diff options
Diffstat (limited to 'kernel')
35 files changed, 563 insertions, 206 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ee4c82667d65..4da543d6bea2 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5,6 +5,7 @@ #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> +#include <linux/ctype.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/anon_inodes.h> @@ -426,6 +427,30 @@ 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) +{ + /* offset must be valid */ + const char *src = &btf->strings[offset]; + const char *src_limit; + + if (!isalpha(*src) && *src != '_') + return false; + + /* set a limit on identifier length */ + src_limit = src + KSYM_NAME_LEN; + src++; + while (*src && src < src_limit) { + if (!isalnum(*src) && *src != '_') + return false; + src++; + } + + return !*src; +} + static const char *btf_name_by_offset(const struct btf *btf, u32 offset) { if (!offset) @@ -1143,6 +1168,22 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* typedef type must have a valid name, and other ref types, + * volatile, const, restrict, should have a null name. + */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + } else { + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + } + btf_verifier_log_type(env, t, NULL); return 0; @@ -1300,6 +1341,13 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* fwd type must have a valid name */ + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); return 0; @@ -1356,6 +1404,12 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* array type should not have a name */ + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; @@ -1532,6 +1586,13 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* struct type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); last_offset = 0; @@ -1543,6 +1604,12 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* struct member either no name or a valid one */ + if (member->name_off && + !btf_name_valid_identifier(btf, member->name_off)) { + btf_verifier_log_member(env, t, member, "Invalid name"); + return -EINVAL; + } /* A member cannot be in type void */ if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { btf_verifier_log_member(env, t, member, @@ -1730,6 +1797,13 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* enum type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { @@ -1739,6 +1813,14 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* enum member must have a valid name */ + if (!enums[i].name_off || + !btf_name_valid_identifier(btf, enums[i].name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log(env, "\t%s val=%d\n", btf_name_by_offset(btf, enums[i].name_off), enums[i].val); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6377225b2082..b1a3545d0ec8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -553,7 +553,6 @@ bool is_bpf_text_address(unsigned long addr) int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - unsigned long symbol_start, symbol_end; struct bpf_prog_aux *aux; unsigned int it = 0; int ret = -ERANGE; @@ -566,10 +565,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); bpf_get_prog_name(aux->prog, sym); - *value = symbol_start; + *value = (unsigned long)aux->prog->bpf_func; *type = BPF_SYM_ELF_TYPE; ret = 0; @@ -674,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638..bed9d48a7ae9 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOENT; new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8bbd72d3a121..b384ea9f3254 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,6 +7,7 @@ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/capability.h> #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* 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) return -EINVAL; @@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int ret, numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u32 size, value_size; - u64 queue_size, cost; - - size = attr->max_entries + 1; - value_size = attr->value_size; - - queue_size = sizeof(*qs) + (u64) value_size * size; + u64 size, queue_size, cost; - cost = queue_size; + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ccb93277aae2..cf5040fd5434 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; goto done; } @@ -2158,11 +2159,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (info.nr_jited_ksyms && ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2170,10 +2171,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2182,7 +2190,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (info.nr_jited_func_lens && ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; @@ -2191,9 +2199,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4..fc760d00a38c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -175,6 +175,7 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 +#define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ @@ -3751,6 +3752,79 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, } } +/* compute branch direction of the expression "if (reg opcode val) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10] + */ +static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) +{ + if (__is_pointer_value(false, reg)) + return -1; + + switch (opcode) { + case BPF_JEQ: + if (tnum_is_const(reg->var_off)) + return !!tnum_equals_const(reg->var_off, val); + break; + case BPF_JNE: + if (tnum_is_const(reg->var_off)) + return !tnum_equals_const(reg->var_off, val); + break; + case BPF_JGT: + if (reg->umin_value > val) + return 1; + else if (reg->umax_value <= val) + return 0; + break; + case BPF_JSGT: + if (reg->smin_value > (s64)val) + return 1; + else if (reg->smax_value < (s64)val) + return 0; + break; + case BPF_JLT: + if (reg->umax_value < val) + return 1; + else if (reg->umin_value >= val) + return 0; + break; + case BPF_JSLT: + if (reg->smax_value < (s64)val) + return 1; + else if (reg->smin_value >= (s64)val) + return 0; + break; + case BPF_JGE: + if (reg->umin_value >= val) + return 1; + else if (reg->umax_value < val) + return 0; + break; + case BPF_JSGE: + if (reg->smin_value >= (s64)val) + return 1; + else if (reg->smax_value < (s64)val) + return 0; + break; + case BPF_JLE: + if (reg->umax_value <= val) + return 1; + else if (reg->umin_value > val) + return 0; + break; + case BPF_JSLE: + if (reg->smax_value <= (s64)val) + return 1; + else if (reg->smin_value > (s64)val) + return 0; + break; + } + + return -1; +} + /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. @@ -4152,21 +4226,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; - /* detect if R == 0 where R was initialized to zero earlier */ - if (BPF_SRC(insn->code) == BPF_K && - (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == SCALAR_VALUE && - tnum_is_const(dst_reg->var_off)) { - if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) || - (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) { - /* if (imm == imm) goto pc+off; - * only follow the goto, ignore fall-through - */ + if (BPF_SRC(insn->code) == BPF_K) { + int pred = is_branch_taken(dst_reg, insn->imm, opcode); + + if (pred == 1) { + /* only follow the goto, ignore fall-through */ *insn_idx += insn->off; return 0; - } else { - /* if (imm != imm) goto pc+off; - * only follow fall-through branch, since + } else if (pred == 0) { + /* only follow fall-through branch, since * that's where the program will go */ return 0; @@ -4980,7 +5048,7 @@ 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 *cur = env->cur_state, *new; - int i, j, err; + int i, j, err, states_cnt = 0; sl = env->explored_states[insn_idx]; if (!sl) @@ -5007,8 +5075,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 1; } sl = sl->next; + states_cnt++; } + if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) + return 0; + /* there were no equivalent states, remember current one. * technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) @@ -5148,6 +5220,9 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } + if (signal_pending(current)) + return -EAGAIN; + if (need_resched()) cond_resched(); @@ -5650,7 +5725,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c7f3b4c453c..91d5c38eb7e5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -10,6 +10,7 @@ #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/task.h> +#include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> @@ -367,6 +368,12 @@ static void lockdep_release_cpus_lock(void) #endif /* CONFIG_HOTPLUG_CPU */ +/* + * Architectures that need SMT-specific errata handling during SMT hotplug + * should override this. + */ +void __weak arch_smt_update(void) { } + #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); @@ -1011,6 +1018,7 @@ out: * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); + arch_smt_update(); return ret; } @@ -1139,6 +1147,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); + arch_smt_update(); return ret; } @@ -2055,12 +2064,6 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -/* - * Architectures that need SMT-specific errata handling during SMT hotplug - * should override this. - */ -void __weak arch_smt_update(void) { }; - static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 6ad4a9fcbd6f..7921ae4fca8d 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv) kdb_printf("no process for cpu %ld\n", cpu); return 0; } - sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu)); kdb_parse(buf); return 0; } kdb_printf("btc: cpu status: "); kdb_parse("cpu\n"); for_each_online_cpu(cpu) { - sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu)); kdb_parse(buf); touch_nmi_watchdog(); } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index ed5d34925ad0..6a4b41484afe 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int count; int i; int diag, dtab_count; - int key; + int key, buf_size, ret; diag = kdbgetintenv("DTABCOUNT", &dtab_count); @@ -336,9 +336,8 @@ poll_again: else p_tmp = tmpbuffer; len = strlen(p_tmp); - count = kallsyms_symbol_complete(p_tmp, - sizeof(tmpbuffer) - - (p_tmp - tmpbuffer)); + buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer); + count = kallsyms_symbol_complete(p_tmp, buf_size); if (tab == 2 && count > 0) { kdb_printf("\n%d symbols are found.", count); if (count > dtab_count) { @@ -350,9 +349,13 @@ poll_again: } kdb_printf("\n"); for (i = 0; i < count; i++) { - if (WARN_ON(!kallsyms_symbol_next(p_tmp, i))) + ret = kallsyms_symbol_next(p_tmp, i, buf_size); + if (WARN_ON(!ret)) break; - kdb_printf("%s ", p_tmp); + if (ret != -E2BIG) + kdb_printf("%s ", p_tmp); + else + kdb_printf("%s... ", p_tmp); *(p_tmp + len) = '\0'; } if (i >= dtab_count) diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 118527aa60ea..750497b0003a 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -173,11 +173,11 @@ int kdb_get_kbd_char(void) case KT_LATIN: if (isprint(keychar)) break; /* printable characters */ - /* drop through */ + /* fall through */ case KT_SPEC: if (keychar == K_ENTER) break; - /* drop through */ + /* fall through */ default: return -1; /* ignore unprintables */ } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index bb4fe4e1a601..d72b32c66f7d 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1192,7 +1192,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, if (reason == KDB_REASON_DEBUG) { /* special case below */ } else { - kdb_printf("\nEntering kdb (current=0x%p, pid %d) ", + kdb_printf("\nEntering kdb (current=0x%px, pid %d) ", kdb_current, kdb_current ? kdb_current->pid : 0); #if defined(CONFIG_SMP) kdb_printf("on processor %d ", raw_smp_processor_id()); @@ -1208,7 +1208,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, */ switch (db_result) { case KDB_DB_BPT: - kdb_printf("\nEntering kdb (0x%p, pid %d) ", + kdb_printf("\nEntering kdb (0x%px, pid %d) ", kdb_current, kdb_current->pid); #if defined(CONFIG_SMP) kdb_printf("on processor %d ", raw_smp_processor_id()); @@ -1493,6 +1493,7 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr, char cbuf[32]; char *c = cbuf; int i; + int j; unsigned long word; memset(cbuf, '\0', sizeof(cbuf)); @@ -1538,25 +1539,9 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr, wc.word = word; #define printable_char(c) \ ({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; }) - switch (bytesperword) { - case 8: + for (j = 0; j < bytesperword; j++) *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - addr += 4; - case 4: - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - addr += 2; - case 2: - *c++ = printable_char(*cp++); - addr++; - case 1: - *c++ = printable_char(*cp++); - addr++; - break; - } + addr += bytesperword; #undef printable_char } } @@ -2048,7 +2033,7 @@ static int kdb_lsmod(int argc, const char **argv) if (mod->state == MODULE_STATE_UNFORMED) continue; - kdb_printf("%-20s%8u 0x%p ", mod->name, + kdb_printf("%-20s%8u 0x%px ", mod->name, mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); @@ -2059,7 +2044,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->core_layout.base); + kdb_printf(" 0x%px", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { @@ -2341,7 +2326,7 @@ void kdb_ps1(const struct task_struct *p) return; cpu = kdb_process_cpu(p); - kdb_printf("0x%p %8d %8d %d %4d %c 0x%p %c%s\n", + kdb_printf("0x%px %8d %8d %d %4d %c 0x%px %c%s\n", (void *)p, p->pid, p->parent->pid, kdb_task_has_cpu(p), kdb_process_cpu(p), kdb_task_state_char(p), @@ -2354,7 +2339,7 @@ void kdb_ps1(const struct task_struct *p) } else { if (KDB_TSK(cpu) != p) kdb_printf(" Error: does not match running " - "process table (0x%p)\n", KDB_TSK(cpu)); + "process table (0x%px)\n", KDB_TSK(cpu)); } } } @@ -2687,7 +2672,7 @@ int kdb_register_flags(char *cmd, for_each_kdbcmd(kp, i) { if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) { kdb_printf("Duplicate kdb command registered: " - "%s, func %p help %s\n", cmd, func, help); + "%s, func %px help %s\n", cmd, func, help); return 1; } } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 1e5a502ba4a7..2118d8258b7c 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -83,7 +83,7 @@ typedef struct __ksymtab { unsigned long sym_start; unsigned long sym_end; } kdb_symtab_t; -extern int kallsyms_symbol_next(char *prefix_name, int flag); +extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size); extern int kallsyms_symbol_complete(char *prefix_name, int max_len); /* Exported Symbols for kernel loadable modules to use. */ diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 990b3cc526c8..50bf9b119bad 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -40,7 +40,7 @@ int kdbgetsymval(const char *symname, kdb_symtab_t *symtab) { if (KDB_DEBUG(AR)) - kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname, + kdb_printf("kdbgetsymval: symname=%s, symtab=%px\n", symname, symtab); memset(symtab, 0, sizeof(*symtab)); symtab->sym_start = kallsyms_lookup_name(symname); @@ -88,7 +88,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) char *knt1 = NULL; if (KDB_DEBUG(AR)) - kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab); + kdb_printf("kdbnearsym: addr=0x%lx, symtab=%px\n", addr, symtab); memset(symtab, 0, sizeof(*symtab)); if (addr < 4096) @@ -149,7 +149,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) symtab->mod_name = "kernel"; if (KDB_DEBUG(AR)) kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, " - "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret, + "symtab->mod_name=%px, symtab->sym_name=%px (%s)\n", ret, symtab->sym_start, symtab->mod_name, symtab->sym_name, symtab->sym_name); @@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len) * Parameters: * prefix_name prefix of a symbol name to lookup * flag 0 means search from the head, 1 means continue search. + * buf_size maximum length that can be written to prefix_name + * buffer * Returns: * 1 if a symbol matches the given prefix. * 0 if no string found */ -int kallsyms_symbol_next(char *prefix_name, int flag) +int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size) { int prefix_len = strlen(prefix_name); static loff_t pos; @@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag) pos = 0; while ((name = kdb_walk_kallsyms(&pos))) { - if (strncmp(name, prefix_name, prefix_len) == 0) { - strncpy(prefix_name, name, strlen(name)+1); - return 1; - } + if (!strncmp(name, prefix_name, prefix_len)) + return strscpy(prefix_name, name, buf_size); } return 0; } @@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_getphysword: bad width %ld\n", (long) size); @@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_getword: bad width %ld\n", (long) size); @@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) diag = kdb_putarea(addr, w8); break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_putword: bad width %ld\n", (long) size); @@ -887,13 +887,13 @@ void debug_kusage(void) __func__, dah_first); if (dah_first) { h_used = (struct debug_alloc_header *)debug_alloc_pool; - kdb_printf("%s: h_used %p size %d\n", __func__, h_used, + kdb_printf("%s: h_used %px size %d\n", __func__, h_used, h_used->size); } do { h_used = (struct debug_alloc_header *) ((char *)h_free + dah_overhead + h_free->size); - kdb_printf("%s: h_used %p size %d caller %p\n", + kdb_printf("%s: h_used %px size %d caller %px\n", __func__, h_used, h_used->size, h_used->caller); h_free = (struct debug_alloc_header *) (debug_alloc_pool + h_free->next); @@ -902,7 +902,7 @@ void debug_kusage(void) ((char *)h_free + dah_overhead + h_free->size); if ((char *)h_used - debug_alloc_pool != sizeof(debug_alloc_pool_aligned)) - kdb_printf("%s: h_used %p size %d caller %p\n", + kdb_printf("%s: h_used %px size %d caller %px\n", __func__, h_used, h_used->size, h_used->caller); out: spin_unlock(&dap_lock); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5731daa09a32..045930e32c0e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -679,7 +679,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, } if (!dev_is_dma_coherent(dev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 && + dev_addr != DIRECT_MAPPING_ERROR) arch_sync_dma_for_device(dev, phys, size, dir); return dev_addr; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 96d4bee83489..abbd8da9ac21 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -572,7 +572,9 @@ static void put_uprobe(struct uprobe *uprobe) * gets called, we don't get a chance to remove uprobe from * delayed_uprobe_list from remove_breakpoint(). Do it here. */ + mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(uprobe, NULL); + mutex_unlock(&delayed_uprobe_lock); kfree(uprobe); } } @@ -829,7 +831,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, BUG_ON((uprobe->offset & ~PAGE_MASK) + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - smp_wmb(); /* pairs with rmb() in find_active_uprobe() */ + smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: @@ -2178,10 +2180,18 @@ static void handle_swbp(struct pt_regs *regs) * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ - smp_rmb(); /* pairs with wmb() in install_breakpoint() */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; + /* + * Pairs with the smp_wmb() in prepare_uprobe(). + * + * Guarantees that if we see the UPROBE_COPY_INSN bit set, then + * we must also see the stores to &uprobe->arch performed by the + * prepare_uprobe() call. + */ + smp_rmb(); + /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; diff --git a/kernel/kcov.c b/kernel/kcov.c index 3ebd09efe72a..97959d7b77e2 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -56,7 +56,7 @@ struct kcov { struct task_struct *t; }; -static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) +static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -78,7 +78,7 @@ static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) return mode == needed_mode; } -static unsigned long canonicalize_ip(unsigned long ip) +static notrace unsigned long canonicalize_ip(unsigned long ip) { #ifdef CONFIG_RANDOMIZE_BASE ip -= kaslr_offset(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 80b34dffdfb9..c2cee9db5204 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -261,9 +261,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - if (mode & PTRACE_MODE_SCHED) - return false; - if (mode & PTRACE_MODE_NOAUDIT) return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); else @@ -331,16 +328,9 @@ ok: !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; - if (mode & PTRACE_MODE_SCHED) - return 0; return security_ptrace_access_check(task, mode); } -bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode) -{ - return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED); -} - bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; diff --git a/kernel/resource.c b/kernel/resource.c index b3a3a1fc499e..b0fbf685c77a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -319,16 +319,23 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /** - * Finds the lowest iomem resource that covers part of [start..end]. The - * caller must specify start, end, flags, and desc (which may be + * Finds the lowest iomem resource that covers part of [@start..@end]. The + * caller must specify @start, @end, @flags, and @desc (which may be * IORES_DESC_NONE). * - * If a resource is found, returns 0 and *res is overwritten with the part - * of the resource that's within [start..end]; if none is found, returns - * -1. + * If a resource is found, returns 0 and @*res is overwritten with the part + * of the resource that's within [@start..@end]; if none is found, returns + * -1 or -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. + * + * @start: start address of the resource searched for + * @end: end address of same resource + * @flags: flags which the resource must have + * @desc: descriptor the resource must have + * @first_lvl: walk only the first level children, if set + * @res: return ptr, if resource found */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, @@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @flags: I/O resource flags * @start: start addr * @end: end addr + * @arg: function argument for the callback @func + * @func: callback function that is called for each qualifying resource area * * NOTE: For a new descriptor search, define a new IORES_DESC in * <linux/ioport.h> and set it in 'desc' of a target resource entry. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f12225f26b70..6fedf3a98581 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5738,15 +5738,10 @@ int sched_cpu_activate(unsigned int cpu) #ifdef CONFIG_SCHED_SMT /* - * The sched_smt_present static key needs to be evaluated on every - * hotplug event because at boot time SMT might be disabled when - * the number of booted CPUs is limited. - * - * If then later a sibling gets hotplugged, then the key would stay - * off and SMT scheduling would never be functional. + * When going up, increment the number of cores with SMT present. */ - if (cpumask_weight(cpu_smt_mask(cpu)) > 1) - static_branch_enable_cpuslocked(&sched_smt_present); + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_inc_cpuslocked(&sched_smt_present); #endif set_cpu_active(cpu, true); @@ -5790,6 +5785,14 @@ int sched_cpu_deactivate(unsigned int cpu) */ synchronize_rcu_mult(call_rcu, call_rcu_sched); +#ifdef CONFIG_SCHED_SMT + /* + * When going down, decrement the number of cores with SMT present. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_dec_cpuslocked(&sched_smt_present); +#endif + if (!sched_smp_initialized) return 0; @@ -5851,11 +5854,14 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. + * happen. The hotplug lock is nevertheless taken to satisfy lockdep, + * but there won't be any contention on it. */ + cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..ac855b2f4774 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); @@ -5674,11 +5674,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return target; } -static unsigned long cpu_util_wake(int cpu, struct task_struct *p); +static unsigned long cpu_util_without(int cpu, struct task_struct *p); -static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +static unsigned long capacity_spare_without(int cpu, struct task_struct *p) { - return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0); + return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0); } /* @@ -5738,7 +5738,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); - spare_cap = capacity_spare_wake(i, p); + spare_cap = capacity_spare_without(i, p); if (spare_cap > max_spare_cap) max_spare_cap = spare_cap; @@ -5889,8 +5889,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p return prev_cpu; /* - * We need task's util for capacity_spare_wake, sync it up to prev_cpu's - * last_update_time. + * We need task's util for capacity_spare_without, sync it up to + * prev_cpu's last_update_time. */ if (!(sd_flag & SD_BALANCE_FORK)) sync_entity_load_avg(&p->se); @@ -6216,10 +6216,19 @@ static inline unsigned long cpu_util(int cpu) } /* - * cpu_util_wake: Compute CPU utilization with any contributions from - * the waking task p removed. + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. */ -static unsigned long cpu_util_wake(int cpu, struct task_struct *p) +static unsigned long cpu_util_without(int cpu, struct task_struct *p) { struct cfs_rq *cfs_rq; unsigned int util; @@ -6231,7 +6240,7 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) cfs_rq = &cpu_rq(cpu)->cfs; util = READ_ONCE(cfs_rq->avg.util_avg); - /* Discount task's blocked util from CPU's util */ + /* Discount task's util from CPU's util */ util -= min_t(unsigned int, util, task_util(p)); /* @@ -6240,14 +6249,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * a) if *p is the only task sleeping on this CPU, then: * cpu_util (== task_util) > util_est (== 0) * and thus we return: - * cpu_util_wake = (cpu_util - task_util) = 0 + * cpu_util_without = (cpu_util - task_util) = 0 * * b) if other tasks are SLEEPING on this CPU, which is now exiting * IDLE, then: * cpu_util >= task_util * cpu_util > util_est (== 0) * and thus we discount *p's blocked utilization to return: - * cpu_util_wake = (cpu_util - task_util) >= 0 + * cpu_util_without = (cpu_util - task_util) >= 0 * * c) if other tasks are RUNNABLE on that CPU and * util_est > cpu_util @@ -6260,8 +6269,33 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * covered by the following code when estimated utilization is * enabled. */ - if (sched_feat(UTIL_EST)) - util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued)); + if (sched_feat(UTIL_EST)) { + unsigned int estimated = + READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * Despite the following checks we still have a small window + * for a possible race, when an execl's select_task_rq_fair() + * races with LB's detach_task(): + * + * detach_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * ---------------------------------- A + * deactivate_task() \ + * dequeue_task() + RaceTime + * util_est_dequeue() / + * ---------------------------------- B + * + * The additional check on "current == p" it's required to + * properly fix the execl regression and it helps in further + * reducing the chances for the above race. + */ + if (unlikely(task_on_rq_queued(p) || current == p)) { + estimated -= min_t(unsigned int, estimated, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + } + util = max(util, estimated); + } /* * Utilization (estimated) can exceed the CPU capacity, thus let's diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7cdecfc010af..fe24de3fbc93 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@ static int psi_bug __read_mostly; -bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); /* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group) void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + } psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; *flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0; cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -633,38 +645,39 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - bool move_psi = !psi_disabled; unsigned int task_flags = 0; struct rq_flags rf; struct rq *rq; - if (move_psi) { - rq = task_rq_lock(task, &rf); + if (static_branch_likely(&psi_disabled)) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + } - if (task_on_rq_queued(task)) - task_flags = TSK_RUNNING; - else if (task->in_iowait) - task_flags = TSK_IOWAIT; + rq = task_rq_lock(task, &rf); - if (task->flags & PF_MEMSTALL) - task_flags |= TSK_MEMSTALL; + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; - if (task_flags) - psi_task_change(task, task_flags, 0); - } + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; - /* - * Lame to do this here, but the scheduler cannot be locked - * from the outside, so we move cgroups from inside sched/. - */ + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ rcu_assign_pointer(task->cgroups, to); - if (move_psi) { - if (task_flags) - psi_task_change(task, 0, task_flags); + if (task_flags) + psi_task_change(task, 0, task_flags); - task_rq_unlock(rq, task, &rf); - } + task_rq_unlock(rq, task, &rf); } #endif /* CONFIG_CGROUPS */ @@ -672,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; update_stats(group); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 618577fc9aa8..4e524ab589c9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -23,6 +23,7 @@ #include <linux/sched/prio.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> +#include <linux/sched/smt.h> #include <linux/sched/stat.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> @@ -936,9 +937,6 @@ static inline int cpu_of(struct rq *rq) #ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 4904c4677000..aa0de240fb41 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -66,7 +66,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!wakeup || p->sched_psi_wake_requeue) { @@ -86,7 +86,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!sleep) { @@ -102,7 +102,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -128,7 +128,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (unlikely(rq->curr->flags & PF_MEMSTALL)) diff --git a/kernel/stackleak.c b/kernel/stackleak.c index e42892926244..b193a59fc05b 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -11,6 +11,7 @@ */ #include <linux/stackleak.h> +#include <linux/kprobes.h> #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include <linux/jump_label.h> @@ -47,7 +48,7 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void stackleak_erase(void) +asmlinkage void notrace stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -101,8 +102,9 @@ asmlinkage void stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } +NOKPROBE_SYMBOL(stackleak_erase); -void __used stackleak_track_stack(void) +void __used notrace stackleak_track_stack(void) { /* * N.B. stackleak_erase() fills the kernel stack with the poison value, diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ce32cf741b25..8f0644af40be 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk, struct task_cputime cputime; unsigned long soft; - if (dl_task(tsk)) - check_dl_overrun(tsk); - /* * If cputimer is not running, then there are no active * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..9864a35c8bb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..e23eb9fc77aa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - int index = trace->depth; + int index = current->curr_ret_stack; function_profile_call(trace->func, 0, NULL, NULL); @@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) if (!fgraph_graph_time) { int index; - index = trace->depth; + index = current->curr_ret_stack; /* Append this call time to the parent time to subtract */ if (index) @@ -5460,6 +5460,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_ENABLED) ftrace_shutdown(ops, 0); ops->flags |= FTRACE_OPS_FL_DELETED; + ftrace_free_filter(ops); mutex_unlock(&ftrace_lock); } @@ -6814,6 +6815,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7040,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7071,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3b8c0e24ab30..447bd96ee658 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -512,12 +512,44 @@ enum { * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr, extern struct ftrace_hash *ftrace_graph_hash; extern struct ftrace_hash *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { + unsigned long addr = trace->func; int ret = 0; preempt_disable_notrace(); @@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr) } if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + + /* + * This needs to be cleared on the return functions + * when the depth is zero. + */ + trace_recursion_set(TRACE_GRAPH_BIT); + trace_recursion_set_depth(trace->depth); + /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still @@ -872,6 +913,13 @@ out: return ret; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ + if (trace_recursion_test(TRACE_GRAPH_BIT) && + trace->depth == trace_recursion_depth()) + trace_recursion_clear(TRACE_GRAPH_BIT); +} + static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; @@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } @@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; @@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ - return !(trace->depth || ftrace_graph_addr(trace->func)) || + return !(trace_recursion_test(TRACE_GRAPH_BIT) || + ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 84a65173b1e9..5574e862de8d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -570,11 +570,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, } } + kfree(op_stack); + kfree(inverts); return prog; out_free: kfree(op_stack); - kfree(prog_stack); kfree(inverts); + kfree(prog_stack); return ERR_PTR(ret); } @@ -1718,6 +1720,7 @@ static int create_filter(struct trace_event_call *call, err = process_preds(call, filter_string, *filterp, pe); if (err && set_str) append_filter_err(pe, *filterp); + create_filter_finish(pe); return err; } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2152d1e530cb..cd12ecb66eb9 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -732,8 +732,10 @@ int set_trigger_filter(char *filter_str, /* The filter is for the 'trigger' event, not the triggered event */ ret = create_event_filter(file->event_call, filter_str, false, &filter); - if (ret) - goto out; + /* + * If create_event_filter() fails, filter still needs to be freed. + * Which the calling code will do with data->filter. + */ assign: tmp = rcu_access_pointer(data->filter); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..086af4f5c3e8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +static int +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; + return 0; +} + +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = ++current->curr_ret_depth; + + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + goto out_ret; return 0; + out_ret: + current->curr_ret_stack--; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth--; + /* + * We still want to trace interrupts coming in if + * max_depth is set to 1. Make sure the decrement is + * seen before ftrace_graph_return. + */ + barrier(); } /* @@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); + ftrace_graph_return(&trace); + /* + * The ftrace_graph_return() may still access the current + * ret_stack structure, we need to make sure the update of + * curr_ret_stack is after that. + */ barrier(); current->curr_ret_stack--; /* @@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } - /* - * The trace should run after decrementing the ret counter - * in case an interrupt were to come in. We don't want to - * lose the interrupt if max_depth is set. - */ - ftrace_graph_return(&trace); - if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace) int cpu; int pc; + ftrace_graph_addr_finish(trace); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr) static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { + ftrace_graph_addr_finish(trace); + if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) return; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b7357f9f82a3..98ea6d28df15 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_dec(tr, &data, &flags)) return; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ef15a6683c0..bd30e9398d2a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -535,7 +535,7 @@ int traceprobe_update_arg(struct probe_arg *arg) if (code[1].op != FETCH_OP_IMM) return -EINVAL; - tmp = strpbrk("+-", code->data); + tmp = strpbrk(code->data, "+-"); if (tmp) c = *tmp; ret = traceprobe_split_symbol_offset(code->data, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index a86b303e6c67..7d04b9890755 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_preempt_disable(tr, &data, &pc)) return; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e5222b5fb4fe..923414a246e9 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; - ret = sort_idmaps(&new_map); - if (ret < 0) - goto out; - ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. @@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf, e->lower_first = lower_first; } + /* + * If we want to use binary search for lookup, this clones the extent + * array and sorts both copies. + */ + ret = sort_idmaps(&new_map); + if (ret < 0) + goto out; + /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, |