diff options
author | Jakub Kicinski <kuba@kernel.org> | 2021-05-27 19:22:11 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2021-05-27 19:55:10 +0300 |
commit | 5ada57a9a6b0be0e6dfcbd4afa519b0347fd5649 (patch) | |
tree | f82f466df9272bb0c385320b25adc51c45309f84 /kernel | |
parent | 59c56342459a483d5e563ed8b5fdb77ab7622a73 (diff) | |
parent | d7c5303fbc8ac874ae3e597a5a0d3707dc0230b4 (diff) | |
download | linux-5ada57a9a6b0be0e6dfcbd4afa519b0347fd5649.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
cdc-wdm: s/kill_urbs/poison_urbs/ to fix build
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'kernel')
35 files changed, 467 insertions, 239 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig new file mode 100644 index 000000000000..bd04f4a44c01 --- /dev/null +++ b/kernel/bpf/Kconfig @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: GPL-2.0-only + +# BPF interpreter that, for example, classic socket filters depend on. +config BPF + bool + +# Used by archs to tell that they support BPF JIT compiler plus which +# flavour. Only one of the two can be selected for a specific arch since +# eBPF JIT supersedes the cBPF JIT. + +# Classic BPF JIT (cBPF) +config HAVE_CBPF_JIT + bool + +# Extended BPF JIT (eBPF) +config HAVE_EBPF_JIT + bool + +# Used by archs to tell that they want the BPF JIT compiler enabled by +# default for kernels that were compiled with BPF JIT support. +config ARCH_WANT_DEFAULT_BPF_JIT + bool + +menu "BPF subsystem" + +config BPF_SYSCALL + bool "Enable bpf() system call" + select BPF + select IRQ_WORK + select TASKS_TRACE_RCU + select BINARY_PRINTF + select NET_SOCK_MSG if INET + default n + help + Enable the bpf() system call that allows to manipulate BPF programs + and maps via file descriptors. + +config BPF_JIT + bool "Enable BPF Just In Time compiler" + depends on BPF + depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT + depends on MODULES + help + BPF programs are normally handled by a BPF interpreter. This option + allows the kernel to generate native code when a program is loaded + into the kernel. This will significantly speed-up processing of BPF + programs. + + Note, an admin should enable this feature changing: + /proc/sys/net/core/bpf_jit_enable + /proc/sys/net/core/bpf_jit_harden (optional) + /proc/sys/net/core/bpf_jit_kallsyms (optional) + +config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid speculative + execution of BPF instructions by the interpreter. + +config BPF_JIT_DEFAULT_ON + def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON + depends on HAVE_EBPF_JIT && BPF_JIT + +config BPF_UNPRIV_DEFAULT_OFF + bool "Disable unprivileged BPF by default" + depends on BPF_SYSCALL + help + Disables unprivileged BPF by default by setting the corresponding + /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can + still reenable it by setting it to 0 later on, or permanently + disable it by setting it to 1 (from which no other transition to + 0 is possible anymore). + +source "kernel/bpf/preload/Kconfig" + +config BPF_LSM + bool "Enable BPF LSM Instrumentation" + depends on BPF_EVENTS + depends on BPF_SYSCALL + depends on SECURITY + depends on BPF_JIT + help + Enables instrumentation of the security hooks with BPF programs for + implementing dynamic MAC and Audit Policies. + + If you are unsure how to answer this question, answer N. + +endmenu # "BPF subsystem" diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 5efb2b24012c..da471bf01b97 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -107,10 +107,12 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; +#ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; +#endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 85716327c375..3925592d62e3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5206,6 +5206,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->ret_size = ret; for (i = 0; i < nargs; i++) { + if (i == nargs - 1 && args[i].type == 0) { + bpf_log(log, + "The function %s with variable args is unsupported.\n", + tname); + return -EINVAL; + } ret = __get_type_size(btf, args[i].type, &t); if (ret < 0) { bpf_log(log, @@ -5213,6 +5219,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); return -EINVAL; } + if (ret == 0) { + bpf_log(log, + "The function %s has malformed void argument.\n", + tname); + return -EINVAL; + } m->arg_size[i] = ret; } m->nr_args = nargs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 544773970dbc..73443498d88f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -692,38 +692,41 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. */ -#define MAX_PRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BUF_LEN 512 -struct bpf_printf_buf { - char tmp_buf[MAX_PRINTF_BUF_LEN]; +/* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 +struct bpf_bprintf_buffers { + char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; }; -static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf); -static DEFINE_PER_CPU(int, bpf_printf_buf_used); +static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); +static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_fmt_tmp_buf(char **tmp_buf) { - struct bpf_printf_buf *bufs; - int used; + struct bpf_bprintf_buffers *bufs; + int nest_level; preempt_disable(); - used = this_cpu_inc_return(bpf_printf_buf_used); - if (WARN_ON_ONCE(used > 1)) { - this_cpu_dec(bpf_printf_buf_used); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_printf_buf); - *tmp_buf = bufs->tmp_buf; + bufs = this_cpu_ptr(&bpf_bprintf_bufs); + *tmp_buf = bufs->tmp_bufs[nest_level - 1]; return 0; } void bpf_bprintf_cleanup(void) { - if (this_cpu_read(bpf_printf_buf_used)) { - this_cpu_dec(bpf_printf_buf_used); + if (this_cpu_read(bpf_bprintf_nest_level)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } } @@ -760,7 +763,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) return -EBUSY; - tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; *bin_args = (u32 *)tmp_buf; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index f25b719ac786..84b3b35fc0d0 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -221,25 +221,20 @@ static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb) -{ - size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT; - - /* consumer page + producer page + 2 x data pages */ - return RINGBUF_POS_PAGES + 2 * data_pages; -} - static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; - size_t mmap_sz; rb_map = container_of(map, struct bpf_ringbuf_map, map); - mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT; - - if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz) - return -EINVAL; + if (vma->vm_flags & VM_WRITE) { + /* allow writable mapping for the consumer_pos only */ + if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EPERM; + } else { + vma->vm_flags &= ~VM_MAYWRITE; + } + /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } @@ -315,6 +310,9 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); + if (len > rb->mask + 1) + return NULL; + cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d1cd80a6e67..73d15bc62d8c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9189eecb26dd..331b170d9fcc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6411,18 +6411,10 @@ enum { }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - const struct bpf_reg_state *off_reg, - u32 *alu_limit, u8 opcode) + u32 *alu_limit, bool mask_to_left) { - bool off_is_neg = off_reg->smin_value < 0; - bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || - (opcode == BPF_SUB && !off_is_neg); u32 max = 0, ptr_limit = 0; - if (!tnum_is_const(off_reg->var_off) && - (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) - return REASON_BOUNDS; - switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the @@ -6488,15 +6480,20 @@ static bool sanitize_needed(u8 opcode) return opcode == BPF_ADD || opcode == BPF_SUB; } +struct bpf_sanitize_info { + struct bpf_insn_aux_data aux; + bool mask_to_left; +}; + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - struct bpf_insn_aux_data *tmp_aux, + struct bpf_sanitize_info *info, const bool commit_window) { - struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux; + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; @@ -6517,7 +6514,16 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode); + if (!commit_window) { + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; + + info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + } + + err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; @@ -6525,8 +6531,8 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ - alu_state = tmp_aux->alu_state; - alu_limit = abs(tmp_aux->alu_limit - alu_limit); + alu_state = info->aux.alu_state; + alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; @@ -6541,8 +6547,12 @@ do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. + * + * Also, when register is a known constant, we rewrite register-based + * operation to immediate-based, and thus do not need masking (and as + * a consequence, do not need to simulate the zero-truncation either). */ - if (commit_window) + if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under @@ -6687,7 +6697,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - struct bpf_insn_aux_data tmp_aux = {}; + struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; @@ -6756,7 +6766,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, - &tmp_aux, false); + &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -6897,7 +6907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, - &tmp_aux, true); + &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } @@ -7086,11 +7096,10 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; - /* Assuming scalar64_min_max_and will be called so its safe - * to skip updating register for known 32-bit case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. @@ -7110,7 +7119,6 @@ static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } - } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, @@ -7157,11 +7165,10 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; - /* Assuming scalar64_min_max_or will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima @@ -7226,11 +7233,10 @@ static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; - /* Assuming scalar64_min_max_xor will be called so it is safe - * to skip updating register for known case. - */ - if (src_known && dst_known) + if (src_known && dst_known) { + __mark_reg32_known(dst_reg, var32_off.value); return; + } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; @@ -13215,6 +13221,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return 0; } +BTF_SET_START(btf_id_deny) +BTF_ID_UNUSED +#ifdef CONFIG_SMP +BTF_ID(func, migrate_disable) +BTF_ID(func, migrate_enable) +#endif +#if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU +BTF_ID(func, rcu_read_unlock_strict) +#endif +BTF_SET_END(btf_id_deny) + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -13282,6 +13299,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; + } else if (prog->type == BPF_PROG_TYPE_TRACING && + btf_id_set_contains(&btf_id_deny, btf_id)) { + return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); @@ -13381,12 +13401,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; - if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env->prog); - if (ret) - goto skip_full_check; - } - env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -13414,6 +13428,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (ret < 0) goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { + ret = bpf_prog_offload_verifier_prep(env->prog); + if (ret) + goto skip_full_check; + } + ret = check_cfg(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 391aa570369b..8190b6bfc978 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1001,7 +1001,7 @@ static int check_cgroupfs_options(struct fs_context *fc) ctx->subsys_mask &= enabled; /* - * In absense of 'none', 'name=' or subsystem name options, + * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e049edd66776..21ecc6ee6a6d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -468,7 +468,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, * @cgrp: the cgroup of interest * @ss: the subsystem of interest * - * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist + * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, @@ -1633,7 +1633,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) /** * css_clear_dir - remove subsys files in a cgroup directory - * @css: taget css + * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { @@ -5350,7 +5350,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -5634,8 +5634,6 @@ int __init cgroup_init_early(void) return 0; } -static u16 cgroup_disable_mask __initdata; - /** * cgroup_init - cgroup initialization * @@ -5694,12 +5692,8 @@ int __init cgroup_init(void) * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ - if (cgroup_disable_mask & (1 << ssid)) { - static_branch_disable(cgroup_subsys_enabled_key[ssid]); - printk(KERN_INFO "Disabling %s control group subsystem\n", - ss->name); + if (!cgroup_ssid_enabled(ssid)) continue; - } if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", @@ -6058,7 +6052,7 @@ out_revert: * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* - * cgroup_can_fork() succeded and cleans up references we took to + * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, @@ -6214,7 +6208,10 @@ static int __init cgroup_disable(char *str) if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; - cgroup_disable_mask |= 1 << i; + + static_branch_disable(cgroup_subsys_enabled_key[i]); + pr_info("Disabling %s control group subsystem\n", + ss->name); } } return 1; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a945504c0ae7..adb5190c4429 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3376,7 +3376,7 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) } /** - * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index ae042c347c64..3135406608c7 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -244,7 +244,7 @@ EXPORT_SYMBOL(rdmacg_uncharge); * This function follows charging resource in hierarchical way. * It will fail if the charge would cause the new value to exceed the * hierarchical limit. - * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. * Returns pointer to rdmacg for this resource when charging is successful. * * Charger needs to account resources on two criteria. diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 3a3fd2993a65..cee265cb535c 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -75,7 +75,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) * @root: root of the tree to traversal * @cpu: target cpu * - * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts + * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. diff --git a/kernel/events/core.c b/kernel/events/core.c index 2e947a485898..6fee4a7e88d7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6389,8 +6389,6 @@ void perf_event_wakeup(struct perf_event *event) static void perf_sigtrap(struct perf_event *event) { - struct kernel_siginfo info; - /* * We'd expect this to only occur if the irq_work is delayed and either * ctx->task or current has changed in the meantime. This can be the @@ -6405,13 +6403,8 @@ static void perf_sigtrap(struct perf_event *event) if (current->flags & PF_EXITING) return; - clear_siginfo(&info); - info.si_signo = SIGTRAP; - info.si_code = TRAP_PERF; - info.si_errno = event->attr.type; - info.si_perf = event->attr.sig_data; - info.si_addr = (void __user *)event->pending_addr; - force_sig_info(&info); + force_sig_perf((void __user *)event->pending_addr, + event->attr.type, event->attr.sig_data); } static void perf_pending_event_disable(struct perf_event *event) diff --git a/kernel/futex.c b/kernel/futex.c index c98b825da9cf..4938a00bc785 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3710,8 +3710,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, if (op & FUTEX_CLOCK_REALTIME) { flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \ - cmd != FUTEX_WAIT_REQUEUE_PI) + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) return -ENOSYS; } @@ -3758,42 +3757,52 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, return -ENOSYS; } +static __always_inline bool futex_cmd_has_timeout(u32 cmd) +{ + switch (cmd) { + case FUTEX_WAIT: + case FUTEX_LOCK_PI: + case FUTEX_WAIT_BITSET: + case FUTEX_WAIT_REQUEUE_PI: + return true; + } + return false; +} + +static __always_inline int +futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) +{ + if (!timespec64_valid(ts)) + return -EINVAL; + + *t = timespec64_to_ktime(*ts); + if (cmd == FUTEX_WAIT) + *t = ktime_add_safe(ktime_get(), *t); + else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) + *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); + return 0; +} SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { - struct timespec64 ts; + int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; - u32 val2 = 0; - int cmd = op & FUTEX_CMD_MASK; + struct timespec64 ts; - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET || - cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; - if (!timespec64_valid(&ts)) - return -EINVAL; - - t = timespec64_to_ktime(ts); - if (cmd == FUTEX_WAIT) - t = ktime_add_safe(ktime_get(), t); - else if (!(op & FUTEX_CLOCK_REALTIME)) - t = timens_ktime_to_host(CLOCK_MONOTONIC, t); + ret = futex_init_timeout(cmd, op, &ts, &t); + if (ret) + return ret; tp = &t; } - /* - * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*. - * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP. - */ - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) - val2 = (u32) (unsigned long) utime; - return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); + return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #ifdef CONFIG_COMPAT @@ -3959,31 +3968,20 @@ SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { - struct timespec64 ts; + int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; - int val2 = 0; - int cmd = op & FUTEX_CMD_MASK; + struct timespec64 ts; - if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET || - cmd == FUTEX_WAIT_REQUEUE_PI)) { + if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; - if (!timespec64_valid(&ts)) - return -EINVAL; - - t = timespec64_to_ktime(ts); - if (cmd == FUTEX_WAIT) - t = ktime_add_safe(ktime_get(), t); - else if (!(op & FUTEX_CLOCK_REALTIME)) - t = timens_ktime_to_host(CLOCK_MONOTONIC, t); + ret = futex_init_timeout(cmd, op, &ts, &t); + if (ret) + return ret; tp = &t; } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || - cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) - val2 = (int) (unsigned long) utime; - return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); + return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c index c1dd02f3be8b..e65de172ccf7 100644 --- a/kernel/kcsan/debugfs.c +++ b/kernel/kcsan/debugfs.c @@ -266,9 +266,10 @@ static const struct file_operations debugfs_ops = .release = single_release }; -static void __init kcsan_debugfs_init(void) +static int __init kcsan_debugfs_init(void) { debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops); + return 0; } late_initcall(kcsan_debugfs_init); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 48d736aa03b2..7641bd407239 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5736,7 +5736,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_acquired(lock, ip); + trace_lock_contended(lock, ip); if (unlikely(!lock_stat || !lockdep_enabled())) return; @@ -5754,7 +5754,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_contended(lock, ip); + trace_lock_acquired(lock, ip); if (unlikely(!lock_stat || !lockdep_enabled())) return; diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index a7276aaf2abc..db9301591e3f 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -57,7 +57,7 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, task->blocked_on = waiter; } -void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, +void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task) { DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); @@ -65,7 +65,7 @@ void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter); task->blocked_on = NULL; - list_del_init(&waiter->list); + INIT_LIST_HEAD(&waiter->list); waiter->task = NULL; } diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 1edd3f45a4ec..53e631e1d76d 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -22,7 +22,7 @@ extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); extern void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task); -extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, +extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task); extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index cb6b112ce155..013e1b08a1bf 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -194,7 +194,7 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait * Add @waiter to a given location in the lock wait_list and set the * FLAG_WAITERS flag if it's the first waiter. */ -static void __sched +static void __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct list_head *list) { @@ -205,6 +205,16 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); } +static void +__mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter) +{ + list_del(&waiter->list); + if (likely(list_empty(&lock->wait_list))) + __mutex_clear_flag(lock, MUTEX_FLAGS); + + debug_mutex_remove_waiter(lock, waiter, current); +} + /* * Give up ownership to a specific task, when @task = NULL, this is equivalent * to a regular unlock. Sets PICKUP on a handoff, clears HANDOFF, preserves @@ -1061,9 +1071,7 @@ acquired: __ww_mutex_check_waiters(lock, ww_ctx); } - mutex_remove_waiter(lock, &waiter, current); - if (likely(list_empty(&lock->wait_list))) - __mutex_clear_flag(lock, MUTEX_FLAGS); + __mutex_remove_waiter(lock, &waiter); debug_mutex_free_waiter(&waiter); @@ -1080,7 +1088,7 @@ skip_wait: err: __set_current_state(TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, current); + __mutex_remove_waiter(lock, &waiter); err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 1c2287d3fa71..f0c710b1d192 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -10,12 +10,10 @@ * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: */ -#define mutex_remove_waiter(lock, waiter, task) \ - __list_del((waiter)->list.prev, (waiter)->list.next) - #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) +#define debug_mutex_remove_waiter(lock, waiter, ti) do { } while (0) #define debug_mutex_unlock(lock) do { } while (0) #define debug_mutex_init(lock, name, key) do { } while (0) diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index b94f3831e963..ec36b73f4733 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -66,12 +66,12 @@ void queued_write_lock_slowpath(struct qrwlock *lock) arch_spin_lock(&lock->wait_lock); /* Try to acquire the lock directly if no reader is present */ - if (!atomic_read(&lock->cnts) && - (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0)) + if (!(cnts = atomic_read(&lock->cnts)) && + atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)) goto unlock; /* Set the waiting flag to notify readers that a writer is pending */ - atomic_add(_QW_WAITING, &lock->cnts); + atomic_or(_QW_WAITING, &lock->cnts); /* When no more readers or writers, set the locked flag */ do { diff --git a/kernel/module.c b/kernel/module.c index b5dd92e35b02..7e78dfabca97 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2401,6 +2401,15 @@ static long get_offset(struct module *mod, unsigned int *size, return ret; } +static bool module_init_layout_section(const char *sname) +{ +#ifndef CONFIG_MODULE_UNLOAD + if (module_exit_section(sname)) + return true; +#endif + return module_init_section(sname); +} + /* * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld * might -- code, read-only data, read-write data, small data. Tally @@ -2435,7 +2444,7 @@ static void layout_sections(struct module *mod, struct load_info *info) if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || module_init_section(sname)) + || module_init_layout_section(sname)) continue; s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); @@ -2468,7 +2477,7 @@ static void layout_sections(struct module *mod, struct load_info *info) if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || !module_init_section(sname)) + || !module_init_layout_section(sname)) continue; s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); @@ -2807,11 +2816,7 @@ void * __weak module_alloc(unsigned long size) bool __weak module_init_section(const char *name) { -#ifndef CONFIG_MODULE_UNLOAD - return strstarts(name, ".init") || module_exit_section(name); -#else return strstarts(name, ".init"); -#endif } bool __weak module_exit_section(const char *name) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 76f09456ec4b..2997ca600d18 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -170,6 +170,21 @@ void __ptrace_unlink(struct task_struct *child) spin_unlock(&child->sighand->siglock); } +static bool looks_like_a_spurious_pid(struct task_struct *task) +{ + if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) + return false; + + if (task_pid_vnr(task) == task->ptrace_message) + return false; + /* + * The tracee changed its pid but the PTRACE_EVENT_EXEC event + * was not wait()'ed, most probably debugger targets the old + * leader which was destroyed in de_thread(). + */ + return true; +} + /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { @@ -180,7 +195,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) return ret; spin_lock_irq(&task->sighand->siglock); - if (task_is_traced(task) && !__fatal_signal_pending(task)) { + if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && + !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } diff --git a/kernel/resource.c b/kernel/resource.c index 028a5ab18818..ca9f5198a01f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1805,7 +1805,7 @@ static struct resource *__request_free_mem_region(struct device *dev, REGION_DISJOINT) continue; - if (!__request_region_locked(res, &iomem_resource, addr, size, + if (__request_region_locked(res, &iomem_resource, addr, size, name, 0)) break; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9143163fa678..5226cc26a095 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -938,7 +938,7 @@ DEFINE_STATIC_KEY_FALSE(sched_uclamp_used); static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) { - return clamp_value / UCLAMP_BUCKET_DELTA; + return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); } static inline unsigned int uclamp_none(enum uclamp_id clamp_id) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1d75af1ecfb4..3248e24a90b0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6217,7 +6217,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool } if (has_idle_core) - set_idle_cores(this, false); + set_idle_cores(target, false); if (sched_feat(SIS_PROP) && !has_idle_core) { time = cpu_clock(this) - time; @@ -10878,16 +10878,22 @@ static void propagate_entity_cfs_rq(struct sched_entity *se) { struct cfs_rq *cfs_rq; + list_add_leaf_cfs_rq(cfs_rq_of(se)); + /* Start to propagate at parent */ se = se->parent; for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - if (cfs_rq_throttled(cfs_rq)) - break; + if (!cfs_rq_throttled(cfs_rq)){ + update_load_avg(cfs_rq, se, UPDATE_TG); + list_add_leaf_cfs_rq(cfs_rq); + continue; + } - update_load_avg(cfs_rq, se, UPDATE_TG); + if (list_add_leaf_cfs_rq(cfs_rq)) + break; } } #else diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index db27b69fa92a..cc25a3cff41f 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -972,7 +972,7 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - unsigned int task_flags = 0; + unsigned int task_flags; struct rq_flags rf; struct rq *rq; @@ -987,15 +987,31 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) rq = task_rq_lock(task, &rf); - if (task_on_rq_queued(task)) { - task_flags = TSK_RUNNING; - if (task_current(rq, task)) - task_flags |= TSK_ONCPU; - } else if (task->in_iowait) - task_flags = TSK_IOWAIT; - - if (task->in_memstall) - task_flags |= TSK_MEMSTALL; + /* + * We may race with schedule() dropping the rq lock between + * deactivating prev and switching to next. Because the psi + * updates from the deactivation are deferred to the switch + * callback to save cgroup tree updates, the task's scheduling + * state here is not coherent with its psi state: + * + * schedule() cgroup_move_task() + * rq_lock() + * deactivate_task() + * p->on_rq = 0 + * psi_dequeue() // defers TSK_RUNNING & TSK_IOWAIT updates + * pick_next_task() + * rq_unlock() + * rq_lock() + * psi_task_change() // old cgroup + * task->cgroups = to + * psi_task_change() // new cgroup + * rq_unlock() + * rq_lock() + * psi_sched_switch() // does deferred updates in new cgroup + * + * Don't rely on the scheduling state. Use psi_flags instead. + */ + task_flags = task->psi_flags; if (task_flags) psi_task_change(task, task_flags, 0); diff --git a/kernel/signal.c b/kernel/signal.c index 66e88649cf74..f7c6ffcbd044 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1236,6 +1236,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) case SIL_TIMER: case SIL_POLL: case SIL_FAULT: + case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: @@ -1804,6 +1805,21 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) } #endif +int force_sig_perf(void __user *addr, u32 type, u64 sig_data) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_PERF; + info.si_addr = addr; + info.si_perf_data = sig_data; + info.si_perf_type = type; + + return force_sig_info(&info); +} + /* For the crazy architectures that include trap information in * the errno field, instead of an actual errno value. */ @@ -2564,6 +2580,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig) { switch (siginfo_layout(ksig->sig, ksig->info.si_code)) { case SIL_FAULT: + case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: @@ -3251,6 +3268,10 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code) #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) layout = SIL_PERF_EVENT; +#ifdef __ARCH_SI_TRAPNO + else if (layout == SIL_FAULT) + layout = SIL_FAULT_TRAPNO; +#endif } else if (si_code <= NSIGPOLL) layout = SIL_POLL; @@ -3354,35 +3375,28 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, break; case SIL_FAULT: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO + break; + case SIL_FAULT_TRAPNO: + to->si_addr = ptr_to_compat(from->si_addr); to->si_trapno = from->si_trapno; -#endif break; case SIL_FAULT_MCEERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_lower = ptr_to_compat(from->si_lower); to->si_upper = ptr_to_compat(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = ptr_to_compat(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_pkey = from->si_pkey; break; case SIL_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -3438,35 +3452,28 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, break; case SIL_FAULT: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO + break; + case SIL_FAULT_TRAPNO: + to->si_addr = compat_ptr(from->si_addr); to->si_trapno = from->si_trapno; -#endif break; case SIL_FAULT_MCEERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_lower = compat_ptr(from->si_lower); to->si_upper = compat_ptr(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = compat_ptr(from->si_addr); -#ifdef __ARCH_SI_TRAPNO - to->si_trapno = from->si_trapno; -#endif to->si_pkey = from->si_pkey; break; case SIL_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -4644,11 +4651,13 @@ static inline void siginfo_buildtime_checks(void) /* sigfault */ CHECK_OFFSET(si_addr); + CHECK_OFFSET(si_trapno); CHECK_OFFSET(si_addr_lsb); CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); - CHECK_OFFSET(si_perf); + CHECK_OFFSET(si_perf_data); + CHECK_OFFSET(si_perf_type); /* sigpoll */ CHECK_OFFSET(si_band); diff --git a/kernel/smp.c b/kernel/smp.c index e21074900006..52bf159ec400 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -211,7 +211,7 @@ static u64 cfd_seq_inc(unsigned int src, unsigned int dst, unsigned int type) } while (0) /* Record current CSD work for current CPU, NULL to erase. */ -static void __csd_lock_record(call_single_data_t *csd) +static void __csd_lock_record(struct __call_single_data *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ @@ -226,13 +226,13 @@ static void __csd_lock_record(call_single_data_t *csd) /* Or before unlock, as the case may be. */ } -static __always_inline void csd_lock_record(call_single_data_t *csd) +static __always_inline void csd_lock_record(struct __call_single_data *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } -static int csd_lock_wait_getcpu(call_single_data_t *csd) +static int csd_lock_wait_getcpu(struct __call_single_data *csd) { unsigned int csd_type; @@ -282,7 +282,7 @@ static const char *csd_lock_get_type(unsigned int type) return (type >= ARRAY_SIZE(seq_type)) ? "?" : seq_type[type]; } -static void csd_lock_print_extended(call_single_data_t *csd, int cpu) +static void csd_lock_print_extended(struct __call_single_data *csd, int cpu) { struct cfd_seq_local *seq = &per_cpu(cfd_seq_local, cpu); unsigned int srccpu = csd->node.src; @@ -321,7 +321,7 @@ static void csd_lock_print_extended(call_single_data_t *csd, int cpu) * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ -static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) +static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; @@ -387,7 +387,7 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void __csd_lock_wait(call_single_data_t *csd) +static void __csd_lock_wait(struct __call_single_data *csd) { int bug_id = 0; u64 ts0, ts1; @@ -401,7 +401,7 @@ static void __csd_lock_wait(call_single_data_t *csd) smp_acquire__after_ctrl_dep(); } -static __always_inline void csd_lock_wait(call_single_data_t *csd) +static __always_inline void csd_lock_wait(struct __call_single_data *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); @@ -431,17 +431,17 @@ static void __smp_call_single_queue_debug(int cpu, struct llist_node *node) #else #define cfd_seq_store(var, src, dst, type) -static void csd_lock_record(call_single_data_t *csd) +static void csd_lock_record(struct __call_single_data *csd) { } -static __always_inline void csd_lock_wait(call_single_data_t *csd) +static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif -static __always_inline void csd_lock(call_single_data_t *csd) +static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; @@ -454,7 +454,7 @@ static __always_inline void csd_lock(call_single_data_t *csd) smp_wmb(); } -static __always_inline void csd_unlock(call_single_data_t *csd) +static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); @@ -501,7 +501,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ -static int generic_exec_single(int cpu, call_single_data_t *csd) +static int generic_exec_single(int cpu, struct __call_single_data *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; @@ -784,7 +784,7 @@ EXPORT_SYMBOL(smp_call_function_single); * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 14edf84cc571..d4a78e08f6d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,7 +225,27 @@ static int bpf_stats_handler(struct ctl_table *table, int write, mutex_unlock(&bpf_stats_enabled_mutex); return ret; } -#endif + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + return ret; +} +#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ /* * /proc/sys support @@ -2600,10 +2620,9 @@ static struct ctl_table kern_table[] = { .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_ONE, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, }, { .procname = "bpf_stats_enabled", diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index bea9d08b1698..5897828b9d7e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -92,7 +92,7 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (rtcdev) return -EBUSY; - if (!rtc->ops->set_alarm) + if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -1; if (!device_may_wakeup(rtc->dev.parent)) return -1; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 560e4c8d3825..a21ef9cd2aae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3704,6 +3704,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, goto print; while (*p) { + bool star = false; + int len = 0; + j = 0; /* We only care about %s and variants */ @@ -3725,13 +3728,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, /* Need to test cases like %08.*s */ for (j = 1; p[i+j]; j++) { if (isdigit(p[i+j]) || - p[i+j] == '*' || p[i+j] == '.') continue; + if (p[i+j] == '*') { + star = true; + continue; + } break; } if (p[i+j] == 's') break; + star = false; } j = 0; } @@ -3744,6 +3751,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, iter->fmt[i] = '\0'; trace_seq_vprintf(&iter->seq, iter->fmt, ap); + if (star) + len = va_arg(ap, int); + /* The ap now points to the string data of the %s */ str = va_arg(ap, const char *); @@ -3762,8 +3772,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, int ret; /* Try to safely read the string */ - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); + if (star) { + if (len + 1 > iter->fmt_size) + len = iter->fmt_size - 1; + if (len < 0) + len = 0; + ret = copy_from_kernel_nofault(iter->fmt, str, len); + iter->fmt[len] = 0; + star = false; + } else { + ret = strncpy_from_kernel_nofault(iter->fmt, str, + iter->fmt_size); + } if (ret < 0) trace_seq_printf(&iter->seq, "(0x%px)", str); else @@ -3775,7 +3795,10 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, strncpy(iter->fmt, p + i, j + 1); iter->fmt[j+1] = '\0'; } - trace_seq_printf(&iter->seq, iter->fmt, str); + if (star) + trace_seq_printf(&iter->seq, iter->fmt, len, str); + else + trace_seq_printf(&iter->seq, iter->fmt, str); p += i + j + 1; } diff --git a/kernel/up.c b/kernel/up.c index df50828cc2f0..a38b8b095251 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -25,7 +25,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, } EXPORT_SYMBOL(smp_call_function_single); -int smp_call_function_single_async(int cpu, call_single_data_t *csd) +int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { unsigned long flags; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 7c397907d0e9..92d3bcc5a5e0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -302,10 +302,10 @@ void touch_softlockup_watchdog_sync(void) __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } -static int is_softlockup(unsigned long touch_ts, unsigned long period_ts) +static int is_softlockup(unsigned long touch_ts, + unsigned long period_ts, + unsigned long now) { - unsigned long now = get_timestamp(); - if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) @@ -353,8 +353,7 @@ static int softlockup_fn(void *data) /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { - unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); - unsigned long period_ts = __this_cpu_read(watchdog_report_ts); + unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; @@ -377,11 +376,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); /* + * Read the current timestamp first. It might become invalid anytime + * when a virtual machine is stopped by the host or when the watchog + * is touched from NMI. + */ + now = get_timestamp(); + /* * If a virtual machine is stopped by the host it can look to - * the watchdog like a soft lockup. Check to see if the host - * stopped the vm before we process the timestamps. + * the watchdog like a soft lockup. This function touches the watchdog. */ kvm_check_and_clear_guest_paused(); + /* + * The stored timestamp is comparable with @now only when not touched. + * It might get touched anytime from NMI. Make sure that is_softlockup() + * uses the same (valid) value. + */ + period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { @@ -398,13 +408,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } - /* check for a softlockup - * This is done by making sure a high priority task is - * being scheduled. The task touches the watchdog to - * indicate it is getting cpu time. If it hasn't then - * this is a good indication some task is hogging the cpu - */ - duration = is_softlockup(touch_ts, period_ts); + /* Check for a softlockup. */ + touch_ts = __this_cpu_read(watchdog_touch_ts); + duration = is_softlockup(touch_ts, period_ts, now); if (unlikely(duration)) { /* * Prevent multiple soft-lockup reports if one cpu is already diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b19d759e55a5..50142fc08902 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -50,6 +50,7 @@ #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> +#include <linux/kvm_para.h> #include "workqueue_internal.h" @@ -5772,6 +5773,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; + unsigned long now = jiffies; struct worker_pool *pool; int pi; @@ -5786,6 +5788,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) if (list_empty(&pool->worklist)) continue; + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a stall. + */ + kvm_check_and_clear_guest_paused(); + /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); @@ -5799,12 +5807,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) ts = touched; /* did we stall? */ - if (time_after(jiffies, ts + thresh)) { + if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", - jiffies_to_msecs(jiffies - pool_ts) / 1000); + jiffies_to_msecs(now - pool_ts) / 1000); } } |