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", - cpu); - cpumask_clear_cpu(cpu, tick_nohz_full_mask); + if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { + pr_warn("NO_HZ: Clearing %d from nohz_full range " + "for timekeeping\n", cpu); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); + } } for_each_cpu(cpu, tick_nohz_full_mask) @@ -645,7 +654,8 @@ static inline bool local_timer_softirq_pending(void) static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; - unsigned long seq, basejiff; + unsigned long basejiff; + unsigned int seq; /* Read jiffies and the time when jiffies were updated last */ do { @@ -904,8 +914,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) /* * Boot safety: make sure the timekeeping duty has been * assigned before entering dyntick-idle mode, + * tick_do_timer_cpu is TICK_DO_TIMER_BOOT */ - if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT)) + return false; + + /* Should not happen for nohz-full */ + if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) return false; } @@ -1023,6 +1038,18 @@ bool tick_nohz_idle_got_tick(void) } /** + * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer + * or the tick, whatever that expires first. Note that, if the tick has been + * stopped, it returns the next hrtimer. + * + * Called from power state control code with interrupts disabled + */ +ktime_t tick_nohz_get_next_hrtimer(void) +{ + return __this_cpu_read(tick_cpu_device.evtdev)->next_event; +} + +/** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 6de959a854b2..4fb06527cf64 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -24,12 +24,19 @@ enum tick_nohz_mode { * struct tick_sched - sched tick emulation and no idle tick control/stats * @sched_timer: hrtimer to schedule the periodic tick in high * resolution mode + * @check_clocks: Notification mechanism about clocksource changes + * @nohz_mode: Mode - one state of tick_nohz_mode + * @inidle: Indicator that the CPU is in the tick idle mode + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_active: Indicator that the CPU is actively in the tick idle mode; + * it is resetted during irq handling phases. + * @do_timer_lst: CPU was the last one doing do_timer before going idle + * @got_idle_tick: Tick timer function has run with @inidle set * @last_tick: Store the last tick expiry time when the tick * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. * @next_tick: Next tick to be fired when in dynticks mode. - * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls * @idle_sleeps: Number of idle calls, where the sched tick was stopped @@ -40,8 +47,8 @@ enum tick_nohz_mode { * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) * @timer_expires_base: Base time clock monotonic for @timer_expires - * @do_timer_lst: CPU was the last one doing do_timer before going idle - * @got_idle_tick: Tick timer function has run with @inidle set + * @next_timer: Expiry time of next expiring timer for debugging purpose only + * @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick */ struct tick_sched { struct hrtimer sched_timer; diff --git a/kernel/time/time.c b/kernel/time/time.c index c3f756f8534b..7f7d6914ddd5 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz static int firsttime = 1; int error = 0; - if (tv && !timespec64_valid(tv)) + if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); @@ -783,6 +783,16 @@ u64 jiffies64_to_nsecs(u64 j) } EXPORT_SYMBOL(jiffies64_to_nsecs); +u64 jiffies64_to_msecs(const u64 j) +{ +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) + return (MSEC_PER_SEC / HZ) * j; +#else + return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); +#endif +} +EXPORT_SYMBOL(jiffies64_to_msecs); + /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f986e1918d12..85f5912d8f70 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -21,6 +21,7 @@ #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> +#include <linux/audit.h> #include "tick-internal.h" #include "ntp_internal.h" @@ -720,7 +721,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); @@ -829,7 +830,7 @@ EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; - unsigned long seq; + unsigned int seq; ktime_t tconv; do { @@ -960,7 +961,7 @@ time64_t __ktime_get_real_seconds(void) void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; @@ -1122,7 +1123,7 @@ int get_device_system_crosststamp(int (*get_time_fn) ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; - unsigned long seq; + unsigned int seq; bool do_interp; int ret; @@ -1221,7 +1222,7 @@ int do_settimeofday64(const struct timespec64 *ts) unsigned long flags; int ret = 0; - if (!timespec64_valid_strict(ts)) + if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); @@ -1250,6 +1251,9 @@ out: /* signal hrtimers about time change */ clock_was_set(); + if (!ret) + audit_tk_injoffset(ts_delta); + return ret; } EXPORT_SYMBOL(do_settimeofday64); @@ -1278,7 +1282,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts) /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || - !timespec64_valid_strict(&tmp)) { + !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } @@ -1409,7 +1413,7 @@ int timekeeping_notify(struct clocksource *clock) void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; do { @@ -1431,7 +1435,7 @@ EXPORT_SYMBOL(ktime_get_raw_ts64); int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; int ret; do { @@ -1450,7 +1454,7 @@ int timekeeping_valid_for_hres(void) u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 ret; do { @@ -1527,7 +1531,7 @@ void __init timekeeping_init(void) unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); - if (timespec64_valid_strict(&wall_time) && + if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { @@ -2150,7 +2154,7 @@ EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2164,7 +2168,7 @@ void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2303,6 +2307,7 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc) int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; + struct audit_ntp_data ad; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; @@ -2322,15 +2327,19 @@ int do_adjtimex(struct __kernel_timex *txc) ret = timekeeping_inject_offset(&delta); if (ret) return ret; + + audit_tk_injoffset(delta); } + audit_ntp_init(&ad); + ktime_get_real_ts64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; - ret = __do_adjtimex(txc, &ts, &tai); + ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); @@ -2341,6 +2350,8 @@ int do_adjtimex(struct __kernel_timex *txc) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + audit_ntp_log(&ad); + /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) timekeeping_advance(TK_ADV_FREQ); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 7a9b4eb7a1d5..141ab3ab0354 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void); extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +#ifdef CONFIG_GENERIC_SCHED_CLOCK +extern int sched_clock_suspend(void); +extern void sched_clock_resume(void); +#else +static inline int sched_clock_suspend(void) { return 0; } +static inline void sched_clock_resume(void) { } +#endif extern void do_timer(unsigned long ticks); extern void update_wall_time(void); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2fce056f8a49..343c7ba33b1c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -536,6 +536,8 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); + + trace_timer_start(timer, timer->expires, timer->flags); } static void @@ -757,13 +759,6 @@ static inline void debug_init(struct timer_list *timer) trace_timer_init(timer); } -static inline void -debug_activate(struct timer_list *timer, unsigned long expires) -{ - debug_timer_activate(timer); - trace_timer_start(timer, expires, timer->flags); -} - static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); @@ -1037,7 +1032,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option } } - debug_activate(timer, expires); + debug_timer_activate(timer); timer->expires = expires; /* @@ -1171,7 +1166,7 @@ void add_timer_on(struct timer_list *timer, int cpu) } forward_timer_base(base); - debug_activate(timer, timer->expires); + debug_timer_activate(timer); internal_add_timer(base, timer); raw_spin_unlock_irqrestore(&base->lock, flags); } @@ -1298,7 +1293,9 @@ int del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(del_timer_sync); #endif -static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *)) +static void call_timer_fn(struct timer_list *timer, + void (*fn)(struct timer_list *), + unsigned long baseclk) { int count = preempt_count(); @@ -1321,14 +1318,14 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list */ lock_map_acquire(&lockdep_map); - trace_timer_expire_entry(timer); + trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { - WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n", + WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent @@ -1342,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list static void expire_timers(struct timer_base *base, struct hlist_head *head) { + /* + * This value is required only for tracing. base->clk was + * incremented directly before expire_timers was called. But expiry + * is related to the old base->clk value. + */ + unsigned long baseclk = base->clk - 1; + while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); @@ -1355,11 +1359,11 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); - call_timer_fn(timer, fn); + call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); } else { raw_spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn); + call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); } } diff --git a/kernel/torture.c b/kernel/torture.c index 8faa1a9aaeb9..17b2be9bde12 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -88,6 +88,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; + if (num_online_cpus() <= 1) + return false; /* Can't offline the last CPU. */ if (verbose > 1) pr_alert("%s" TORTURE_FLAG diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fac0ddf8a8e2..e1c6d79fb4cc 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -723,6 +723,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) #endif case BLKTRACESTART: start = 1; + /* fall through */ case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d64c00afceb5..b496ffdf5f36 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,6 +14,8 @@ #include <linux/syscalls.h> #include <linux/error-injection.h> +#include <asm/tlb.h> + #include "trace_probe.h" #include "trace.h" @@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. + * + * nmi_uaccess_okay() ensures the probe is not run in an interim + * state, when the task or mm are switched. This is specifically + * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || @@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; + if (unlikely(!nmi_uaccess_okay())) + return -EPERM; if (!access_ok(unsafe_ptr, size)) return -EPERM; @@ -569,6 +577,12 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_probe_read: return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: @@ -909,6 +923,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; +static bool raw_tp_writable_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off == 0) { + if (size != sizeof(u64) || type != BPF_READ) + return false; + info->reg_type = PTR_TO_TP_BUFFER; + } + return raw_tp_prog_is_valid_access(off, size, type, prog, info); +} + +const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { + .get_func_proto = raw_tp_prog_func_proto, + .is_valid_access = raw_tp_writable_prog_is_valid_access, +}; + +const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -1198,6 +1233,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; + if (prog->aux->max_tp_access > btp->writable_size) + return -EINVAL; + return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa79323331b2..b920358dd8f7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -33,6 +33,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/rcupdate.h> +#include <linux/kprobes.h> #include <trace/events/sched.h> @@ -1992,7 +1993,7 @@ static void print_bug_type(void) * modifying the code. @failed should be one of either: * EFAULT - if the problem happens on reading the @ip address * EINVAL - if what is read at @ip is not what was expected - * EPERM - if the problem happens on writting to the @ip address + * EPERM - if the problem happens on writing to the @ip address */ void ftrace_bug(int failed, struct dyn_ftrace *rec) { @@ -2391,7 +2392,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } - return -1; /* unknow ftrace bug */ + return -1; /* unknown ftrace bug */ } void __weak ftrace_replace_code(int mod_flags) @@ -3004,7 +3005,7 @@ ftrace_allocate_pages(unsigned long num_to_init) int cnt; if (!num_to_init) - return 0; + return NULL; start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL); if (!pg) @@ -4755,7 +4756,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, int reset, int enable) { - return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable); } /** @@ -5463,7 +5464,7 @@ void ftrace_create_filter_files(struct ftrace_ops *ops, /* * The name "destroy_filter_files" is really a misnomer. Although - * in the future, it may actualy delete the files, but this is + * in the future, it may actually delete the files, but this is * really intended to make sure the ops passed in are disabled * and that when this function returns, the caller is free to * free the ops. @@ -5786,7 +5787,7 @@ void ftrace_module_enable(struct module *mod) /* * If the tracing is enabled, go ahead and enable the record. * - * The reason not to enable the record immediatelly is the + * The reason not to enable the record immediately is the * inherent check of ftrace_make_nop/ftrace_make_call for * correct previous instructions. Making first the NOP * conversion puts the module to the correct state, thus @@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) tr->ops->func = ftrace_stub; } -static inline void +static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { @@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } +NOKPROBE_SYMBOL(ftrace_ops_list_func); #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } +NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif /* @@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); trace_clear_recursion(bit); } +NOKPROBE_SYMBOL(ftrace_ops_assist_func); /** * ftrace_ops_get_func - get the function a trampoline should call diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9a91479bbbfe..4ee8d8aa3d0f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -762,7 +762,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) preempt_disable_notrace(); time = rb_time_stamp(buffer); - preempt_enable_no_resched_notrace(); + preempt_enable_notrace(); return time; } @@ -4191,6 +4191,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer * @buffer: The ring buffer to read from * @cpu: The cpu buffer to iterate over + * @flags: gfp flags to use for memory allocation * * This performs the initial preparations necessary to iterate * through the buffer. Memory is allocated, buffer recording @@ -4208,7 +4209,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * This overall must be paired with ring_buffer_read_finish. */ struct ring_buffer_iter * -ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) +ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_iter *iter; @@ -4216,7 +4217,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - iter = kmalloc(sizeof(*iter), GFP_KERNEL); + iter = kmalloc(sizeof(*iter), flags); if (!iter) return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 94ffc1c559d5..ec439999f387 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -159,6 +159,8 @@ static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ static int tracing_set_tracer(struct trace_array *tr, const char *buf); +static void ftrace_trace_userstack(struct ring_buffer *buffer, + unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; @@ -496,8 +498,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, * not modified. */ pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) + if (!pid_list) { + trace_parser_put(&parser); return -ENOMEM; + } pid_list->pid_max = READ_ONCE(pid_max); @@ -507,6 +511,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); if (!pid_list->pids) { + trace_parser_put(&parser); kfree(pid_list); return -ENOMEM; } @@ -2749,12 +2754,21 @@ trace_function(struct trace_array *tr, #ifdef CONFIG_STACKTRACE -#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) +/* Allow 4 levels of nesting: normal, softirq, irq, NMI */ +#define FTRACE_KSTACK_NESTING 4 + +#define FTRACE_KSTACK_ENTRIES (PAGE_SIZE / FTRACE_KSTACK_NESTING) + struct ftrace_stack { - unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; + unsigned long calls[FTRACE_KSTACK_ENTRIES]; }; -static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); + +struct ftrace_stacks { + struct ftrace_stack stacks[FTRACE_KSTACK_NESTING]; +}; + +static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct ring_buffer *buffer, @@ -2763,13 +2777,10 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, { struct trace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; + unsigned int size, nr_entries; + struct ftrace_stack *fstack; struct stack_entry *entry; - struct stack_trace trace; - int use_stack; - int size = FTRACE_STACK_ENTRIES; - - trace.nr_entries = 0; - trace.skip = skip; + int stackidx; /* * Add one, for this function and the call to save_stack_trace() @@ -2777,7 +2788,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ #ifndef CONFIG_UNWINDER_ORC if (!regs) - trace.skip++; + skip++; #endif /* @@ -2788,53 +2799,40 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ preempt_disable_notrace(); - use_stack = __this_cpu_inc_return(ftrace_stack_reserve); + stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; + + /* This should never happen. If it does, yell once and skip */ + if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING)) + goto out; + /* - * We don't need any atomic variables, just a barrier. - * If an interrupt comes in, we don't care, because it would - * have exited and put the counter back to what we want. - * We just need a barrier to keep gcc from moving things - * around. + * The above __this_cpu_inc_return() is 'atomic' cpu local. An + * interrupt will either see the value pre increment or post + * increment. If the interrupt happens pre increment it will have + * restored the counter when it returns. We just need a barrier to + * keep gcc from moving things around. */ barrier(); - if (use_stack == 1) { - trace.entries = this_cpu_ptr(ftrace_stack.calls); - trace.max_entries = FTRACE_STACK_MAX_ENTRIES; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); - - if (trace.nr_entries > size) - size = trace.nr_entries; - } else - /* From now on, use_stack is a boolean */ - use_stack = 0; + fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx; + size = ARRAY_SIZE(fstack->calls); - size *= sizeof(unsigned long); + if (regs) { + nr_entries = stack_trace_save_regs(regs, fstack->calls, + size, skip); + } else { + nr_entries = stack_trace_save(fstack->calls, size, skip); + } + size = nr_entries * sizeof(unsigned long); event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, sizeof(*entry) + size, flags, pc); if (!event) goto out; entry = ring_buffer_event_data(event); - memset(&entry->caller, 0, size); - - if (use_stack) - memcpy(&entry->caller, trace.entries, - trace.nr_entries * sizeof(unsigned long)); - else { - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.entries = entry->caller; - if (regs) - save_stack_trace_regs(regs, &trace); - else - save_stack_trace(&trace); - } - - entry->size = trace.nr_entries; + memcpy(&entry->caller, fstack->calls, size); + entry->size = nr_entries; if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); @@ -2904,15 +2902,15 @@ void trace_dump_stack(int skip) } EXPORT_SYMBOL_GPL(trace_dump_stack); +#ifdef CONFIG_USER_STACKTRACE_SUPPORT static DEFINE_PER_CPU(int, user_stack_count); -void +static void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - struct stack_trace trace; if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) return; @@ -2943,12 +2941,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); - trace.nr_entries = 0; - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.skip = 0; - trace.entries = entry->caller; - - save_stack_trace_user(&trace); + stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES); if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); @@ -2957,13 +2950,12 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) out: preempt_enable(); } - -#ifdef UNUSED -static void __trace_userstack(struct trace_array *tr, unsigned long flags) +#else /* CONFIG_USER_STACKTRACE_SUPPORT */ +static void ftrace_trace_userstack(struct ring_buffer *buffer, + unsigned long flags, int pc) { - ftrace_trace_userstack(tr, flags, preempt_count()); } -#endif /* UNUSED */ +#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* CONFIG_STACKTRACE */ @@ -4079,7 +4071,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, + cpu, GFP_KERNEL); } ring_buffer_read_prepare_sync(); for_each_tracing_cpu(cpu) { @@ -4089,7 +4082,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, + cpu, GFP_KERNEL); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); @@ -7023,35 +7017,43 @@ struct buffer_ref { struct ring_buffer *buffer; void *page; int cpu; - int ref; + refcount_t refcount; }; +static void buffer_ref_release(struct buffer_ref *ref) +{ + if (!refcount_dec_and_test(&ref->refcount)) + return; + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + kfree(ref); +} + static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - ref->ref++; + if (refcount_read(&ref->refcount) > INT_MAX/2) + return false; + + refcount_inc(&ref->refcount); + return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = generic_pipe_buf_steal, + .steal = generic_pipe_buf_nosteal, .get = buffer_pipe_buf_get, }; @@ -7064,11 +7066,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); spd->partial[i].private = 0; } @@ -7123,7 +7121,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - ref->ref = 1; + refcount_set(&ref->refcount, 1); ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d80cee49e0eb..639047b259d7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -782,17 +782,9 @@ void update_max_tr_single(struct trace_array *tr, #endif /* CONFIG_TRACER_MAX_TRACE */ #ifdef CONFIG_STACKTRACE -void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, - int pc); - void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); #else -static inline void ftrace_trace_userstack(struct ring_buffer *buffer, - unsigned long flags, int pc) -{ -} - static inline void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 4ad967453b6f..3ea65cdff30d 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -205,6 +205,8 @@ void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant) { + unsigned long flags = user_access_save(); + /* A constant is always correct */ if (is_constant) { f->constant++; @@ -223,6 +225,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, f->data.correct++; else f->data.incorrect++; + + user_access_restore(flags); } EXPORT_SYMBOL(ftrace_likely_update); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index dd1f43588d70..fa100ed3b4de 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -74,7 +74,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) static int create_dyn_event(int argc, char **argv) { struct dyn_event_operations *ops; - int ret; + int ret = -ENODEV; if (argv[0][0] == '-' || argv[0][0] == '!') return dyn_event_release(argc, argv, NULL); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ca46339f3009..a1d20421f4b0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3713,7 +3713,6 @@ static void track_data_destroy(struct hist_trigger_data *hist_data, struct trace_event_file *file = hist_data->event_file; destroy_hist_field(data->track_data.track_var, 0); - destroy_hist_field(data->track_data.var_ref, 0); if (data->action == ACTION_SNAPSHOT) { struct track_data *track_data; @@ -5187,7 +5186,6 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, u64 var_ref_vals[TRACING_MAP_VARS_MAX]; char compound_key[HIST_KEY_SIZE_MAX]; struct tracing_map_elt *elt = NULL; - struct stack_trace stacktrace; struct hist_field *key_field; u64 field_contents; void *key = NULL; @@ -5199,14 +5197,9 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, key_field = hist_data->fields[i]; if (key_field->flags & HIST_FIELD_FL_STACKTRACE) { - stacktrace.max_entries = HIST_STACKTRACE_DEPTH; - stacktrace.entries = entries; - stacktrace.nr_entries = 0; - stacktrace.skip = HIST_STACKTRACE_SKIP; - - memset(stacktrace.entries, 0, HIST_STACKTRACE_SIZE); - save_stack_trace(&stacktrace); - + memset(entries, 0, HIST_STACKTRACE_SIZE); + stack_trace_save(entries, HIST_STACKTRACE_DEPTH, + HIST_STACKTRACE_SKIP); key = entries; } else { field_contents = key_field->fn(key_field, elt, rbe, rec); @@ -5247,7 +5240,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m, unsigned int i; for (i = 0; i < max_entries; i++) { - if (stacktrace_entries[i] == ULONG_MAX) + if (!stacktrace_entries[i]) return; seq_printf(m, "%*c", 1 + spaces, ' '); diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index d953c163a079..810d78a8d14c 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -51,14 +51,16 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter.buffer_iter[cpu] = - ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu); + ring_buffer_read_prepare(iter.trace_buffer->buffer, + cpu, GFP_ATOMIC); ring_buffer_read_start(iter.buffer_iter[cpu]); tracing_iter_reset(&iter, cpu); } } else { iter.cpu_file = cpu_file; iter.buffer_iter[cpu_file] = - ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file); + ring_buffer_read_prepare(iter.trace_buffer->buffer, + cpu_file, GFP_ATOMIC); ring_buffer_read_start(iter.buffer_iter[cpu_file]); tracing_iter_reset(&iter, cpu_file); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 99592c27465e..5d5129b05df7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,7 +35,7 @@ static struct dyn_event_operations trace_kprobe_ops = { .match = trace_kprobe_match, }; -/** +/* * Kprobe event core functions */ struct trace_kprobe { @@ -221,7 +221,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, tk->rp.maxactive = maxactive; - if (!event || !is_good_name(event)) { + if (!event || !group) { ret = -EINVAL; goto error; } @@ -231,11 +231,6 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, if (!tk->tp.call.name) goto error; - if (!group || !is_good_name(group)) { - ret = -EINVAL; - goto error; - } - tk->tp.class.system = kstrdup(group, GFP_KERNEL); if (!tk->tp.class.system) goto error; @@ -624,7 +619,11 @@ static int trace_kprobe_create(int argc, const char *argv[]) if (event) event++; - if (is_return && isdigit(argv[0][1])) { + if (isdigit(argv[0][1])) { + if (!is_return) { + pr_info("Maxactive is not for kprobe"); + return -EINVAL; + } if (event) len = event - &argv[0][1] - 1; else @@ -634,8 +633,8 @@ static int trace_kprobe_create(int argc, const char *argv[]) memcpy(buf, &argv[0][1], len); buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); - if (ret) { - pr_info("Failed to parse maxactive.\n"); + if (ret || !maxactive) { + pr_info("Invalid maxactive number\n"); return ret; } /* kretprobes instances are iterated over via a list. The @@ -694,9 +693,9 @@ static int trace_kprobe_create(int argc, const char *argv[]) tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, argc, is_return); if (IS_ERR(tk)) { - pr_info("Failed to allocate trace_probe.(%d)\n", - (int)PTR_ERR(tk)); ret = PTR_ERR(tk); + /* This must return -ENOMEM otherwise there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM); goto out; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 89da34b326e3..8f8411e7835f 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -13,7 +13,7 @@ #include "trace_probe.h" -const char *reserved_field_names[] = { +static const char *reserved_field_names[] = { "common_type", "common_flags", "common_preempt_count", @@ -159,6 +159,7 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup, char *buf) { const char *slash, *event = *pevent; + int len; slash = strchr(event, '/'); if (slash) { @@ -171,12 +172,25 @@ int traceprobe_parse_event_name(const char **pevent, const char **pgroup, return -E2BIG; } strlcpy(buf, event, slash - event + 1); + if (!is_good_name(buf)) { + pr_info("Group name must follow the same rules as C identifiers\n"); + return -EINVAL; + } *pgroup = buf; *pevent = slash + 1; + event = *pevent; } - if (strlen(event) == 0) { + len = strlen(event); + if (len == 0) { pr_info("Event name is not specified\n"); return -EINVAL; + } else if (len > MAX_EVENT_NAME_LEN) { + pr_info("Event name is too long\n"); + return -E2BIG; + } + if (!is_good_name(event)) { + pr_info("Event name must follow the same rules as C identifiers\n"); + return -EINVAL; } return 0; } @@ -548,6 +562,8 @@ int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, char *arg, body = strchr(arg, '='); if (body) { + if (body - arg > MAX_ARG_NAME_LEN || body == arg) + return -EINVAL; parg->name = kmemdup_nul(arg, body - arg, GFP_KERNEL); body++; } else { diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 8a63f8bc01bc..2177c206de15 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -32,6 +32,7 @@ #define MAX_TRACE_ARGS 128 #define MAX_ARGSTR_LEN 63 #define MAX_ARRAY_LEN 64 +#define MAX_ARG_NAME_LEN 32 #define MAX_STRING_SIZE PATH_MAX /* Reserved field names */ diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index eec648a0d673..5d16f73898db 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -18,44 +18,32 @@ #include "trace.h" -static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] = - { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX }; -unsigned stack_trace_index[STACK_TRACE_ENTRIES]; +#define STACK_TRACE_ENTRIES 500 -/* - * Reserve one entry for the passed in ip. This will allow - * us to remove most or all of the stack size overhead - * added by the stack tracer itself. - */ -struct stack_trace stack_trace_max = { - .max_entries = STACK_TRACE_ENTRIES - 1, - .entries = &stack_dump_trace[0], -}; +static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES]; +static unsigned stack_trace_index[STACK_TRACE_ENTRIES]; -unsigned long stack_trace_max_size; -arch_spinlock_t stack_trace_max_lock = +static unsigned int stack_trace_nr_entries; +static unsigned long stack_trace_max_size; +static arch_spinlock_t stack_trace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; DEFINE_PER_CPU(int, disable_stack_tracer); static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; -static int last_stack_tracer_enabled; -void stack_trace_print(void) +static void print_max_stack(void) { long i; int size; pr_emerg(" Depth Size Location (%d entries)\n" " ----- ---- --------\n", - stack_trace_max.nr_entries); + stack_trace_nr_entries); - for (i = 0; i < stack_trace_max.nr_entries; i++) { - if (stack_dump_trace[i] == ULONG_MAX) - break; - if (i+1 == stack_trace_max.nr_entries || - stack_dump_trace[i+1] == ULONG_MAX) + for (i = 0; i < stack_trace_nr_entries; i++) { + if (i + 1 == stack_trace_nr_entries) size = stack_trace_index[i]; else size = stack_trace_index[i] - stack_trace_index[i+1]; @@ -65,16 +53,7 @@ void stack_trace_print(void) } } -/* - * When arch-specific code overrides this function, the following - * data should be filled up, assuming stack_trace_max_lock is held to - * prevent concurrent updates. - * stack_trace_index[] - * stack_trace_max - * stack_trace_max_size - */ -void __weak -check_stack(unsigned long ip, unsigned long *stack) +static void check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; static int tracer_frame; @@ -110,13 +89,12 @@ check_stack(unsigned long ip, unsigned long *stack) stack_trace_max_size = this_size; - stack_trace_max.nr_entries = 0; - stack_trace_max.skip = 0; - - save_stack_trace(&stack_trace_max); + stack_trace_nr_entries = stack_trace_save(stack_dump_trace, + ARRAY_SIZE(stack_dump_trace) - 1, + 0); /* Skip over the overhead of the stack tracer itself */ - for (i = 0; i < stack_trace_max.nr_entries; i++) { + for (i = 0; i < stack_trace_nr_entries; i++) { if (stack_dump_trace[i] == ip) break; } @@ -125,7 +103,7 @@ check_stack(unsigned long ip, unsigned long *stack) * Some archs may not have the passed in ip in the dump. * If that happens, we need to show everything. */ - if (i == stack_trace_max.nr_entries) + if (i == stack_trace_nr_entries) i = 0; /* @@ -143,15 +121,13 @@ check_stack(unsigned long ip, unsigned long *stack) * loop will only happen once. This code only takes place * on a new max, so it is far from a fast path. */ - while (i < stack_trace_max.nr_entries) { + while (i < stack_trace_nr_entries) { int found = 0; stack_trace_index[x] = this_size; p = start; - for (; p < top && i < stack_trace_max.nr_entries; p++) { - if (stack_dump_trace[i] == ULONG_MAX) - break; + for (; p < top && i < stack_trace_nr_entries; p++) { /* * The READ_ONCE_NOCHECK is used to let KASAN know that * this is not a stack-out-of-bounds error. @@ -182,12 +158,10 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } - stack_trace_max.nr_entries = x; - for (; x < i; x++) - stack_dump_trace[x] = ULONG_MAX; + stack_trace_nr_entries = x; if (task_stack_end_corrupted(current)) { - stack_trace_print(); + print_max_stack(); BUG(); } @@ -286,7 +260,7 @@ __next(struct seq_file *m, loff_t *pos) { long n = *pos - 1; - if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX) + if (n >= stack_trace_nr_entries) return NULL; m->private = (void *)n; @@ -350,7 +324,7 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, " Depth Size Location" " (%d entries)\n" " ----- ---- --------\n", - stack_trace_max.nr_entries); + stack_trace_nr_entries); if (!stack_tracer_enabled && !stack_trace_max_size) print_disabled(m); @@ -360,12 +334,10 @@ static int t_show(struct seq_file *m, void *v) i = *(long *)v; - if (i >= stack_trace_max.nr_entries || - stack_dump_trace[i] == ULONG_MAX) + if (i >= stack_trace_nr_entries) return 0; - if (i+1 == stack_trace_max.nr_entries || - stack_dump_trace[i+1] == ULONG_MAX) + if (i + 1 == stack_trace_nr_entries) size = stack_trace_index[i]; else size = stack_trace_index[i] - stack_trace_index[i+1]; @@ -422,23 +394,21 @@ stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int was_enabled; int ret; mutex_lock(&stack_sysctl_mutex); + was_enabled = !!stack_tracer_enabled; ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret || !write || - (last_stack_tracer_enabled == !!stack_tracer_enabled)) + if (ret || !write || (was_enabled == !!stack_tracer_enabled)) goto out; - last_stack_tracer_enabled = !!stack_tracer_enabled; - if (stack_tracer_enabled) register_ftrace_function(&trace_ops); else unregister_ftrace_function(&trace_ops); - out: mutex_unlock(&stack_sysctl_mutex); return ret; @@ -454,7 +424,6 @@ static __init int enable_stacktrace(char *str) strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE); stack_tracer_enabled = 1; - last_stack_tracer_enabled = 1; return 1; } __setup("stacktrace", enable_stacktrace); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index f93a56d2db27..fa8fbff736d6 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -314,6 +314,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct ring_buffer_event *event; struct ring_buffer *buffer; unsigned long irq_flags; + unsigned long args[6]; int pc; int syscall_nr; int size; @@ -347,7 +348,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry = ring_buffer_event_data(event); entry->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); + syscall_get_arguments(current, regs, args); + memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args); event_trigger_unlock_commit(trace_file, buffer, event, entry, irq_flags, pc); @@ -583,6 +585,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; struct hlist_head *head; + unsigned long args[6]; bool valid_prog_array; int syscall_nr; int rctx; @@ -613,8 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) return; rec->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, - (unsigned long *)&rec->args); + syscall_get_arguments(current, regs, args); + memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args); if ((valid_prog_array && !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) || diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 9bde07c06362..be78d99ee6bc 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -273,10 +273,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; - if (!event || !is_good_name(event)) - return ERR_PTR(-EINVAL); - - if (!group || !is_good_name(group)) + if (!event || !group) return ERR_PTR(-EINVAL); tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); @@ -524,8 +521,9 @@ static int trace_uprobe_create(int argc, const char **argv) tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { - pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); ret = PTR_ERR(tu); + /* This must return -ENOMEM otherwise there is a bug */ + WARN_ON_ONCE(ret != -ENOMEM); goto fail_address_parse; } tu->offset = offset; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 8fbfda94a67b..7f9e7b9306fe 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -42,9 +42,9 @@ int __read_mostly watchdog_user_enabled = 1; int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; -int __read_mostly nmi_watchdog_available; +static int __read_mostly nmi_watchdog_available; -struct cpumask watchdog_allowed_mask __read_mostly; +static struct cpumask watchdog_allowed_mask __read_mostly; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -554,13 +554,15 @@ static void softlockup_start_all(void) int lockup_detector_online_cpu(unsigned int cpu) { - watchdog_enable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { - watchdog_disable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_disable(cpu); return 0; } @@ -588,7 +590,7 @@ static void lockup_detector_reconfigure(void) * Create the watchdog thread infrastructure and configure the detector(s). * * The threads are not unparked as watchdog_allowed_mask is empty. When - * the threads are sucessfully initialized, take the proper locks and + * the threads are successfully initialized, take the proper locks and * unpark the threads in the watchdog_cpumask if the watchdog is enabled. */ static __init void lockup_detector_setup(void) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 71381168dede..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,7 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", + this_cpu); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 37a32884986b..9657315405de 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -841,43 +841,32 @@ static void wake_up_worker(struct worker_pool *pool) } /** - * wq_worker_waking_up - a worker is waking up + * wq_worker_running - a worker is running again * @task: task waking up - * @cpu: CPU @task is waking up to * - * This function is called during try_to_wake_up() when a worker is - * being awoken. - * - * CONTEXT: - * spin_lock_irq(rq->lock) + * This function is called when a worker returns from schedule() */ -void wq_worker_waking_up(struct task_struct *task, int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); - if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->cpu != cpu); + if (!worker->sleeping) + return; + if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); - } + worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * - * This function is called during schedule() when a busy worker is - * going to sleep. Worker on the same cpu can be woken up by - * returning pointer to its task. - * - * CONTEXT: - * spin_lock_irq(rq->lock) - * - * Return: - * Worker task on @cpu to wake up, %NULL if none. + * This function is called from schedule() when a busy worker is + * going to sleep. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; + struct worker *next, *worker = kthread_data(task); struct worker_pool *pool; /* @@ -886,13 +875,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; pool = worker->pool; - /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id())) - return NULL; + if (WARN_ON_ONCE(worker->sleeping)) + return; + + worker->sleeping = 1; + spin_lock_irq(&pool->lock); /* * The counterpart of the following dec_and_test, implied mb, @@ -906,9 +897,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && - !list_empty(&pool->worklist)) - to_wakeup = first_idle_worker(pool); - return to_wakeup ? to_wakeup->task : NULL; + !list_empty(&pool->worklist)) { + next = first_idle_worker(pool); + if (next) + wake_up_process(next->task); + } + spin_unlock_irq(&pool->lock); } /** @@ -2282,7 +2276,7 @@ __acquires(&pool->lock) if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" - " last function: %pf\n", + " last function: %ps\n", current->comm, preempt_count(), task_pid_nr(current), worker->current_func); debug_show_held_locks(current); @@ -2601,11 +2595,11 @@ static void check_flush_dependency(struct workqueue_struct *target_wq, worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, - "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf", + "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), - "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf", + "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } @@ -4273,7 +4267,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, INIT_LIST_HEAD(&wq->list); if (alloc_and_link_pwqs(wq) < 0) - goto err_free_wq; + goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; @@ -4299,9 +4293,10 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, return wq; -err_free_wq: +err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); +err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; @@ -4595,7 +4590,7 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { - printk("%sWorkqueue: %s %pf", log_lvl, name, fn); + printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); @@ -4620,7 +4615,7 @@ static void pr_cont_work(bool comma, struct work_struct *work) pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { - pr_cont("%s %pf", comma ? "," : "", work->func); + pr_cont("%s %ps", comma ? "," : "", work->func); } } @@ -4652,7 +4647,7 @@ static void show_pwq(struct pool_workqueue *pwq) if (worker->current_pwq != pwq) continue; - pr_cont("%s %d%s:%pf", comma ? "," : "", + pr_cont("%s %d%s:%ps", comma ? "," : "", task_pid_nr(worker->task), worker == pwq->wq->rescuer ? "(RESCUER)" : "", worker->current_func); @@ -4937,7 +4932,7 @@ static void rebind_workers(struct worker_pool *pool) * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in - * wq_worker_waking_up(). Without it, NOT_RUNNING test may + * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index cb68b03ca89a..498de0e909a4 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -44,6 +44,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + int sleeping; /* None */ /* * Opaque string set with work_set_desc(). Printed out with task @@ -72,8 +73,8 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |