diff options
Diffstat (limited to 'kernel')
59 files changed, 5717 insertions, 1269 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f85ae5dfa474..9b9241361311 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -112,7 +112,8 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o -obj-$(CONFIG_HAS_IOMEM) += memremap.o +obj-$(CONFIG_HAS_IOMEM) += iomem.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/audit.c b/kernel/audit.c index 670665c6e2a6..e7478cb58079 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1099,8 +1099,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature if (audit_enabled == AUDIT_OFF) return; - - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab, current); @@ -2317,8 +2316,7 @@ void audit_log_link_denied(const char *operation) return; /* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */ - ab = audit_log_start(current->audit_context, GFP_KERNEL, - AUDIT_ANOM_LINK); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_LINK); if (!ab) return; audit_log_format(ab, "op=%s", operation); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 9eb8b3511636..f1ba88994508 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -274,7 +274,7 @@ static void audit_update_watch(struct audit_parent *parent, /* If the update involves invalidating rules, do the inode-based * filtering now, so we don't omit records. */ if (invalidating && !audit_dummy_context()) - audit_filter_inodes(current, current->audit_context); + audit_filter_inodes(current, audit_context()); /* updating ino will likely change which audit_hash_list we * are on so we need a new watch for the new list */ diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index d7a807e81451..eaa320148d97 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -426,7 +426,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) return -EINVAL; break; case AUDIT_EXE: - if (f->op != Audit_equal) + if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; if (entry->rule.listnr != AUDIT_FILTER_EXIT) return -EINVAL; @@ -1089,8 +1089,6 @@ static void audit_list_rules(int seq, struct sk_buff_head *q) static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; - uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); - unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) return; @@ -1098,7 +1096,7 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; - audit_log_format(ab, "auid=%u ses=%u" ,loginuid, sessionid); + audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4e0a4ac803db..ceb1c4596c51 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -374,7 +374,7 @@ static int audit_field_compare(struct task_struct *tsk, case AUDIT_COMPARE_EGID_TO_OBJ_GID: return audit_compare_gid(cred->egid, name, f, ctx); case AUDIT_COMPARE_AUID_TO_OBJ_UID: - return audit_compare_uid(tsk->loginuid, name, f, ctx); + return audit_compare_uid(audit_get_loginuid(tsk), name, f, ctx); case AUDIT_COMPARE_SUID_TO_OBJ_UID: return audit_compare_uid(cred->suid, name, f, ctx); case AUDIT_COMPARE_SGID_TO_OBJ_GID: @@ -385,7 +385,8 @@ static int audit_field_compare(struct task_struct *tsk, return audit_compare_gid(cred->fsgid, name, f, ctx); /* uid comparisons */ case AUDIT_COMPARE_UID_TO_AUID: - return audit_uid_comparator(cred->uid, f->op, tsk->loginuid); + return audit_uid_comparator(cred->uid, f->op, + audit_get_loginuid(tsk)); case AUDIT_COMPARE_UID_TO_EUID: return audit_uid_comparator(cred->uid, f->op, cred->euid); case AUDIT_COMPARE_UID_TO_SUID: @@ -394,11 +395,14 @@ static int audit_field_compare(struct task_struct *tsk, return audit_uid_comparator(cred->uid, f->op, cred->fsuid); /* auid comparisons */ case AUDIT_COMPARE_AUID_TO_EUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->euid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->euid); case AUDIT_COMPARE_AUID_TO_SUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->suid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->suid); case AUDIT_COMPARE_AUID_TO_FSUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->fsuid); /* euid comparisons */ case AUDIT_COMPARE_EUID_TO_SUID: return audit_uid_comparator(cred->euid, f->op, cred->suid); @@ -471,6 +475,8 @@ static int audit_filter_rules(struct task_struct *tsk, break; case AUDIT_EXE: result = audit_exe_compare(tsk, rule->exe); + if (f->op == Audit_not_equal) + result = !result; break; case AUDIT_UID: result = audit_uid_comparator(cred->uid, f->op, f->uid); @@ -511,7 +517,7 @@ static int audit_filter_rules(struct task_struct *tsk, result = audit_gid_comparator(cred->fsgid, f->op, f->gid); break; case AUDIT_SESSIONID: - sessionid = audit_get_sessionid(current); + sessionid = audit_get_sessionid(tsk); result = audit_comparator(sessionid, f->op, f->val); break; case AUDIT_PERS: @@ -609,7 +615,8 @@ static int audit_filter_rules(struct task_struct *tsk, result = match_tree_refs(ctx, rule->tree); break; case AUDIT_LOGINUID: - result = audit_uid_comparator(tsk->loginuid, f->op, f->uid); + result = audit_uid_comparator(audit_get_loginuid(tsk), + f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); @@ -863,7 +870,7 @@ static inline struct audit_context *audit_take_context(struct task_struct *tsk, audit_filter_inodes(tsk, context); } - tsk->audit_context = NULL; + audit_set_context(tsk, NULL); return context; } @@ -950,7 +957,7 @@ int audit_alloc(struct task_struct *tsk) } context->filterkey = key; - tsk->audit_context = context; + audit_set_context(tsk, context); set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); return 0; } @@ -1507,8 +1514,7 @@ void __audit_free(struct task_struct *tsk) void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4) { - struct task_struct *tsk = current; - struct audit_context *context = tsk->audit_context; + struct audit_context *context = audit_context(); enum audit_state state; if (!audit_enabled || !context) @@ -1523,7 +1529,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, context->dummy = !audit_n_rules; if (!context->dummy && state == AUDIT_BUILD_CONTEXT) { context->prio = 0; - if (auditd_test_task(tsk)) + if (auditd_test_task(current)) return; } @@ -1553,7 +1559,6 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, */ void __audit_syscall_exit(int success, long return_code) { - struct task_struct *tsk = current; struct audit_context *context; if (success) @@ -1561,12 +1566,12 @@ void __audit_syscall_exit(int success, long return_code) else success = AUDITSC_FAILURE; - context = audit_take_context(tsk, success, return_code); + context = audit_take_context(current, success, return_code); if (!context) return; if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) - audit_log_exit(context, tsk); + audit_log_exit(context, current); context->in_syscall = 0; context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; @@ -1588,7 +1593,7 @@ void __audit_syscall_exit(int success, long return_code) kfree(context->filterkey); context->filterkey = NULL; } - tsk->audit_context = context; + audit_set_context(current, context); } static inline void handle_one(const struct inode *inode) @@ -1600,7 +1605,7 @@ static inline void handle_one(const struct inode *inode) int count; if (likely(!inode->i_fsnotify_marks)) return; - context = current->audit_context; + context = audit_context(); p = context->trees; count = context->tree_count; rcu_read_lock(); @@ -1631,7 +1636,7 @@ static void handle_path(const struct dentry *dentry) unsigned long seq; int count; - context = current->audit_context; + context = audit_context(); p = context->trees; count = context->tree_count; retry: @@ -1713,7 +1718,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context, struct filename * __audit_reusename(const __user char *uptr) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct audit_names *n; list_for_each_entry(n, &context->names_list, list) { @@ -1736,7 +1741,7 @@ __audit_reusename(const __user char *uptr) */ void __audit_getname(struct filename *name) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct audit_names *n; if (!context->in_syscall) @@ -1764,7 +1769,7 @@ void __audit_getname(struct filename *name) void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct inode *inode = d_backing_inode(dentry); struct audit_names *n; bool parent = flags & AUDIT_INODE_PARENT; @@ -1863,7 +1868,7 @@ void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct inode *inode = d_backing_inode(dentry); const char *dname = dentry->d_name.name; struct audit_names *n, *found_parent = NULL, *found_child = NULL; @@ -2048,7 +2053,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, int audit_set_loginuid(kuid_t loginuid) { struct task_struct *task = current; - unsigned int oldsessionid, sessionid = (unsigned int)-1; + unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; @@ -2062,7 +2067,7 @@ int audit_set_loginuid(kuid_t loginuid) /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); - if (unlikely(sessionid == (unsigned int)-1)) + if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } @@ -2082,7 +2087,7 @@ out: */ void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (attr) memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr)); @@ -2106,7 +2111,7 @@ void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct timespec64 *p = &context->mq_sendrecv.abs_timeout; if (abs_timeout) @@ -2130,7 +2135,7 @@ void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (notification) context->mq_notify.sigev_signo = notification->sigev_signo; @@ -2149,7 +2154,7 @@ void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) */ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->mq_getsetattr.mqdes = mqdes; context->mq_getsetattr.mqstat = *mqstat; context->type = AUDIT_MQ_GETSETATTR; @@ -2162,7 +2167,7 @@ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) */ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->ipc.uid = ipcp->uid; context->ipc.gid = ipcp->gid; context->ipc.mode = ipcp->mode; @@ -2182,7 +2187,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) */ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->ipc.qbytes = qbytes; context->ipc.perm_uid = uid; @@ -2193,7 +2198,7 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo void __audit_bprm(struct linux_binprm *bprm) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->type = AUDIT_EXECVE; context->execve.argc = bprm->argc; @@ -2208,7 +2213,7 @@ void __audit_bprm(struct linux_binprm *bprm) */ int __audit_socketcall(int nargs, unsigned long *args) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (nargs <= 0 || nargs > AUDITSC_ARGS || !args) return -EINVAL; @@ -2226,7 +2231,7 @@ int __audit_socketcall(int nargs, unsigned long *args) */ void __audit_fd_pair(int fd1, int fd2) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->fds[0] = fd1; context->fds[1] = fd2; } @@ -2240,7 +2245,7 @@ void __audit_fd_pair(int fd1, int fd2) */ int __audit_sockaddr(int len, void *a) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (!context->sockaddr) { void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); @@ -2256,7 +2261,7 @@ int __audit_sockaddr(int len, void *a) void __audit_ptrace(struct task_struct *t) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->target_pid = task_tgid_nr(t); context->target_auid = audit_get_loginuid(t); @@ -2277,19 +2282,19 @@ void __audit_ptrace(struct task_struct *t) int audit_signal_info(int sig, struct task_struct *t) { struct audit_aux_data_pids *axp; - struct task_struct *tsk = current; - struct audit_context *ctx = tsk->audit_context; - kuid_t uid = current_uid(), t_uid = task_uid(t); + struct audit_context *ctx = audit_context(); + kuid_t uid = current_uid(), auid, t_uid = task_uid(t); if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { - audit_sig_pid = task_tgid_nr(tsk); - if (uid_valid(tsk->loginuid)) - audit_sig_uid = tsk->loginuid; + audit_sig_pid = task_tgid_nr(current); + auid = audit_get_loginuid(current); + if (uid_valid(auid)) + audit_sig_uid = auid; else audit_sig_uid = uid; - security_task_getsecid(tsk, &audit_sig_sid); + security_task_getsecid(current, &audit_sig_sid); } if (!audit_signals || audit_dummy_context()) @@ -2345,7 +2350,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { struct audit_aux_data_bprm_fcaps *ax; - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct cpu_vfs_cap_data vcaps; ax = kmalloc(sizeof(*ax), GFP_KERNEL); @@ -2385,7 +2390,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, */ void __audit_log_capset(const struct cred *new, const struct cred *old) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; context->capset.cap.inheritable = new->cap_effective; @@ -2396,7 +2401,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) void __audit_mmap_fd(int fd, int flags) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->mmap.fd = fd; context->mmap.flags = flags; context->type = AUDIT_MMAP; @@ -2404,7 +2409,7 @@ void __audit_mmap_fd(int fd, int flags) void __audit_log_kern_module(char *name) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL); strcpy(context->module.name, name); @@ -2413,7 +2418,7 @@ void __audit_log_kern_module(char *name) void __audit_fanotify(unsigned int response) { - audit_log(current->audit_context, GFP_KERNEL, + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, "resp=%u", response); } @@ -2464,7 +2469,19 @@ void audit_core_dumps(long signr) audit_log_end(ab); } -void __audit_seccomp(unsigned long syscall, long signr, int code) +/** + * audit_seccomp - record information about a seccomp action + * @syscall: syscall number + * @signr: signal value + * @code: the seccomp action + * + * Record the information associated with a seccomp action. Event filtering for + * seccomp actions that are not to be logged is done in seccomp_log(). + * Therefore, this function forces auditing independent of the audit_enabled + * and dummy context state because seccomp actions should be logged even when + * audit is not in use. + */ +void audit_seccomp(unsigned long syscall, long signr, int code) { struct audit_buffer *ab; @@ -2478,9 +2495,29 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) audit_log_end(ab); } +void audit_seccomp_actions_logged(const char *names, const char *old_names, + int res) +{ + struct audit_buffer *ab; + + if (!audit_enabled) + return; + + ab = audit_log_start(audit_context(), GFP_KERNEL, + AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; + + audit_log_format(ab, "op=seccomp-logging"); + audit_log_format(ab, " actions=%s", names); + audit_log_format(ab, " old-actions=%s", old_names); + audit_log_format(ab, " res=%d", res); + audit_log_end(ab); +} + struct list_head *audit_killed_trees(void) { - struct audit_context *ctx = current->audit_context; + struct audit_context *ctx = audit_context(); if (likely(!ctx || !ctx->in_syscall)) return NULL; return &ctx->killed_trees; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index a713fd23ec88..f27f5496d6fe 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,9 +4,13 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +ifeq ($(CONFIG_XDP_SOCKETS),y) +obj-$(CONFIG_BPF_SYSCALL) += xskmap.o +endif obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) ifeq ($(CONFIG_INET),y) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 027107f4be53..544e58f5f642 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,11 +11,13 @@ * General Public License for more details. */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> #include <linux/perf_event.h> +#include <uapi/linux/btf.h> #include "map_in_map.h" @@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map) bpf_map_area_free(array); } +static void array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + + rcu_read_lock(); + + value = array_map_lookup_elem(map, key); + if (!value) { + rcu_read_unlock(); + return; + } + + seq_printf(m, "%u: ", *(u32 *)key); + btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); + seq_puts(m, "\n"); + + rcu_read_unlock(); +} + +static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) +{ + const struct btf_type *key_type, *value_type; + u32 key_size, value_size; + u32 int_data; + + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + /* bpf array can only take a u32 key. This check makes + * sure that the btf matches the attr used during map_create. + */ + if (BTF_INT_BITS(int_data) != 32 || key_size != 4 || + BTF_INT_OFFSET(int_data)) + return -EINVAL; + + value_type = btf_type_id_size(btf, &btf_value_id, &value_size); + if (!value_type || value_size > map->value_size) + return -EINVAL; + + return 0; +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_seq_show_elem = array_map_seq_show_elem, + .map_check_btf = array_map_check_btf, }; const struct bpf_map_ops percpu_array_map_ops = { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c new file mode 100644 index 000000000000..8653ab004c73 --- /dev/null +++ b/kernel/bpf/btf.c @@ -0,0 +1,2348 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <uapi/linux/btf.h> +#include <uapi/linux/types.h> +#include <linux/seq_file.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/anon_inodes.h> +#include <linux/file.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/sort.h> +#include <linux/bpf_verifier.h> +#include <linux/btf.h> + +/* BTF (BPF Type Format) is the meta data format which describes + * the data types of BPF program/map. Hence, it basically focus + * on the C programming language which the modern BPF is primary + * using. + * + * ELF Section: + * ~~~~~~~~~~~ + * The BTF data is stored under the ".BTF" ELF section + * + * struct btf_type: + * ~~~~~~~~~~~~~~~ + * Each 'struct btf_type' object describes a C data type. + * Depending on the type it is describing, a 'struct btf_type' + * object may be followed by more data. F.e. + * To describe an array, 'struct btf_type' is followed by + * 'struct btf_array'. + * + * 'struct btf_type' and any extra data following it are + * 4 bytes aligned. + * + * Type section: + * ~~~~~~~~~~~~~ + * The BTF type section contains a list of 'struct btf_type' objects. + * Each one describes a C type. Recall from the above section + * that a 'struct btf_type' object could be immediately followed by extra + * data in order to desribe some particular C types. + * + * type_id: + * ~~~~~~~ + * Each btf_type object is identified by a type_id. The type_id + * is implicitly implied by the location of the btf_type object in + * the BTF type section. The first one has type_id 1. The second + * one has type_id 2...etc. Hence, an earlier btf_type has + * a smaller type_id. + * + * A btf_type object may refer to another btf_type object by using + * type_id (i.e. the "type" in the "struct btf_type"). + * + * NOTE that we cannot assume any reference-order. + * A btf_type object can refer to an earlier btf_type object + * but it can also refer to a later btf_type object. + * + * For example, to describe "const void *". A btf_type + * object describing "const" may refer to another btf_type + * object describing "void *". This type-reference is done + * by specifying type_id: + * + * [1] CONST (anon) type_id=2 + * [2] PTR (anon) type_id=0 + * + * The above is the btf_verifier debug log: + * - Each line started with "[?]" is a btf_type object + * - [?] is the type_id of the btf_type object. + * - CONST/PTR is the BTF_KIND_XXX + * - "(anon)" is the name of the type. It just + * happens that CONST and PTR has no name. + * - type_id=XXX is the 'u32 type' in btf_type + * + * NOTE: "void" has type_id 0 + * + * String section: + * ~~~~~~~~~~~~~~ + * The BTF string section contains the names used by the type section. + * Each string is referred by an "offset" from the beginning of the + * string section. + * + * Each string is '\0' terminated. + * + * The first character in the string section must be '\0' + * which is used to mean 'anonymous'. Some btf_type may not + * have a name. + */ + +/* BTF verification: + * + * To verify BTF data, two passes are needed. + * + * Pass #1 + * ~~~~~~~ + * The first pass is to collect all btf_type objects to + * an array: "btf->types". + * + * Depending on the C type that a btf_type is describing, + * a btf_type may be followed by extra data. We don't know + * how many btf_type is there, and more importantly we don't + * know where each btf_type is located in the type section. + * + * Without knowing the location of each type_id, most verifications + * cannot be done. e.g. an earlier btf_type may refer to a later + * btf_type (recall the "const void *" above), so we cannot + * check this type-reference in the first pass. + * + * In the first pass, it still does some verifications (e.g. + * checking the name is a valid offset to the string section). + * + * Pass #2 + * ~~~~~~~ + * The main focus is to resolve a btf_type that is referring + * to another type. + * + * We have to ensure the referring type: + * 1) does exist in the BTF (i.e. in btf->types[]) + * 2) does not cause a loop: + * struct A { + * struct B b; + * }; + * + * struct B { + * struct A a; + * }; + * + * btf_type_needs_resolve() decides if a btf_type needs + * to be resolved. + * + * The needs_resolve type implements the "resolve()" ops which + * essentially does a DFS and detects backedge. + * + * During resolve (or DFS), different C types have different + * "RESOLVED" conditions. + * + * When resolving a BTF_KIND_STRUCT, we need to resolve all its + * members because a member is always referring to another + * type. A struct's member can be treated as "RESOLVED" if + * it is referring to a BTF_KIND_PTR. Otherwise, the + * following valid C struct would be rejected: + * + * struct A { + * int m; + * struct A *a; + * }; + * + * When resolving a BTF_KIND_PTR, it needs to keep resolving if + * it is referring to another BTF_KIND_PTR. Otherwise, we cannot + * detect a pointer loop, e.g.: + * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR + + * ^ | + * +-----------------------------------------+ + * + */ + +#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE) +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +#define BTF_INFO_MASK 0x0f00ffff +#define BTF_INT_MASK 0x0fffffff +#define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) +#define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) + +/* 16MB for 64k structs and each has 16 members and + * a few MB spaces for the string section. + * The hard limit is S32_MAX. + */ +#define BTF_MAX_SIZE (16 * 1024 * 1024) + +#define for_each_member(i, struct_type, member) \ + for (i = 0, member = btf_type_member(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +#define for_each_member_from(i, from, struct_type, member) \ + for (i = from, member = btf_type_member(struct_type) + from; \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +static DEFINE_IDR(btf_idr); +static DEFINE_SPINLOCK(btf_idr_lock); + +struct btf { + void *data; + struct btf_type **types; + u32 *resolved_ids; + u32 *resolved_sizes; + const char *strings; + void *nohdr_data; + struct btf_header hdr; + u32 nr_types; + u32 types_size; + u32 data_size; + refcount_t refcnt; + u32 id; + struct rcu_head rcu; +}; + +enum verifier_phase { + CHECK_META, + CHECK_TYPE, +}; + +struct resolve_vertex { + const struct btf_type *t; + u32 type_id; + u16 next_member; +}; + +enum visit_state { + NOT_VISITED, + VISITED, + RESOLVED, +}; + +enum resolve_mode { + RESOLVE_TBD, /* To Be Determined */ + RESOLVE_PTR, /* Resolving for Pointer */ + RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union + * or array + */ +}; + +#define MAX_RESOLVE_DEPTH 32 + +struct btf_sec_info { + u32 off; + u32 len; +}; + +struct btf_verifier_env { + struct btf *btf; + u8 *visit_states; + struct resolve_vertex stack[MAX_RESOLVE_DEPTH]; + struct bpf_verifier_log log; + u32 log_type_id; + u32 top_stack; + enum verifier_phase phase; + enum resolve_mode resolve_mode; +}; + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", +}; + +struct btf_kind_operations { + s32 (*check_meta)(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left); + int (*resolve)(struct btf_verifier_env *env, + const struct resolve_vertex *v); + int (*check_member)(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type); + void (*log_details)(struct btf_verifier_env *env, + const struct btf_type *t); + void (*seq_show)(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m); +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; +static struct btf_type btf_void; + +static bool btf_type_is_modifier(const struct btf_type *t) +{ + /* Some of them is not strictly a C modifier + * but they are grouped into the same bucket + * for BTF concern: + * A type (t) that refers to another + * type through t->type AND its size cannot + * be determined without following the t->type. + * + * ptr does not fall into this bucket + * because its size is always sizeof(void *). + */ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return true; + } + + return false; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + /* void => no type and size info. + * Hence, FWD is also treated as void. + */ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +/* union is only a special case of struct: + * all its offsetof(member) == 0 + */ +static bool btf_type_is_struct(const struct btf_type *t) +{ + u8 kind = BTF_INFO_KIND(t->info); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + +static bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +/* What types need to be resolved? + * + * btf_type_is_modifier() is an obvious one. + * + * btf_type_is_struct() because its member refers to + * another type (through member->type). + + * btf_type_is_array() because its element (array->type) + * refers to another type. Array can be thought of a + * special case of struct while array just has the same + * member-type repeated by array->nelems of times. + */ +static bool btf_type_needs_resolve(const struct btf_type *t) +{ + return btf_type_is_modifier(t) || + btf_type_is_ptr(t) || + btf_type_is_struct(t) || + btf_type_is_array(t); +} + +/* t->size can be used */ +static bool btf_type_has_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return true; + } + + return false; +} + +static const char *btf_int_encoding_str(u8 encoding) +{ + if (encoding == 0) + return "(none)"; + else if (encoding == BTF_INT_SIGNED) + return "SIGNED"; + else if (encoding == BTF_INT_CHAR) + return "CHAR"; + else if (encoding == BTF_INT_BOOL) + return "BOOL"; + else + return "UNKN"; +} + +static u16 btf_type_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static u32 btf_type_int(const struct btf_type *t) +{ + return *(u32 *)(t + 1); +} + +static const struct btf_array *btf_type_array(const struct btf_type *t) +{ + return (const struct btf_array *)(t + 1); +} + +static const struct btf_member *btf_type_member(const struct btf_type *t) +{ + return (const struct btf_member *)(t + 1); +} + +static const struct btf_enum *btf_type_enum(const struct btf_type *t) +{ + return (const struct btf_enum *)(t + 1); +} + +static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) +{ + return kind_ops[BTF_INFO_KIND(t->info)]; +} + +static bool btf_name_offset_valid(const struct btf *btf, u32 offset) +{ + return BTF_STR_OFFSET_VALID(offset) && + offset < btf->hdr.str_len; +} + +static const char *btf_name_by_offset(const struct btf *btf, u32 offset) +{ + if (!offset) + return "(anon)"; + else if (offset < btf->hdr.str_len) + return &btf->strings[offset]; + else + return "(invalid-name-offset)"; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +/* + * Regular int is not a bit field and it must be either + * u8/u16/u32/u64. + */ +static bool btf_type_int_is_regular(const struct btf_type *t) +{ + u16 nr_bits, nr_bytes; + u32 int_data; + + int_data = btf_type_int(t); + nr_bits = BTF_INT_BITS(int_data); + nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); + if (BITS_PER_BYTE_MASKED(nr_bits) || + BTF_INT_OFFSET(int_data) || + (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && + nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) { + return false; + } + + return true; +} + +__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, + const struct btf_type *t, + bool log_details, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + u8 kind = BTF_INFO_KIND(t->info); + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + __btf_verifier_log(log, "[%u] %s %s%s", + env->log_type_id, + btf_kind_str[kind], + btf_name_by_offset(btf, t->name_off), + log_details ? " " : ""); + + if (log_details) + btf_type_ops(t)->log_details(env, t); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +#define btf_verifier_log_type(env, t, ...) \ + __btf_verifier_log_type((env), (t), true, __VA_ARGS__) +#define btf_verifier_log_basic(env, t, ...) \ + __btf_verifier_log_type((env), (t), false, __VA_ARGS__) + +__printf(4, 5) +static void btf_verifier_log_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + /* The CHECK_META phase already did a btf dump. + * + * If member is logged again, it must hit an error in + * parsing this member. It is useful to print out which + * struct this member belongs to. + */ + if (env->phase != CHECK_META) + btf_verifier_log_type(env, struct_type, NULL); + + __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", + btf_name_by_offset(btf, member->name_off), + member->type, member->offset); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +static void btf_verifier_log_hdr(struct btf_verifier_env *env, + u32 btf_data_size) +{ + struct bpf_verifier_log *log = &env->log; + const struct btf *btf = env->btf; + const struct btf_header *hdr; + + if (!bpf_verifier_log_needed(log)) + return; + + hdr = &btf->hdr; + __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); + __btf_verifier_log(log, "version: %u\n", hdr->version); + __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); + __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len); + __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); + __btf_verifier_log(log, "type_len: %u\n", hdr->type_len); + __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); + __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); + __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size); +} + +static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) +{ + struct btf *btf = env->btf; + + /* < 2 because +1 for btf_void which is always in btf->types[0]. + * btf_void is not accounted in btf->nr_types because btf_void + * does not come from the BTF file. + */ + if (btf->types_size - btf->nr_types < 2) { + /* Expand 'types' array */ + + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_TYPE) { + btf_verifier_log(env, "Exceeded max num of types"); + return -E2BIG; + } + + expand_by = max_t(u32, btf->types_size >> 2, 16); + new_size = min_t(u32, BTF_MAX_TYPE, + btf->types_size + expand_by); + + new_types = kvzalloc(new_size * sizeof(*new_types), + GFP_KERNEL | __GFP_NOWARN); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + else + memcpy(new_types, btf->types, + sizeof(*btf->types) * (btf->nr_types + 1)); + + kvfree(btf->types); + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_alloc_id(struct btf *btf) +{ + int id; + + idr_preload(GFP_KERNEL); + spin_lock_bh(&btf_idr_lock); + id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + btf->id = id; + spin_unlock_bh(&btf_idr_lock); + idr_preload_end(); + + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void btf_free_id(struct btf *btf) +{ + unsigned long flags; + + /* + * In map-in-map, calling map_delete_elem() on outer + * map will call bpf_map_put on the inner map. + * It will then eventually call btf_free_id() + * on the inner map. Some of the map_delete_elem() + * implementation may have irq disabled, so + * we need to use the _irqsave() version instead + * of the _bh() version. + */ + spin_lock_irqsave(&btf_idr_lock, flags); + idr_remove(&btf_idr, btf->id); + spin_unlock_irqrestore(&btf_idr_lock, flags); +} + +static void btf_free(struct btf *btf) +{ + kvfree(btf->types); + kvfree(btf->resolved_sizes); + kvfree(btf->resolved_ids); + kvfree(btf->data); + kfree(btf); +} + +static void btf_free_rcu(struct rcu_head *rcu) +{ + struct btf *btf = container_of(rcu, struct btf, rcu); + + btf_free(btf); +} + +void btf_put(struct btf *btf) +{ + if (btf && refcount_dec_and_test(&btf->refcnt)) { + btf_free_id(btf); + call_rcu(&btf->rcu, btf_free_rcu); + } +} + +static int env_resolve_init(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 nr_types = btf->nr_types; + u32 *resolved_sizes = NULL; + u32 *resolved_ids = NULL; + u8 *visit_states = NULL; + + /* +1 for btf_void */ + resolved_sizes = kvzalloc((nr_types + 1) * sizeof(*resolved_sizes), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_sizes) + goto nomem; + + resolved_ids = kvzalloc((nr_types + 1) * sizeof(*resolved_ids), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_ids) + goto nomem; + + visit_states = kvzalloc((nr_types + 1) * sizeof(*visit_states), + GFP_KERNEL | __GFP_NOWARN); + if (!visit_states) + goto nomem; + + btf->resolved_sizes = resolved_sizes; + btf->resolved_ids = resolved_ids; + env->visit_states = visit_states; + + return 0; + +nomem: + kvfree(resolved_sizes); + kvfree(resolved_ids); + kvfree(visit_states); + return -ENOMEM; +} + +static void btf_verifier_env_free(struct btf_verifier_env *env) +{ + kvfree(env->visit_states); + kfree(env); +} + +static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, + const struct btf_type *next_type) +{ + switch (env->resolve_mode) { + case RESOLVE_TBD: + /* int, enum or void is a sink */ + return !btf_type_needs_resolve(next_type); + case RESOLVE_PTR: + /* int, enum, void, struct or array is a sink for ptr */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_ptr(next_type); + case RESOLVE_STRUCT_OR_ARRAY: + /* int, enum, void or ptr is a sink for struct and array */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_array(next_type) && + !btf_type_is_struct(next_type); + default: + BUG(); + } +} + +static bool env_type_is_resolved(const struct btf_verifier_env *env, + u32 type_id) +{ + return env->visit_states[type_id] == RESOLVED; +} + +static int env_stack_push(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + struct resolve_vertex *v; + + if (env->top_stack == MAX_RESOLVE_DEPTH) + return -E2BIG; + + if (env->visit_states[type_id] != NOT_VISITED) + return -EEXIST; + + env->visit_states[type_id] = VISITED; + + v = &env->stack[env->top_stack++]; + v->t = t; + v->type_id = type_id; + v->next_member = 0; + + if (env->resolve_mode == RESOLVE_TBD) { + if (btf_type_is_ptr(t)) + env->resolve_mode = RESOLVE_PTR; + else if (btf_type_is_struct(t) || btf_type_is_array(t)) + env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY; + } + + return 0; +} + +static void env_stack_set_next_member(struct btf_verifier_env *env, + u16 next_member) +{ + env->stack[env->top_stack - 1].next_member = next_member; +} + +static void env_stack_pop_resolved(struct btf_verifier_env *env, + u32 resolved_type_id, + u32 resolved_size) +{ + u32 type_id = env->stack[--(env->top_stack)].type_id; + struct btf *btf = env->btf; + + btf->resolved_sizes[type_id] = resolved_size; + btf->resolved_ids[type_id] = resolved_type_id; + env->visit_states[type_id] = RESOLVED; +} + +static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) +{ + return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; +} + +/* The input param "type_id" must point to a needs_resolve type */ +static const struct btf_type *btf_type_id_resolve(const struct btf *btf, + u32 *type_id) +{ + *type_id = btf->resolved_ids[*type_id]; + return btf_type_by_id(btf, *type_id); +} + +const struct btf_type *btf_type_id_size(const struct btf *btf, + u32 *type_id, u32 *ret_size) +{ + const struct btf_type *size_type; + u32 size_type_id = *type_id; + u32 size = 0; + + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void_or_null(size_type)) + return NULL; + + if (btf_type_has_size(size_type)) { + size = size_type->size; + } else if (btf_type_is_array(size_type)) { + size = btf->resolved_sizes[size_type_id]; + } else if (btf_type_is_ptr(size_type)) { + size = sizeof(void *); + } else { + if (WARN_ON_ONCE(!btf_type_is_modifier(size_type))) + return NULL; + + size = btf->resolved_sizes[size_type_id]; + size_type_id = btf->resolved_ids[size_type_id]; + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void(size_type)) + return NULL; + } + + *type_id = size_type_id; + if (ret_size) + *ret_size = size; + + return size_type; +} + +static int btf_df_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + btf_verifier_log_basic(env, struct_type, + "Unsupported check_member"); + return -EINVAL; +} + +static int btf_df_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + btf_verifier_log_basic(env, v->t, "Unsupported resolve"); + return -EINVAL; +} + +static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m) +{ + seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); +} + +static int btf_int_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 int_data = btf_type_int(member_type); + u32 struct_bits_off = member->offset; + u32 struct_size = struct_type->size; + u32 nr_copy_bits; + u32 bytes_offset; + + if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) { + btf_verifier_log_member(env, struct_type, member, + "bits_offset exceeds U32_MAX"); + return -EINVAL; + } + + struct_bits_off += BTF_INT_OFFSET(int_data); + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + nr_copy_bits = BTF_INT_BITS(int_data) + + BITS_PER_BYTE_MASKED(struct_bits_off); + + if (nr_copy_bits > BITS_PER_U64) { + btf_verifier_log_member(env, struct_type, member, + "nr_copy_bits exceeds 64"); + return -EINVAL; + } + + if (struct_size < bytes_offset || + struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_int_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 int_data, nr_bits, meta_needed = sizeof(int_data); + u16 encoding; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + int_data = btf_type_int(t); + if (int_data & ~BTF_INT_MASK) { + btf_verifier_log_basic(env, t, "Invalid int_data:%x", + int_data); + return -EINVAL; + } + + nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); + + if (nr_bits > BITS_PER_U64) { + btf_verifier_log_type(env, t, "nr_bits exceeds %zu", + BITS_PER_U64); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) { + btf_verifier_log_type(env, t, "nr_bits exceeds type_size"); + return -EINVAL; + } + + /* + * Only one of the encoding bits is allowed and it + * should be sufficient for the pretty print purpose (i.e. decoding). + * Multiple bits can be allowed later if it is found + * to be insufficient. + */ + encoding = BTF_INT_ENCODING(int_data); + if (encoding && + encoding != BTF_INT_SIGNED && + encoding != BTF_INT_CHAR && + encoding != BTF_INT_BOOL) { + btf_verifier_log_type(env, t, "Unsupported encoding"); + return -ENOTSUPP; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_int_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + int int_data = btf_type_int(t); + + btf_verifier_log(env, + "size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(int_data), + BTF_INT_BITS(int_data), + btf_int_encoding_str(BTF_INT_ENCODING(int_data))); +} + +static void btf_int_bits_seq_show(const struct btf *btf, + const struct btf_type *t, + void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u16 nr_bits = BTF_INT_BITS(int_data); + u16 total_bits_offset; + u16 nr_copy_bytes; + u16 nr_copy_bits; + u8 nr_upper_bits; + union { + u64 u64_num; + u8 u8_nums[8]; + } print_num; + + total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + nr_copy_bits = nr_bits + bits_offset; + nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); + + print_num.u64_num = 0; + memcpy(&print_num.u64_num, data, nr_copy_bytes); + + /* Ditch the higher order bits */ + nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); + if (nr_upper_bits) { + /* We need to mask out some bits of the upper byte. */ + u8 mask = (1 << nr_upper_bits) - 1; + + print_num.u8_nums[nr_copy_bytes - 1] &= mask; + } + + print_num.u64_num >>= bits_offset; + + seq_printf(m, "0x%llx", print_num.u64_num); +} + +static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u8 encoding = BTF_INT_ENCODING(int_data); + bool sign = encoding & BTF_INT_SIGNED; + u32 nr_bits = BTF_INT_BITS(int_data); + + if (bits_offset || BTF_INT_OFFSET(int_data) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + return; + } + + switch (nr_bits) { + case 64: + if (sign) + seq_printf(m, "%lld", *(s64 *)data); + else + seq_printf(m, "%llu", *(u64 *)data); + break; + case 32: + if (sign) + seq_printf(m, "%d", *(s32 *)data); + else + seq_printf(m, "%u", *(u32 *)data); + break; + case 16: + if (sign) + seq_printf(m, "%d", *(s16 *)data); + else + seq_printf(m, "%u", *(u16 *)data); + break; + case 8: + if (sign) + seq_printf(m, "%d", *(s8 *)data); + else + seq_printf(m, "%u", *(u8 *)data); + break; + default: + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + } +} + +static const struct btf_kind_operations int_ops = { + .check_meta = btf_int_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_int_check_member, + .log_details = btf_int_log, + .seq_show = btf_int_seq_show, +}; + +static int btf_modifier_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + const struct btf_type *resolved_type; + u32 resolved_type_id = member->type; + struct btf_member resolved_member; + struct btf *btf = env->btf; + + resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); + if (!resolved_type) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member"); + return -EINVAL; + } + + resolved_member = *member; + resolved_member.type = resolved_type_id; + + return btf_type_ops(resolved_type)->check_member(env, struct_type, + &resolved_member, + resolved_type); +} + +static int btf_ptr_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_size, struct_bits_off, bytes_offset; + + struct_size = struct_type->size; + struct_bits_off = member->offset; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + if (struct_size - bytes_offset < sizeof(void *)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static int btf_ref_type_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (!BTF_TYPE_ID_VALID(t->type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static int btf_modifier_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *t = v->t; + const struct btf_type *next_type; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "typedef void new_void", "const void"...etc */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* Figure out the resolved next_type_id with size. + * They will be stored in the current modifier's + * resolved_ids and resolved_sizes such that it can + * save us a few type-following when we use it later (e.g. in + * pretty print). + */ + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, next_type_size); + + return 0; +} + +static int btf_ptr_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "void *" */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY, + * the modifier may have stopped resolving when it was resolved + * to a ptr (last-resolved-ptr). + * + * We now need to continue from the last-resolved-ptr to + * ensure the last-resolved-ptr will not referring back to + * the currenct ptr (t). + */ + if (btf_type_is_modifier(next_type)) { + const struct btf_type *resolved_type; + u32 resolved_type_id; + + resolved_type_id = next_type_id; + resolved_type = btf_type_id_resolve(btf, &resolved_type_id); + + if (btf_type_is_ptr(resolved_type) && + !env_type_is_resolve_sink(env, resolved_type) && + !env_type_is_resolved(env, resolved_type_id)) + return env_stack_push(env, resolved_type, + resolved_type_id); + } + + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_modifier_seq_show(const struct btf *btf, + const struct btf_type *t, + u32 type_id, void *data, + u8 bits_offset, struct seq_file *m) +{ + t = btf_type_id_resolve(btf, &type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); +} + +static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + /* It is a hashed value */ + seq_printf(m, "%p", *(void **)data); +} + +static void btf_ref_type_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "type_id=%u", t->type); +} + +static struct btf_kind_operations modifier_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_modifier_resolve, + .check_member = btf_modifier_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_modifier_seq_show, +}; + +static struct btf_kind_operations ptr_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_ptr_resolve, + .check_member = btf_ptr_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_ptr_seq_show, +}; + +static s32 btf_fwd_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (t->type) { + btf_verifier_log_type(env, t, "type != 0"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static struct btf_kind_operations fwd_ops = { + .check_meta = btf_fwd_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_df_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_df_seq_show, +}; + +static int btf_array_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + u32 array_type_id, array_size; + struct btf *btf = env->btf; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + array_type_id = member->type; + btf_type_id_size(btf, &array_type_id, &array_size); + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < array_size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_array_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_array *array = btf_type_array(t); + u32 meta_needed = sizeof(*array); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (t->size) { + btf_verifier_log_type(env, t, "size != 0"); + return -EINVAL; + } + + /* Array elem type and index type cannot be in type void, + * so !array->type and !array->index_type are not allowed. + */ + if (!array->type || !BTF_TYPE_ID_VALID(array->type)) { + btf_verifier_log_type(env, t, "Invalid elem"); + return -EINVAL; + } + + if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) { + btf_verifier_log_type(env, t, "Invalid index"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_array_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_array *array = btf_type_array(v->t); + const struct btf_type *elem_type, *index_type; + u32 elem_type_id, index_type_id; + struct btf *btf = env->btf; + u32 elem_size; + + /* Check array->index_type */ + index_type_id = array->index_type; + index_type = btf_type_by_id(btf, index_type_id); + if (btf_type_is_void_or_null(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, index_type) && + !env_type_is_resolved(env, index_type_id)) + return env_stack_push(env, index_type, index_type_id); + + index_type = btf_type_id_size(btf, &index_type_id, NULL); + if (!index_type || !btf_type_is_int(index_type) || + !btf_type_int_is_regular(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + /* Check array->type */ + elem_type_id = array->type; + elem_type = btf_type_by_id(btf, elem_type_id); + if (btf_type_is_void_or_null(elem_type)) { + btf_verifier_log_type(env, v->t, + "Invalid elem"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, elem_type) && + !env_type_is_resolved(env, elem_type_id)) + return env_stack_push(env, elem_type, elem_type_id); + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + if (!elem_type) { + btf_verifier_log_type(env, v->t, "Invalid elem"); + return -EINVAL; + } + + if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) { + btf_verifier_log_type(env, v->t, "Invalid array of int"); + return -EINVAL; + } + + if (array->nelems && elem_size > U32_MAX / array->nelems) { + btf_verifier_log_type(env, v->t, + "Array size overflows U32_MAX"); + return -EINVAL; + } + + env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems); + + return 0; +} + +static void btf_array_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_array *array = btf_type_array(t); + + btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u", + array->type, array->index_type, array->nelems); +} + +static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_array *array = btf_type_array(t); + const struct btf_kind_operations *elem_ops; + const struct btf_type *elem_type; + u32 i, elem_size, elem_type_id; + + elem_type_id = array->type; + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + elem_ops = btf_type_ops(elem_type); + seq_puts(m, "["); + for (i = 0; i < array->nelems; i++) { + if (i) + seq_puts(m, ","); + + elem_ops->seq_show(btf, elem_type, elem_type_id, data, + bits_offset, m); + data += elem_size; + } + seq_puts(m, "]"); +} + +static struct btf_kind_operations array_ops = { + .check_meta = btf_array_check_meta, + .resolve = btf_array_resolve, + .check_member = btf_array_check_member, + .log_details = btf_array_log, + .seq_show = btf_array_seq_show, +}; + +static int btf_struct_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < member_type->size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_struct_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; + const struct btf_member *member; + struct btf *btf = env->btf; + u32 struct_size = t->size; + u32 meta_needed; + u16 i; + + meta_needed = btf_type_vlen(t) * sizeof(*member); + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for_each_member(i, t, member) { + if (!btf_name_offset_valid(btf, member->name_off)) { + btf_verifier_log_member(env, t, member, + "Invalid member name_offset:%u", + member->name_off); + 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, + "Invalid type_id"); + return -EINVAL; + } + + if (is_union && member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { + btf_verifier_log_member(env, t, member, + "Memmber bits_offset exceeds its struct size"); + return -EINVAL; + } + + btf_verifier_log_member(env, t, member, NULL); + } + + return meta_needed; +} + +static int btf_struct_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_member *member; + int err; + u16 i; + + /* Before continue resolving the next_member, + * ensure the last member is indeed resolved to a + * type with size info. + */ + if (v->next_member) { + const struct btf_type *last_member_type; + const struct btf_member *last_member; + u16 last_member_type_id; + + last_member = btf_type_member(v->t) + v->next_member - 1; + last_member_type_id = last_member->type; + if (WARN_ON_ONCE(!env_type_is_resolved(env, + last_member_type_id))) + return -EINVAL; + + last_member_type = btf_type_by_id(env->btf, + last_member_type_id); + err = btf_type_ops(last_member_type)->check_member(env, v->t, + last_member, + last_member_type); + if (err) + return err; + } + + for_each_member_from(i, v->next_member, v->t, member) { + u32 member_type_id = member->type; + const struct btf_type *member_type = btf_type_by_id(env->btf, + member_type_id); + + if (btf_type_is_void_or_null(member_type)) { + btf_verifier_log_member(env, v->t, member, + "Invalid member"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, member_type) && + !env_type_is_resolved(env, member_type_id)) { + env_stack_set_next_member(env, i + 1); + return env_stack_push(env, member_type, member_type_id); + } + + err = btf_type_ops(member_type)->check_member(env, v->t, + member, + member_type); + if (err) + return err; + } + + env_stack_pop_resolved(env, 0, 0); + + return 0; +} + +static void btf_struct_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ","; + const struct btf_member *member; + u32 i; + + seq_puts(m, "{"); + for_each_member(i, t, member) { + const struct btf_type *member_type = btf_type_by_id(btf, + member->type); + u32 member_offset = member->offset; + u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); + u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset); + const struct btf_kind_operations *ops; + + if (i) + seq_puts(m, seq); + + ops = btf_type_ops(member_type); + ops->seq_show(btf, member_type, member->type, + data + bytes_offset, bits8_offset, m); + } + seq_puts(m, "}"); +} + +static struct btf_kind_operations struct_ops = { + .check_meta = btf_struct_check_meta, + .resolve = btf_struct_resolve, + .check_member = btf_struct_check_member, + .log_details = btf_struct_log, + .seq_show = btf_struct_seq_show, +}; + +static int btf_enum_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < sizeof(int)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_enum_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_enum *enums = btf_type_enum(t); + struct btf *btf = env->btf; + u16 i, nr_enums; + u32 meta_needed; + + nr_enums = btf_type_vlen(t); + meta_needed = nr_enums * sizeof(*enums); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->size != sizeof(int)) { + btf_verifier_log_type(env, t, "Expected size:%zu", + sizeof(int)); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for (i = 0; i < nr_enums; i++) { + if (!btf_name_offset_valid(btf, enums[i].name_off)) { + btf_verifier_log(env, "\tInvalid name_offset:%u", + enums[i].name_off); + return -EINVAL; + } + + btf_verifier_log(env, "\t%s val=%d\n", + btf_name_by_offset(btf, enums[i].name_off), + enums[i].val); + } + + return meta_needed; +} + +static void btf_enum_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_enum *enums = btf_type_enum(t); + u32 i, nr_enums = btf_type_vlen(t); + int v = *(int *)data; + + for (i = 0; i < nr_enums; i++) { + if (v == enums[i].val) { + seq_printf(m, "%s", + btf_name_by_offset(btf, enums[i].name_off)); + return; + } + } + + seq_printf(m, "%d", v); +} + +static struct btf_kind_operations enum_ops = { + .check_meta = btf_enum_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_enum_check_member, + .log_details = btf_enum_log, + .seq_show = btf_enum_seq_show, +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { + [BTF_KIND_INT] = &int_ops, + [BTF_KIND_PTR] = &ptr_ops, + [BTF_KIND_ARRAY] = &array_ops, + [BTF_KIND_STRUCT] = &struct_ops, + [BTF_KIND_UNION] = &struct_ops, + [BTF_KIND_ENUM] = &enum_ops, + [BTF_KIND_FWD] = &fwd_ops, + [BTF_KIND_TYPEDEF] = &modifier_ops, + [BTF_KIND_VOLATILE] = &modifier_ops, + [BTF_KIND_CONST] = &modifier_ops, + [BTF_KIND_RESTRICT] = &modifier_ops, +}; + +static s32 btf_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 saved_meta_left = meta_left; + s32 var_meta_size; + + if (meta_left < sizeof(*t)) { + btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu", + env->log_type_id, meta_left, sizeof(*t)); + return -EINVAL; + } + meta_left -= sizeof(*t); + + if (t->info & ~BTF_INFO_MASK) { + btf_verifier_log(env, "[%u] Invalid btf_info:%x", + env->log_type_id, t->info); + return -EINVAL; + } + + if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || + BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { + btf_verifier_log(env, "[%u] Invalid kind:%u", + env->log_type_id, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + if (!btf_name_offset_valid(env->btf, t->name_off)) { + btf_verifier_log(env, "[%u] Invalid name_offset:%u", + env->log_type_id, t->name_off); + return -EINVAL; + } + + var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left); + if (var_meta_size < 0) + return var_meta_size; + + meta_left -= var_meta_size; + + return saved_meta_left - meta_left; +} + +static int btf_check_all_metas(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + struct btf_header *hdr; + void *cur, *end; + + hdr = &btf->hdr; + cur = btf->nohdr_data + hdr->type_off; + end = btf->nohdr_data + hdr->type_len; + + env->log_type_id = 1; + while (cur < end) { + struct btf_type *t = cur; + s32 meta_size; + + meta_size = btf_check_meta(env, t, end - cur); + if (meta_size < 0) + return meta_size; + + btf_add_type(env, t); + cur += meta_size; + env->log_type_id++; + } + + return 0; +} + +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + const struct resolve_vertex *v; + int err = 0; + + env->resolve_mode = RESOLVE_TBD; + env_stack_push(env, t, type_id); + while (!err && (v = env_stack_peak(env))) { + env->log_type_id = v->type_id; + err = btf_type_ops(v->t)->resolve(env, v); + } + + env->log_type_id = type_id; + if (err == -E2BIG) + btf_verifier_log_type(env, t, + "Exceeded max resolving depth:%u", + MAX_RESOLVE_DEPTH); + else if (err == -EEXIST) + btf_verifier_log_type(env, t, "Loop detected"); + + return err; +} + +static bool btf_resolve_valid(struct btf_verifier_env *env, + const struct btf_type *t, + u32 type_id) +{ + struct btf *btf = env->btf; + + if (!env_type_is_resolved(env, type_id)) + return false; + + if (btf_type_is_struct(t)) + return !btf->resolved_ids[type_id] && + !btf->resolved_sizes[type_id]; + + if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) { + t = btf_type_id_resolve(btf, &type_id); + return t && !btf_type_is_modifier(t); + } + + if (btf_type_is_array(t)) { + const struct btf_array *array = btf_type_array(t); + const struct btf_type *elem_type; + u32 elem_type_id = array->type; + u32 elem_size; + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + return elem_type && !btf_type_is_modifier(elem_type) && + (array->nelems * elem_size == + btf->resolved_sizes[type_id]); + } + + return false; +} + +static int btf_check_all_types(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 type_id; + int err; + + err = env_resolve_init(env); + if (err) + return err; + + env->phase++; + for (type_id = 1; type_id <= btf->nr_types; type_id++) { + const struct btf_type *t = btf_type_by_id(btf, type_id); + + env->log_type_id = type_id; + if (btf_type_needs_resolve(t) && + !env_type_is_resolved(env, type_id)) { + err = btf_resolve(env, t, type_id); + if (err) + return err; + } + + if (btf_type_needs_resolve(t) && + !btf_resolve_valid(env, t, type_id)) { + btf_verifier_log_type(env, t, "Invalid resolve state"); + return -EINVAL; + } + } + + return 0; +} + +static int btf_parse_type_sec(struct btf_verifier_env *env) +{ + const struct btf_header *hdr = &env->btf->hdr; + int err; + + /* Type section must align to 4 bytes */ + if (hdr->type_off & (sizeof(u32) - 1)) { + btf_verifier_log(env, "Unaligned type_off"); + return -EINVAL; + } + + if (!hdr->type_len) { + btf_verifier_log(env, "No type found"); + return -EINVAL; + } + + err = btf_check_all_metas(env); + if (err) + return err; + + return btf_check_all_types(env); +} + +static int btf_parse_str_sec(struct btf_verifier_env *env) +{ + const struct btf_header *hdr; + struct btf *btf = env->btf; + const char *start, *end; + + hdr = &btf->hdr; + start = btf->nohdr_data + hdr->str_off; + end = start + hdr->str_len; + + if (end != btf->data + btf->data_size) { + btf_verifier_log(env, "String section is not at the end"); + return -EINVAL; + } + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + btf_verifier_log(env, "Invalid string section"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static const size_t btf_sec_info_offset[] = { + offsetof(struct btf_header, type_off), + offsetof(struct btf_header, str_off), +}; + +static int btf_sec_info_cmp(const void *a, const void *b) +{ + const struct btf_sec_info *x = a; + const struct btf_sec_info *y = b; + + return (int)(x->off - y->off) ? : (int)(x->len - y->len); +} + +static int btf_check_sec_info(struct btf_verifier_env *env, + u32 btf_data_size) +{ + struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)]; + u32 total, expected_total, i; + const struct btf_header *hdr; + const struct btf *btf; + + btf = env->btf; + hdr = &btf->hdr; + + /* Populate the secs from hdr */ + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) + secs[i] = *(struct btf_sec_info *)((void *)hdr + + btf_sec_info_offset[i]); + + sort(secs, ARRAY_SIZE(btf_sec_info_offset), + sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL); + + /* Check for gaps and overlap among sections */ + total = 0; + expected_total = btf_data_size - hdr->hdr_len; + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) { + if (expected_total < secs[i].off) { + btf_verifier_log(env, "Invalid section offset"); + return -EINVAL; + } + if (total < secs[i].off) { + /* gap */ + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + if (total > secs[i].off) { + btf_verifier_log(env, "Section overlap found"); + return -EINVAL; + } + if (expected_total - total < secs[i].len) { + btf_verifier_log(env, + "Total section length too long"); + return -EINVAL; + } + total += secs[i].len; + } + + /* There is data other than hdr and known sections */ + if (expected_total != total) { + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + + return 0; +} + +static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, + u32 btf_data_size) +{ + const struct btf_header *hdr; + u32 hdr_len, hdr_copy; + /* + * Minimal part of the "struct btf_header" that + * contains the hdr_len. + */ + struct btf_min_header { + u16 magic; + u8 version; + u8 flags; + u32 hdr_len; + } __user *min_hdr; + struct btf *btf; + int err; + + btf = env->btf; + min_hdr = btf_data; + + if (btf_data_size < sizeof(*min_hdr)) { + btf_verifier_log(env, "hdr_len not found"); + return -EINVAL; + } + + if (get_user(hdr_len, &min_hdr->hdr_len)) + return -EFAULT; + + if (btf_data_size < hdr_len) { + btf_verifier_log(env, "btf_header not found"); + return -EINVAL; + } + + err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); + if (err) { + if (err == -E2BIG) + btf_verifier_log(env, "Unsupported btf_header"); + return err; + } + + hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); + if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) + return -EFAULT; + + hdr = &btf->hdr; + + btf_verifier_log_hdr(env, btf_data_size); + + if (hdr->magic != BTF_MAGIC) { + btf_verifier_log(env, "Invalid magic"); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + btf_verifier_log(env, "Unsupported version"); + return -ENOTSUPP; + } + + if (hdr->flags) { + btf_verifier_log(env, "Unsupported flags"); + return -ENOTSUPP; + } + + if (btf_data_size == hdr->hdr_len) { + btf_verifier_log(env, "No data"); + return -EINVAL; + } + + err = btf_check_sec_info(env, btf_data_size); + if (err) + return err; + + return 0; +} + +static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, + u32 log_level, char __user *log_ubuf, u32 log_size) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf = NULL; + u8 *data; + int err; + + if (btf_data_size > BTF_MAX_SIZE) + return ERR_PTR(-E2BIG); + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + if (log_level || log_ubuf || log_size) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log->level = log_level; + log->ubuf = log_ubuf; + log->len_total = log_size; + + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) { + err = -EINVAL; + goto errout; + } + } + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + env->btf = btf; + + err = btf_parse_hdr(env, btf_data, btf_data_size); + if (err) + goto errout; + + data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); + if (!data) { + err = -ENOMEM; + goto errout; + } + + btf->data = data; + btf->data_size = btf_data_size; + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + + if (copy_from_user(data, btf_data, btf_data_size)) { + err = -EFAULT; + goto errout; + } + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_parse_type_sec(env); + if (err) + goto errout; + + if (log->level && bpf_verifier_log_full(log)) { + err = -ENOSPC; + goto errout; + } + + btf_verifier_env_free(env); + refcount_set(&btf->refcnt, 1); + return btf; + +errout: + btf_verifier_env_free(env); + if (btf) + btf_free(btf); + return ERR_PTR(err); +} + +void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m) +{ + const struct btf_type *t = btf_type_by_id(btf, type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); +} + +static int btf_release(struct inode *inode, struct file *filp) +{ + btf_put(filp->private_data); + return 0; +} + +const struct file_operations btf_fops = { + .release = btf_release, +}; + +static int __btf_new_fd(struct btf *btf) +{ + return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); +} + +int btf_new_fd(const union bpf_attr *attr) +{ + struct btf *btf; + int ret; + + btf = btf_parse(u64_to_user_ptr(attr->btf), + attr->btf_size, attr->btf_log_level, + u64_to_user_ptr(attr->btf_log_buf), + attr->btf_log_size); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + ret = btf_alloc_id(btf); + if (ret) { + btf_free(btf); + return ret; + } + + /* + * The BTF ID is published to the userspace. + * All BTF free must go through call_rcu() from + * now on (i.e. free by calling btf_put()). + */ + + ret = __btf_new_fd(btf); + if (ret < 0) + btf_put(btf); + + return ret; +} + +struct btf *btf_get_by_fd(int fd) +{ + struct btf *btf; + struct fd f; + + f = fdget(fd); + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &btf_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + btf = f.file->private_data; + refcount_inc(&btf->refcnt); + fdput(f); + + return btf; +} + +int btf_get_info_by_fd(const struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_btf_info __user *uinfo; + struct bpf_btf_info info = {}; + u32 info_copy, btf_copy; + void __user *ubtf; + u32 uinfo_len; + + uinfo = u64_to_user_ptr(attr->info.info); + uinfo_len = attr->info.info_len; + + info_copy = min_t(u32, uinfo_len, sizeof(info)); + if (copy_from_user(&info, uinfo, info_copy)) + return -EFAULT; + + info.id = btf->id; + ubtf = u64_to_user_ptr(info.btf); + btf_copy = min_t(u32, btf->data_size, info.btf_size); + if (copy_to_user(ubtf, btf->data, btf_copy)) + return -EFAULT; + info.btf_size = btf->data_size; + + if (copy_to_user(uinfo, &info, info_copy) || + put_user(info_copy, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +int btf_get_fd_by_id(u32 id) +{ + struct btf *btf; + int fd; + + rcu_read_lock(); + btf = idr_find(&btf_idr, id); + if (!btf || !refcount_inc_not_zero(&btf->refcnt)) + btf = ERR_PTR(-ENOENT); + rcu_read_unlock(); + + if (IS_ERR(btf)) + return PTR_ERR(btf); + + fd = __btf_new_fd(btf); + if (fd < 0) + btf_put(btf); + + return fd; +} + +u32 btf_id(const struct btf *btf) +{ + return btf->id; +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 43171a0bb02b..f7c00bd6f8e4 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -500,6 +500,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted + * @t_ctx: Pointer to attach type specific context * * socket is expected to be of type INET or INET6. * @@ -508,12 +509,15 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type) + enum bpf_attach_type type, + void *t_ctx) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, + .t_ctx = t_ctx, }; + struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; @@ -523,6 +527,11 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; + if (!ctx.uaddr) { + memset(&unspec, 0, sizeof(unspec)); + ctx.uaddr = (struct sockaddr *)&unspec; + } + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6ef6746a7871..9f1493705f40 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -31,6 +31,7 @@ #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> +#include <linux/perf_event.h> #include <asm/unaligned.h> @@ -683,23 +684,6 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; - case BPF_LD | BPF_ABS | BPF_W: - case BPF_LD | BPF_ABS | BPF_H: - case BPF_LD | BPF_ABS | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - - case BPF_LD | BPF_IND | BPF_W: - case BPF_LD | BPF_IND | BPF_H: - case BPF_LD | BPF_IND | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); @@ -940,14 +924,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ /* Immediate based. */ \ - INSN_3(LD, IMM, DW), \ - /* Misc (old cBPF carry-over). */ \ - INSN_3(LD, ABS, B), \ - INSN_3(LD, ABS, H), \ - INSN_3(LD, ABS, W), \ - INSN_3(LD, IND, B), \ - INSN_3(LD, IND, H), \ - INSN_3(LD, IND, W) + INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { @@ -957,6 +934,13 @@ bool bpf_opcode_in_insntable(u8 code) [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), + /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ + [BPF_LD | BPF_ABS | BPF_B] = true, + [BPF_LD | BPF_ABS | BPF_H] = true, + [BPF_LD | BPF_ABS | BPF_W] = true, + [BPF_LD | BPF_IND | BPF_B] = true, + [BPF_LD | BPF_IND | BPF_H] = true, + [BPF_LD | BPF_IND | BPF_W] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -987,8 +971,6 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; - void *ptr; - int off; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) @@ -1315,67 +1297,6 @@ out: atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); CONT; - LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ - off = IMM; -load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only - * appearing in the programs where ctx == skb - * (see may_access_skb() in the verifier). All programs - * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6, - * bpf_convert_filter() saves it in BPF_R6, internal BPF - * verifier will check that BPF_R6 == ctx. - * - * BPF_ABS and BPF_IND are wrappers of function calls, - * so they scratch BPF_R1-BPF_R5 registers, preserve - * BPF_R6-BPF_R9, and store return value into BPF_R0. - * - * Implicit input: - * ctx == skb == BPF_R6 == CTX - * - * Explicit input: - * SRC == any register - * IMM == 32-bit immediate - * - * Output: - * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness - */ - - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be32(ptr); - CONT; - } - - return 0; - LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ - off = IMM; -load_half: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be16(ptr); - CONT; - } - - return 0; - LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ - off = IMM; -load_byte: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = *(u8 *)ptr; - CONT; - } - - return 0; - LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_word; - LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_half; - LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ - off = IMM + SRC; - goto load_byte; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here @@ -1695,6 +1616,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog **existing_prog; struct bpf_prog_array *array; + bool found_exclude = false; int new_prog_idx = 0; /* Figure out how many existing progs we need to carry over to @@ -1703,14 +1625,20 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, if (old_array) { existing_prog = old_array->progs; for (; *existing_prog; existing_prog++) { - if (*existing_prog != exclude_prog && - *existing_prog != &dummy_bpf_prog.prog) + if (*existing_prog == exclude_prog) { + found_exclude = true; + continue; + } + if (*existing_prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (*existing_prog == include_prog) return -EEXIST; } } + if (exclude_prog && !found_exclude) + return -ENOENT; + /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) @@ -1772,6 +1700,10 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux = container_of(work, struct bpf_prog_aux, work); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); +#ifdef CONFIG_PERF_EVENTS + if (aux->prog->has_callchain_buf) + put_callchain_buffers(); +#endif for (i = 0; i < aux->func_cnt; i++) bpf_jit_free(aux->func[i]); if (aux->func_cnt) { @@ -1832,6 +1764,8 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_sock_map_update_proto __weak; +const struct bpf_func_proto bpf_sock_hash_update_proto __weak; +const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { @@ -1844,6 +1778,7 @@ bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, { return -ENOTSUPP; } +EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { @@ -1890,9 +1825,3 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); -#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a4bb0b34375a..e0918d180f08 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -19,6 +19,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> +#include <net/xdp.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -137,27 +138,6 @@ free_cmap: return ERR_PTR(err); } -static void __cpu_map_queue_destructor(void *ptr) -{ - /* The tear-down procedure should have made sure that queue is - * empty. See __cpu_map_entry_replace() and work-queue - * invoked cpu_map_kthread_stop(). Catch any broken behaviour - * gracefully and warn once. - */ - if (WARN_ON_ONCE(ptr)) - page_frag_free(ptr); -} - -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - /* The queue should be empty at this point */ - ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); - kfree(rcpu->queue); - kfree(rcpu); - } -} - static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) { atomic_inc(&rcpu->refcnt); @@ -179,45 +159,8 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } -/* For now, xdp_pkt is a cpumap internal data structure, with info - * carried between enqueue to dequeue. It is mapped into the top - * headroom of the packet, to avoid allocating separate mem. - */ -struct xdp_pkt { - void *data; - u16 len; - u16 headroom; - u16 metasize; - struct net_device *dev_rx; -}; - -/* Convert xdp_buff to xdp_pkt */ -static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) -{ - struct xdp_pkt *xdp_pkt; - int metasize; - int headroom; - - /* Assure headroom is available for storing info */ - headroom = xdp->data - xdp->data_hard_start; - metasize = xdp->data - xdp->data_meta; - metasize = metasize > 0 ? metasize : 0; - if (unlikely((headroom - metasize) < sizeof(*xdp_pkt))) - return NULL; - - /* Store info in top of packet */ - xdp_pkt = xdp->data_hard_start; - - xdp_pkt->data = xdp->data; - xdp_pkt->len = xdp->data_end - xdp->data; - xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); - xdp_pkt->metasize = metasize; - - return xdp_pkt; -} - static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_pkt *xdp_pkt) + struct xdp_frame *xdpf) { unsigned int frame_size; void *pkt_data_start; @@ -232,7 +175,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * would be preferred to set frame_size to 2048 or 4096 * depending on the driver. * frame_size = 2048; - * frame_len = frame_size - sizeof(*xdp_pkt); + * frame_len = frame_size - sizeof(*xdp_frame); * * Instead, with info avail, skb_shared_info in placed after * packet len. This, unfortunately fakes the truesize. @@ -240,21 +183,21 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + pkt_data_start = xdpf->data - xdpf->headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdp_pkt->headroom); - __skb_put(skb, xdp_pkt->len); - if (xdp_pkt->metasize) - skb_metadata_set(skb, xdp_pkt->metasize); + skb_reserve(skb, xdpf->headroom); + __skb_put(skb, xdpf->len); + if (xdpf->metasize) + skb_metadata_set(skb, xdpf->metasize); /* Essential SKB info: protocol and skb->dev */ - skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + skb->protocol = eth_type_trans(skb, xdpf->dev_rx); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) @@ -265,6 +208,31 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, return skb; } +static void __cpu_map_ring_cleanup(struct ptr_ring *ring) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + struct xdp_frame *xdpf; + + while ((xdpf = ptr_ring_consume(ring))) + if (WARN_ON_ONCE(xdpf)) + xdp_return_frame(xdpf); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + __cpu_map_ring_cleanup(rcpu->queue); + ptr_ring_cleanup(rcpu->queue, NULL); + kfree(rcpu->queue); + kfree(rcpu); + } +} + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -278,7 +246,7 @@ static int cpu_map_kthread_run(void *data) */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { unsigned int processed = 0, drops = 0, sched = 0; - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -301,13 +269,13 @@ static int cpu_map_kthread_run(void *data) * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + while ((xdpf = __ptr_ring_consume(rcpu->queue))) { struct sk_buff *skb; int ret; - skb = cpu_map_build_skb(rcpu, xdp_pkt); + skb = cpu_map_build_skb(rcpu, xdpf); if (!skb) { - page_frag_free(xdp_pkt); + xdp_return_frame(xdpf); continue; } @@ -604,13 +572,13 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, spin_lock(&q->producer_lock); for (i = 0; i < bq->count; i++) { - void *xdp_pkt = bq->q[i]; + struct xdp_frame *xdpf = bq->q[i]; int err; - err = __ptr_ring_produce(q, xdp_pkt); + err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - page_frag_free(xdp_pkt); /* Free xdp_pkt */ + xdp_return_frame_rx_napi(xdpf); } processed++; } @@ -625,7 +593,7 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); @@ -636,28 +604,28 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) * driver to code invoking us to finished, due to driver * (e.g. ixgbe) recycle tricks based on page-refcnt. * - * Thus, incoming xdp_pkt is always queued here (else we race + * Thus, incoming xdp_frame is always queued here (else we race * with another CPU on page-refcnt and remaining driver code). * Queue time is very short, as driver will invoke flush * operation, when completing napi->poll call. */ - bq->q[bq->count++] = xdp_pkt; + bq->q[bq->count++] = xdpf; return 0; } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) { - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; - xdp_pkt = convert_to_xdp_pkt(xdp); - if (unlikely(!xdp_pkt)) + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) return -EOVERFLOW; /* Info needed when constructing SKB on remote CPU */ - xdp_pkt->dev_rx = dev_rx; + xdpf->dev_rx = dev_rx; - bq_enqueue(rcpu, xdp_pkt); + bq_enqueue(rcpu, xdpf); return 0; } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 565f9ece9115..a7cc7b3494a9 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -48,15 +48,25 @@ * calls will fail at this point. */ #include <linux/bpf.h> +#include <net/xdp.h> #include <linux/filter.h> +#include <trace/events/xdp.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +#define DEV_MAP_BULK_SIZE 16 +struct xdp_bulk_queue { + struct xdp_frame *q[DEV_MAP_BULK_SIZE]; + struct net_device *dev_rx; + unsigned int count; +}; + struct bpf_dtab_netdev { - struct net_device *dev; + struct net_device *dev; /* must be first member, due to tracepoint */ struct bpf_dtab *dtab; unsigned int bit; + struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; }; @@ -206,6 +216,50 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) __set_bit(bit, bitmap); } +static int bq_xmit_all(struct bpf_dtab_netdev *obj, + struct xdp_bulk_queue *bq, u32 flags) +{ + struct net_device *dev = obj->dev; + int sent = 0, drops = 0, err = 0; + int i; + + if (unlikely(!bq->count)) + return 0; + + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + prefetch(xdpf); + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); + if (sent < 0) { + err = sent; + sent = 0; + goto error; + } + drops = bq->count - sent; +out: + bq->count = 0; + + trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + sent, drops, bq->dev_rx, dev, err); + bq->dev_rx = NULL; + return 0; +error: + /* If ndo_xdp_xmit fails with an errno, no frames have been + * xmit'ed and it's our responsibility to them free all. + */ + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + /* RX path under NAPI protection, can return frames faster */ + xdp_return_frame_rx_napi(xdpf); + drops++; + } + goto out; +} + /* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled @@ -221,7 +275,7 @@ void __dev_map_flush(struct bpf_map *map) for_each_set_bit(bit, bitmap, map->max_entries) { struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); - struct net_device *netdev; + struct xdp_bulk_queue *bq; /* This is possible if the dev entry is removed by user space * between xdp redirect and flush op. @@ -230,9 +284,9 @@ void __dev_map_flush(struct bpf_map *map) continue; __clear_bit(bit, bitmap); - netdev = dev->dev; - if (likely(netdev->netdev_ops->ndo_xdp_flush)) - netdev->netdev_ops->ndo_xdp_flush(netdev); + + bq = this_cpu_ptr(dev->bulkq); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); } } @@ -240,37 +294,79 @@ void __dev_map_flush(struct bpf_map *map) * update happens in parallel here a dev_put wont happen until after reading the * ifindex. */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct bpf_dtab_netdev *dev; + struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; - dev = READ_ONCE(dtab->netdev_map[key]); - return dev ? dev->dev : NULL; + obj = READ_ONCE(dtab->netdev_map[key]); + return obj; +} + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, + struct net_device *dev_rx) + +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + + if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) + bq_xmit_all(obj, bq, 0); + + /* Ingress dev_rx will be the same for all xdp_frame's in + * bulk_queue, because bq stored per-CPU and must be flushed + * from net_device drivers NAPI func end. + */ + if (!bq->dev_rx) + bq->dev_rx = dev_rx; + + bq->q[bq->count++] = xdpf; + return 0; +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + struct xdp_frame *xdpf; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + return bq_enqueue(dst, xdpf, dev_rx); } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { - struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key); + struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; return dev ? &dev->ifindex : NULL; } static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { - if (dev->dev->netdev_ops->ndo_xdp_flush) { - struct net_device *fl = dev->dev; + if (dev->dev->netdev_ops->ndo_xdp_xmit) { + struct xdp_bulk_queue *bq; unsigned long *bitmap; + int cpu; for_each_online_cpu(cpu) { bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); __clear_bit(dev->bit, bitmap); - fl->netdev_ops->ndo_xdp_flush(dev->dev); + bq = per_cpu_ptr(dev->bulkq, cpu); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); } } } @@ -281,6 +377,7 @@ static void __dev_map_entry_free(struct rcu_head *rcu) dev = container_of(rcu, struct bpf_dtab_netdev, rcu); dev_map_flush_old(dev); + free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -313,6 +410,7 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct net *net = current->nsproxy->net_ns; + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; u32 i = *(u32 *)key; u32 ifindex = *(u32 *)value; @@ -327,13 +425,20 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); if (!dev) return -ENOMEM; + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return -ENOMEM; + } + dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { + free_percpu(dev->bulkq); kfree(dev); return -EINVAL; } @@ -405,6 +510,9 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { + /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ + BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != + offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b76828f23b49..3ca2198a6d22 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -503,7 +503,9 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -530,7 +532,9 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map, const int ret = BPF_REG_0; const int ref_reg = BPF_REG_1; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -1369,7 +1373,9 @@ static u32 htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3d24e238221e..73065e2d23c2 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -179,3 +179,18 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, }; + +#ifdef CONFIG_CGROUPS +BPF_CALL_0(bpf_get_current_cgroup_id) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + + return cgrp->kn->id.id; +} + +const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { + .func = bpf_get_current_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; +#endif diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index bf6da59ae0d0..ed13645bd80c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -150,8 +150,154 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; } +struct map_iter { + void *key; + bool done; +}; + +static struct map_iter *map_iter(struct seq_file *m) +{ + return m->private; +} + +static struct bpf_map *seq_file_to_map(struct seq_file *m) +{ + return file_inode(m->file)->i_private; +} + +static void map_iter_free(struct map_iter *iter) +{ + if (iter) { + kfree(iter->key); + kfree(iter); + } +} + +static struct map_iter *map_iter_alloc(struct bpf_map *map) +{ + struct map_iter *iter; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); + if (!iter) + goto error; + + iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); + if (!iter->key) + goto error; + + return iter; + +error: + map_iter_free(iter); + return NULL; +} + +static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (map_iter(m)->done) + return NULL; + + if (unlikely(v == SEQ_START_TOKEN)) + goto done; + + if (map->ops->map_get_next_key(map, key, key)) { + map_iter(m)->done = true; + return NULL; + } + +done: + ++(*pos); + return key; +} + +static void *map_seq_start(struct seq_file *m, loff_t *pos) +{ + if (map_iter(m)->done) + return NULL; + + return *pos ? map_iter(m)->key : SEQ_START_TOKEN; +} + +static void map_seq_stop(struct seq_file *m, void *v) +{ +} + +static int map_seq_show(struct seq_file *m, void *v) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (unlikely(v == SEQ_START_TOKEN)) { + seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); + seq_puts(m, "# WARNING!! The output format will change\n"); + } else { + map->ops->map_seq_show_elem(map, key, m); + } + + return 0; +} + +static const struct seq_operations bpffs_map_seq_ops = { + .start = map_seq_start, + .next = map_seq_next, + .show = map_seq_show, + .stop = map_seq_stop, +}; + +static int bpffs_map_open(struct inode *inode, struct file *file) +{ + struct bpf_map *map = inode->i_private; + struct map_iter *iter; + struct seq_file *m; + int err; + + iter = map_iter_alloc(map); + if (!iter) + return -ENOMEM; + + err = seq_open(file, &bpffs_map_seq_ops); + if (err) { + map_iter_free(iter); + return err; + } + + m = file->private_data; + m->private = iter; + + return 0; +} + +static int bpffs_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + map_iter_free(map_iter(m)); + + return seq_release(inode, file); +} + +/* bpffs_map_fops should only implement the basic + * read operation for a BPF map. The purpose is to + * provide a simple user intuitive way to do + * "cat bpffs/pathto/a-pinned-map". + * + * Other operations (e.g. write, lookup...) should be realized by + * the userspace tools (e.g. bpftool) through the + * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update + * interface. + */ +static const struct file_operations bpffs_map_fops = { + .open = bpffs_map_open, + .read = seq_read, + .release = bpffs_map_release, +}; + static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, - const struct inode_operations *iops) + const struct inode_operations *iops, + const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); @@ -159,6 +305,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, return PTR_ERR(inode); inode->i_op = iops; + inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); @@ -167,12 +314,15 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops); + return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, NULL); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops); + struct bpf_map *map = arg; + + return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, + map->btf ? &bpffs_map_fops : NULL); } static struct dentry * @@ -279,13 +429,6 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) ret = bpf_obj_do_pin(pname, raw, type); if (ret != 0) bpf_any_put(raw, type); - if ((trace_bpf_obj_pin_prog_enabled() || - trace_bpf_obj_pin_map_enabled()) && !ret) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_pin_prog(raw, ufd, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_pin_map(raw, ufd, pname); - } out: putname(pname); return ret; @@ -352,15 +495,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) else goto out; - if (ret < 0) { + if (ret < 0) bpf_any_put(raw, type); - } else if (trace_bpf_obj_get_prog_enabled() || - trace_bpf_obj_get_map_enabled()) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_get_prog(raw, ret, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_get_map(raw, ret, pname); - } out: putname(pname); return ret; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index c9401075b58c..ac747d5cf7c6 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -474,8 +474,10 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) struct bpf_prog_offload *offload; bool ret; - if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map)) + if (!bpf_prog_is_dev_bound(prog->aux)) return false; + if (!bpf_map_is_dev_bound(map)) + return bpf_map_offload_neutral(map); down_read(&bpf_devs_lock); offload = prog->aux->offload; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 95a84b2f10ce..52a91d816c0e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -48,14 +48,40 @@ #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) -struct bpf_stab { - struct bpf_map map; - struct sock **sock_map; +struct bpf_sock_progs { struct bpf_prog *bpf_tx_msg; struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; }; +struct bpf_stab { + struct bpf_map map; + struct sock **sock_map; + struct bpf_sock_progs progs; +}; + +struct bucket { + struct hlist_head head; + raw_spinlock_t lock; +}; + +struct bpf_htab { + struct bpf_map map; + struct bucket *buckets; + atomic_t count; + u32 n_buckets; + u32 elem_size; + struct bpf_sock_progs progs; +}; + +struct htab_elem { + struct rcu_head rcu; + struct hlist_node hash_node; + u32 hash; + struct sock *sk; + char key[0]; +}; + enum smap_psock_state { SMAP_TX_RUNNING, }; @@ -63,6 +89,8 @@ enum smap_psock_state { struct smap_psock_map_entry { struct list_head list; struct sock **entry; + struct htab_elem *hash_link; + struct bpf_htab *htab; }; struct smap_psock { @@ -191,6 +219,12 @@ out: rcu_read_unlock(); } +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + atomic_dec(&htab->count); + kfree_rcu(l, rcu); +} + static void bpf_tcp_close(struct sock *sk, long timeout) { void (*close_fun)(struct sock *sk, long timeout); @@ -227,10 +261,16 @@ static void bpf_tcp_close(struct sock *sk, long timeout) } list_for_each_entry_safe(e, tmp, &psock->maps, list) { - osk = cmpxchg(e->entry, sk, NULL); - if (osk == sk) { - list_del(&e->list); - smap_release_sock(psock, sk); + if (e->entry) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + list_del(&e->list); + smap_release_sock(psock, sk); + } + } else { + hlist_del_rcu(&e->hash_link->hash_node); + smap_release_sock(psock, e->hash_link->sk); + free_htab_elem(e->htab, e->hash_link); } } write_unlock_bh(&sk->sk_callback_lock); @@ -461,7 +501,7 @@ static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) { return ((_rc == SK_PASS) ? - (md->map ? __SK_REDIRECT : __SK_PASS) : + (md->sk_redir ? __SK_REDIRECT : __SK_PASS) : __SK_DROP); } @@ -483,6 +523,7 @@ static unsigned int smap_do_tx_msg(struct sock *sk, } bpf_compute_data_pointers_sg(md); + md->sk = sk; rc = (*prog->bpf_func)(md, prog->insnsi); psock->apply_bytes = md->apply_bytes; @@ -1092,7 +1133,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) * when we orphan the skb so that we don't have the possibility * to reference a stale map. */ - TCP_SKB_CB(skb)->bpf.map = NULL; + TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; bpf_compute_data_pointers(skb); preempt_disable(); @@ -1102,7 +1143,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) /* Moving return codes from UAPI namespace into internal namespace */ return rc == SK_PASS ? - (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) : + (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) : __SK_DROP; } @@ -1372,7 +1413,6 @@ static int smap_init_sock(struct smap_psock *psock, } static void smap_init_progs(struct smap_psock *psock, - struct bpf_stab *stab, struct bpf_prog *verdict, struct bpf_prog *parse) { @@ -1450,14 +1490,13 @@ static void smap_gc_work(struct work_struct *w) kfree(psock); } -static struct smap_psock *smap_init_psock(struct sock *sock, - struct bpf_stab *stab) +static struct smap_psock *smap_init_psock(struct sock *sock, int node) { struct smap_psock *psock; psock = kzalloc_node(sizeof(struct smap_psock), GFP_ATOMIC | __GFP_NOWARN, - stab->map.numa_node); + node); if (!psock) return ERR_PTR(-ENOMEM); @@ -1525,12 +1564,14 @@ free_stab: return ERR_PTR(err); } -static void smap_list_remove(struct smap_psock *psock, struct sock **entry) +static void smap_list_remove(struct smap_psock *psock, + struct sock **entry, + struct htab_elem *hash_link) { struct smap_psock_map_entry *e, *tmp; list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry) { + if (e->entry == entry || e->hash_link == hash_link) { list_del(&e->list); break; } @@ -1568,7 +1609,7 @@ static void sock_map_free(struct bpf_map *map) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, &stab->sock_map[i]); + smap_list_remove(psock, &stab->sock_map[i], NULL); smap_release_sock(psock, sock); } write_unlock_bh(&sock->sk_callback_lock); @@ -1627,7 +1668,7 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) if (psock->bpf_parse) smap_stop_sock(psock, sock); - smap_list_remove(psock, &stab->sock_map[k]); + smap_list_remove(psock, &stab->sock_map[k], NULL); smap_release_sock(psock, sock); out: write_unlock_bh(&sock->sk_callback_lock); @@ -1662,40 +1703,26 @@ out: * - sock_map must use READ_ONCE and (cmp)xchg operations * - BPF verdict/parse programs must use READ_ONCE and xchg operations */ -static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 flags) + +static int __sock_map_ctx_update_elem(struct bpf_map *map, + struct bpf_sock_progs *progs, + struct sock *sock, + struct sock **map_link, + void *key) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct smap_psock_map_entry *e = NULL; struct bpf_prog *verdict, *parse, *tx_msg; - struct sock *osock, *sock; + struct smap_psock_map_entry *e = NULL; struct smap_psock *psock; - u32 i = *(u32 *)key; bool new = false; - int err; - - if (unlikely(flags > BPF_EXIST)) - return -EINVAL; - - if (unlikely(i >= stab->map.max_entries)) - return -E2BIG; - - sock = READ_ONCE(stab->sock_map[i]); - if (flags == BPF_EXIST && !sock) - return -ENOENT; - else if (flags == BPF_NOEXIST && sock) - return -EEXIST; - - sock = skops->sk; + int err = 0; /* 1. If sock map has BPF programs those will be inherited by the * sock being added. If the sock is already attached to BPF programs * this results in an error. */ - verdict = READ_ONCE(stab->bpf_verdict); - parse = READ_ONCE(stab->bpf_parse); - tx_msg = READ_ONCE(stab->bpf_tx_msg); + verdict = READ_ONCE(progs->bpf_verdict); + parse = READ_ONCE(progs->bpf_parse); + tx_msg = READ_ONCE(progs->bpf_tx_msg); if (parse && verdict) { /* bpf prog refcnt may be zero if a concurrent attach operation @@ -1748,7 +1775,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto out_progs; } } else { - psock = smap_init_psock(sock, stab); + psock = smap_init_psock(sock, map->numa_node); if (IS_ERR(psock)) { err = PTR_ERR(psock); goto out_progs; @@ -1758,12 +1785,13 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, new = true; } - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) { - err = -ENOMEM; - goto out_progs; + if (map_link) { + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) { + err = -ENOMEM; + goto out_progs; + } } - e->entry = &stab->sock_map[i]; /* 3. At this point we have a reference to a valid psock that is * running. Attach any BPF programs needed. @@ -1780,7 +1808,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, err = smap_init_sock(psock, sock); if (err) goto out_free; - smap_init_progs(psock, stab, verdict, parse); + smap_init_progs(psock, verdict, parse); smap_start_sock(psock, sock); } @@ -1789,19 +1817,12 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, * it with. Because we can only have a single set of programs if * old_sock has a strp we can stop it. */ - list_add_tail(&e->list, &psock->maps); - write_unlock_bh(&sock->sk_callback_lock); - - osock = xchg(&stab->sock_map[i], sock); - if (osock) { - struct smap_psock *opsock = smap_psock_sk(osock); - - write_lock_bh(&osock->sk_callback_lock); - smap_list_remove(opsock, &stab->sock_map[i]); - smap_release_sock(opsock, osock); - write_unlock_bh(&osock->sk_callback_lock); + if (map_link) { + e->entry = map_link; + list_add_tail(&e->list, &psock->maps); } - return 0; + write_unlock_bh(&sock->sk_callback_lock); + return err; out_free: smap_release_sock(psock, sock); out_progs: @@ -1816,23 +1837,73 @@ out_progs: return err; } -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) +static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_sock_progs *progs = &stab->progs; + struct sock *osock, *sock; + u32 i = *(u32 *)key; + int err; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + if (unlikely(i >= stab->map.max_entries)) + return -E2BIG; + + sock = READ_ONCE(stab->sock_map[i]); + if (flags == BPF_EXIST && !sock) + return -ENOENT; + else if (flags == BPF_NOEXIST && sock) + return -EEXIST; + + sock = skops->sk; + err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i], + key); + if (err) + goto out; + + osock = xchg(&stab->sock_map[i], sock); + if (osock) { + struct smap_psock *opsock = smap_psock_sk(osock); + + write_lock_bh(&osock->sk_callback_lock); + smap_list_remove(opsock, &stab->sock_map[i], NULL); + smap_release_sock(opsock, osock); + write_unlock_bh(&osock->sk_callback_lock); + } +out: + return err; +} + +int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) +{ + struct bpf_sock_progs *progs; struct bpf_prog *orig; - if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP)) + if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + progs = &stab->progs; + } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + progs = &htab->progs; + } else { return -EINVAL; + } switch (type) { case BPF_SK_MSG_VERDICT: - orig = xchg(&stab->bpf_tx_msg, prog); + orig = xchg(&progs->bpf_tx_msg, prog); break; case BPF_SK_SKB_STREAM_PARSER: - orig = xchg(&stab->bpf_parse, prog); + orig = xchg(&progs->bpf_parse, prog); break; case BPF_SK_SKB_STREAM_VERDICT: - orig = xchg(&stab->bpf_verdict, prog); + orig = xchg(&progs->bpf_verdict, prog); break; default: return -EOPNOTSUPP; @@ -1880,21 +1951,421 @@ static int sock_map_update_elem(struct bpf_map *map, static void sock_map_release(struct bpf_map *map) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_sock_progs *progs; struct bpf_prog *orig; - orig = xchg(&stab->bpf_parse, NULL); + if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + progs = &stab->progs; + } else { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + progs = &htab->progs; + } + + orig = xchg(&progs->bpf_parse, NULL); if (orig) bpf_prog_put(orig); - orig = xchg(&stab->bpf_verdict, NULL); + orig = xchg(&progs->bpf_verdict, NULL); if (orig) bpf_prog_put(orig); - orig = xchg(&stab->bpf_tx_msg, NULL); + orig = xchg(&progs->bpf_tx_msg, NULL); if (orig) bpf_prog_put(orig); } +static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) +{ + struct bpf_htab *htab; + int i, err; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->value_size != 4 || + attr->map_flags & ~SOCK_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + + if (attr->key_size > MAX_BPF_STACK) + /* eBPF programs initialize keys on stack, so they cannot be + * larger than max stack size + */ + return ERR_PTR(-E2BIG); + + err = bpf_tcp_ulp_register(); + if (err && err != -EEXIST) + return ERR_PTR(err); + + htab = kzalloc(sizeof(*htab), GFP_USER); + if (!htab) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&htab->map, attr); + + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); + htab->elem_size = sizeof(struct htab_elem) + + round_up(htab->map.key_size, 8); + err = -EINVAL; + if (htab->n_buckets == 0 || + htab->n_buckets > U32_MAX / sizeof(struct bucket)) + goto free_htab; + + cost = (u64) htab->n_buckets * sizeof(struct bucket) + + (u64) htab->elem_size * htab->map.max_entries; + + if (cost >= U32_MAX - PAGE_SIZE) + goto free_htab; + + htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(htab->map.pages); + if (err) + goto free_htab; + + err = -ENOMEM; + htab->buckets = bpf_map_area_alloc( + htab->n_buckets * sizeof(struct bucket), + htab->map.numa_node); + if (!htab->buckets) + goto free_htab; + + for (i = 0; i < htab->n_buckets; i++) { + INIT_HLIST_HEAD(&htab->buckets[i].head); + raw_spin_lock_init(&htab->buckets[i].lock); + } + + return &htab->map; +free_htab: + kfree(htab); + return ERR_PTR(err); +} + +static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &htab->buckets[hash & (htab->n_buckets - 1)]; +} + +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &__select_bucket(htab, hash)->head; +} + +static void sock_hash_free(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + int i; + + synchronize_rcu(); + + /* At this point no update, lookup or delete operations can happen. + * However, be aware we can still get a socket state event updates, + * and data ready callabacks that reference the psock from sk_user_data + * Also psock worker threads are still in-flight. So smap_release_sock + * will only free the psock after cancel_sync on the worker threads + * and a grace period expire to ensure psock is really safe to remove. + */ + rcu_read_lock(); + for (i = 0; i < htab->n_buckets; i++) { + struct hlist_head *head = select_bucket(htab, i); + struct hlist_node *n; + struct htab_elem *l; + + hlist_for_each_entry_safe(l, n, head, hash_node) { + struct sock *sock = l->sk; + struct smap_psock *psock; + + hlist_del_rcu(&l->hash_node); + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + /* This check handles a racing sock event that can get + * the sk_callback_lock before this case but after xchg + * causing the refcnt to hit zero and sock user data + * (psock) to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_remove(psock, NULL, l); + smap_release_sock(psock, sock); + } + write_unlock_bh(&sock->sk_callback_lock); + kfree(l); + } + } + rcu_read_unlock(); + bpf_map_area_free(htab->buckets); + kfree(htab); +} + +static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, + void *key, u32 key_size, u32 hash, + struct sock *sk, + struct htab_elem *old_elem) +{ + struct htab_elem *l_new; + + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + if (!old_elem) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + } + l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); + if (!l_new) + return ERR_PTR(-ENOMEM); + + memcpy(l_new->key, key, key_size); + l_new->sk = sk; + l_new->hash = hash; + return l_new; +} + +static struct htab_elem *lookup_elem_raw(struct hlist_head *head, + u32 hash, void *key, u32 key_size) +{ + struct htab_elem *l; + + hlist_for_each_entry_rcu(l, head, hash_node) { + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + } + + return NULL; +} + +static inline u32 htab_map_hash(const void *key, u32 key_len) +{ + return jhash(key, key_len, 0); +} + +static int sock_hash_get_next_key(struct bpf_map *map, + void *key, void *next_key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l, *next_l; + struct hlist_head *h; + u32 hash, key_size; + int i = 0; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + if (!key) + goto find_first_elem; + hash = htab_map_hash(key, key_size); + h = select_bucket(htab, hash); + + l = lookup_elem_raw(h, hash, key, key_size); + if (!l) + goto find_first_elem; + next_l = hlist_entry_safe( + rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + struct htab_elem, hash_node); + if (next_l) { + memcpy(next_key, next_l->key, key_size); + return 0; + } + + /* no more elements in this hash list, go to the next bucket */ + i = hash & (htab->n_buckets - 1); + i++; + +find_first_elem: + /* iterate over buckets */ + for (; i < htab->n_buckets; i++) { + h = select_bucket(htab, i); + + /* pick first element in the bucket */ + next_l = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(h)), + struct htab_elem, hash_node); + if (next_l) { + /* if it's not empty, just return it */ + memcpy(next_key, next_l->key, key_size); + return 0; + } + } + + /* iterated over all buckets and all elements */ + return -ENOENT; +} + +static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 map_flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct bpf_sock_progs *progs = &htab->progs; + struct htab_elem *l_new = NULL, *l_old; + struct smap_psock_map_entry *e = NULL; + struct hlist_head *head; + struct smap_psock *psock; + u32 key_size, hash; + struct sock *sock; + struct bucket *b; + int err; + + sock = skops->sk; + + if (sock->sk_type != SOCK_STREAM || + sock->sk_protocol != IPPROTO_TCP) + return -EOPNOTSUPP; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) + return -ENOMEM; + + WARN_ON_ONCE(!rcu_read_lock_held()); + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key); + if (err) + goto err; + + /* bpf_map_update_elem() can be called in_irq() */ + raw_spin_lock_bh(&b->lock); + l_old = lookup_elem_raw(head, hash, key, key_size); + if (l_old && map_flags == BPF_NOEXIST) { + err = -EEXIST; + goto bucket_err; + } + if (!l_old && map_flags == BPF_EXIST) { + err = -ENOENT; + goto bucket_err; + } + + l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old); + if (IS_ERR(l_new)) { + err = PTR_ERR(l_new); + goto bucket_err; + } + + psock = smap_psock_sk(sock); + if (unlikely(!psock)) { + err = -EINVAL; + goto bucket_err; + } + + e->hash_link = l_new; + e->htab = container_of(map, struct bpf_htab, map); + list_add_tail(&e->list, &psock->maps); + + /* add new element to the head of the list, so that + * concurrent search will find it before old elem + */ + hlist_add_head_rcu(&l_new->hash_node, head); + if (l_old) { + psock = smap_psock_sk(l_old->sk); + + hlist_del_rcu(&l_old->hash_node); + smap_list_remove(psock, NULL, l_old); + smap_release_sock(psock, l_old->sk); + free_htab_elem(htab, l_old); + } + raw_spin_unlock_bh(&b->lock); + return 0; +bucket_err: + raw_spin_unlock_bh(&b->lock); +err: + kfree(e); + psock = smap_psock_sk(sock); + if (psock) + smap_release_sock(psock, sock); + return err; +} + +static int sock_hash_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_sock_ops_kern skops; + u32 fd = *(u32 *)value; + struct socket *socket; + int err; + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + skops.sk = socket->sk; + if (!skops.sk) { + fput(socket->file); + return -EINVAL; + } + + err = sock_hash_ctx_update_elem(&skops, map, key, flags); + fput(socket->file); + return err; +} + +static int sock_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct bucket *b; + struct htab_elem *l; + u32 hash, key_size; + int ret = -ENOENT; + + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, hash, key, key_size); + if (l) { + struct sock *sock = l->sk; + struct smap_psock *psock; + + hlist_del_rcu(&l->hash_node); + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + /* This check handles a racing sock event that can get the + * sk_callback_lock before this case but after xchg happens + * causing the refcnt to hit zero and sock user data (psock) + * to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_remove(psock, NULL, l); + smap_release_sock(psock, sock); + } + write_unlock_bh(&sock->sk_callback_lock); + free_htab_elem(htab, l); + ret = 0; + } + raw_spin_unlock_bh(&b->lock); + return ret; +} + +struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct htab_elem *l; + u32 key_size, hash; + struct bucket *b; + struct sock *sk; + + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, hash, key, key_size); + sk = l ? l->sk : NULL; + raw_spin_unlock_bh(&b->lock); + return sk; +} + const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, @@ -1905,6 +2376,15 @@ const struct bpf_map_ops sock_map_ops = { .map_release_uref = sock_map_release, }; +const struct bpf_map_ops sock_hash_ops = { + .map_alloc = sock_hash_alloc, + .map_free = sock_hash_free, + .map_lookup_elem = sock_map_lookup, + .map_get_next_key = sock_hash_get_next_key, + .map_update_elem = sock_hash_update_elem, + .map_delete_elem = sock_hash_delete_elem, +}; + BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { @@ -1922,3 +2402,21 @@ const struct bpf_func_proto bpf_sock_map_update_proto = { .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, void *, key, u64, flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); +} + +const struct bpf_func_proto bpf_sock_hash_update_proto = { + .func = bpf_sock_hash_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 57eeb1234b67..b675a3f3d141 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,7 @@ #include <linux/perf_event.h> #include <linux/elf.h> #include <linux/pagemap.h> +#include <linux/irq_work.h> #include "percpu_freelist.h" #define STACK_CREATE_FLAG_MASK \ @@ -32,6 +33,23 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[]; }; +/* irq_work to run up_read() for build_id lookup in nmi context */ +struct stack_map_irq_work { + struct irq_work irq_work; + struct rw_semaphore *sem; +}; + +static void do_up_read(struct irq_work *entry) +{ + struct stack_map_irq_work *work; + + work = container_of(entry, struct stack_map_irq_work, irq_work); + up_read(work->sem); + work->sem = NULL; +} + +static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); + static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -262,27 +280,31 @@ out: return ret; } -static void stack_map_get_build_id_offset(struct bpf_map *map, - struct stack_map_bucket *bucket, +static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; struct vm_area_struct *vma; - struct bpf_stack_build_id *id_offs; - - bucket->nr = trace_nr; - id_offs = (struct bpf_stack_build_id *)bucket->data; + bool irq_work_busy = false; + struct stack_map_irq_work *work = NULL; + + if (in_nmi()) { + work = this_cpu_ptr(&up_read_work); + if (work->irq_work.flags & IRQ_WORK_BUSY) + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } /* - * We cannot do up_read() in nmi context, so build_id lookup is - * only supported for non-nmi events. If at some point, it is - * possible to run find_vma() without taking the semaphore, we - * would like to allow build_id lookup in nmi context. + * We cannot do up_read() in nmi context. To do build_id lookup + * in nmi context, we need to run up_read() in irq_work. We use + * a percpu variable to do the irq_work. If the irq_work is + * already used by another lookup, we fall back to report ips. * * Same fallback is used for kernel stack (!user) on a stackmap * with build_id. */ - if (!user || !current || !current->mm || in_nmi() || + if (!user || !current || !current->mm || irq_work_busy || down_read_trylock(¤t->mm->mmap_sem) == 0) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { @@ -304,7 +326,13 @@ static void stack_map_get_build_id_offset(struct bpf_map *map, - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - up_read(¤t->mm->mmap_sem); + + if (!work) { + up_read(¤t->mm->mmap_sem); + } else { + work->sem = ¤t->mm->mmap_sem; + irq_work_queue(&work->irq_work); + } } BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, @@ -361,8 +389,10 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; - stack_map_get_build_id_offset(map, new_bucket, ips, - trace_nr, user); + new_bucket->nr = trace_nr; + stack_map_get_build_id_offset( + (struct bpf_stack_build_id *)new_bucket->data, + ips, trace_nr, user); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { @@ -405,6 +435,73 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, + u64, flags) +{ + u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + bool user_build_id = flags & BPF_F_USER_BUILD_ID; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + bool user = flags & BPF_F_USER_STACK; + struct perf_callchain_entry *trace; + bool kernel = !user; + int err = -EINVAL; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_USER_BUILD_ID))) + goto clear; + if (kernel && user_build_id) + goto clear; + + elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) + : sizeof(u64); + if (unlikely(size % elem_size)) + goto clear; + + num_elem = size / elem_size; + if (sysctl_perf_event_max_stack < num_elem) + init_nr = 0; + else + init_nr = sysctl_perf_event_max_stack - num_elem; + trace = get_perf_callchain(regs, init_nr, kernel, user, + sysctl_perf_event_max_stack, false, false); + if (unlikely(!trace)) + goto err_fault; + + trace_nr = trace->nr - init_nr; + if (trace_nr < skip) + goto err_fault; + + trace_nr -= skip; + trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; + copy_len = trace_nr * elem_size; + ips = trace->ip + skip + init_nr; + if (user && user_build_id) + stack_map_get_build_id_offset(buf, ips, trace_nr, user); + else + memcpy(buf, ips, copy_len); + + if (size > copy_len) + memset(buf + copy_len, 0, size - copy_len); + return copy_len; + +err_fault: + err = -EFAULT; +clear: + memset(buf, 0, size); + return err; +} + +const struct bpf_func_proto bpf_get_stack_proto = { + .func = bpf_get_stack, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { @@ -511,3 +608,16 @@ const struct bpf_map_ops stack_map_ops = { .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, }; + +static int __init stack_map_init(void) +{ + int cpu; + struct stack_map_irq_work *work; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&up_read_work, cpu); + init_irq_work(&work->irq_work, do_up_read); + } + return 0; +} +subsys_initcall(stack_map_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 016ef9025827..0fa20624707f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -11,13 +11,17 @@ */ #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/bpf_lirc.h> +#include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> +#include <linux/fdtable.h> #include <linux/file.h> +#include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/version.h> @@ -26,6 +30,7 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> +#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -63,9 +68,9 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -static int check_uarg_tail_zero(void __user *uaddr, - size_t expected_size, - size_t actual_size) +int bpf_check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) { unsigned char __user *addr; unsigned char __user *end; @@ -273,6 +278,7 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) if (atomic_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); + btf_put(map->btf); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } @@ -282,6 +288,7 @@ void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); } +EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { @@ -320,13 +327,15 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "map_id:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, - map->pages * 1ULL << PAGE_SHIFT); + map->pages * 1ULL << PAGE_SHIFT, + map->id); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", @@ -418,7 +427,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_ifindex +#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -452,6 +461,33 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); + if (bpf_map_support_seq_show(map) && + (attr->btf_key_type_id || attr->btf_value_type_id)) { + struct btf *btf; + + if (!attr->btf_key_type_id || !attr->btf_value_type_id) { + err = -EINVAL; + goto free_map_nouncharge; + } + + btf = btf_get_by_fd(attr->btf_fd); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto free_map_nouncharge; + } + + err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); + if (err) { + btf_put(btf); + goto free_map_nouncharge; + } + + map->btf = btf; + map->btf_key_type_id = attr->btf_key_type_id; + map->btf_value_type_id = attr->btf_value_type_id; + } + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; @@ -476,7 +512,6 @@ static int map_create(union bpf_attr *attr) return err; } - trace_bpf_map_create(map, err); return err; free_map: @@ -484,6 +519,7 @@ free_map: free_map_sec: security_bpf_map_free(map); free_map_nouncharge: + btf_put(map->btf); map->ops->map_free(map); return err; } @@ -516,6 +552,7 @@ struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) atomic_inc(&map->usercnt); return map; } +EXPORT_SYMBOL_GPL(bpf_map_inc); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { @@ -635,7 +672,6 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; - trace_bpf_map_lookup_elem(map, ufd, key, value); err = 0; free_value: @@ -732,8 +768,6 @@ static int map_update_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_update_elem(map, ufd, key, value); free_value: kfree(value); free_key: @@ -786,8 +820,6 @@ static int map_delete_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_delete_elem(map, ufd, key); kfree(key); err_put: fdput(f); @@ -851,7 +883,6 @@ out: if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; - trace_bpf_map_next_key(map, ufd, key, next_key); err = 0; free_next_key: @@ -1005,7 +1036,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) if (atomic_dec_and_test(&prog->aux->refcnt)) { int i; - trace_bpf_prog_put_rcu(prog); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); @@ -1042,11 +1072,13 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "prog_id:\t%u\n", prog->type, prog->jited, prog_tag, - prog->pages * 1ULL << PAGE_SHIFT); + prog->pages * 1ULL << PAGE_SHIFT, + prog->aux->id); } #endif @@ -1172,11 +1204,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv); - - if (!IS_ERR(prog)) - trace_bpf_prog_get_type(prog); - return prog; + return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); @@ -1226,6 +1254,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: return 0; default: return -EINVAL; @@ -1351,7 +1381,6 @@ static int bpf_prog_load(union bpf_attr *attr) } bpf_prog_kallsyms_add(prog); - trace_bpf_prog_load(prog, err); return err; free_used_maps: @@ -1543,6 +1572,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1556,6 +1587,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); + case BPF_LIRC_MODE2: + return lirc_prog_attach(attr); default: return -EINVAL; } @@ -1613,6 +1646,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1626,6 +1661,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); + case BPF_LIRC_MODE2: + return lirc_prog_detach(attr); default: return -EINVAL; } @@ -1670,9 +1707,13 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: break; + case BPF_LIRC_MODE2: + return lirc_prog_query(attr, uattr); default: return -EINVAL; } @@ -1879,7 +1920,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, u32 ulen; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -1892,6 +1933,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); + info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); @@ -1912,6 +1954,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; info.xlated_prog_len = 0; + info.nr_jited_ksyms = 0; goto done; } @@ -1948,18 +1991,93 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, * for offload. */ ulen = info.jited_prog_len; - info.jited_prog_len = prog->jited_len; + if (prog->aux->func_cnt) { + u32 i; + + info.jited_prog_len = 0; + for (i = 0; i < prog->aux->func_cnt; i++) + info.jited_prog_len += prog->aux->func[i]->jited_len; + } else { + info.jited_prog_len = prog->jited_len; + } + if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok()) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); - if (copy_to_user(uinsns, prog->bpf_func, ulen)) - return -EFAULT; + + /* for multi-function programs, copy the JITed + * instructions for all the functions + */ + if (prog->aux->func_cnt) { + u32 len, free, i; + u8 *img; + + free = ulen; + for (i = 0; i < prog->aux->func_cnt; i++) { + len = prog->aux->func[i]->jited_len; + len = min_t(u32, len, free); + img = (u8 *) prog->aux->func[i]->bpf_func; + if (copy_to_user(uinsns, img, len)) + return -EFAULT; + uinsns += len; + free -= len; + if (!free) + break; + } + } else { + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } } else { info.jited_prog_insns = 0; } } + ulen = info.nr_jited_ksyms; + info.nr_jited_ksyms = prog->aux->func_cnt; + if (info.nr_jited_ksyms && ulen) { + if (bpf_dump_raw_ok()) { + u64 __user *user_ksyms; + ulong ksym_addr; + u32 i; + + /* copy the address of the kernel symbol + * corresponding to each function + */ + 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])) + return -EFAULT; + } + } else { + info.jited_ksyms = 0; + } + } + + ulen = info.nr_jited_func_lens; + info.nr_jited_func_lens = prog->aux->func_cnt; + if (info.nr_jited_func_lens && ulen) { + if (bpf_dump_raw_ok()) { + u32 __user *user_lens; + u32 func_len, i; + + /* 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])) + return -EFAULT; + } + } else { + info.jited_func_lens = 0; + } + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -1977,7 +2095,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, u32 info_len = attr->info.info_len; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -1990,6 +2108,12 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.map_flags = map->map_flags; memcpy(info.name, map->name, sizeof(map->name)); + if (map->btf) { + info.btf_id = btf_id(map->btf); + info.btf_key_type_id = map->btf_key_type_id; + info.btf_value_type_id = map->btf_value_type_id; + } + if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) @@ -2003,6 +2127,21 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, return 0; } +static int bpf_btf_get_info_by_fd(struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); + u32 info_len = attr->info.info_len; + int err; + + err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + if (err) + return err; + + return btf_get_info_by_fd(btf, attr, uattr); +} + #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, @@ -2025,6 +2164,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, else if (f.file->f_op == &bpf_map_fops) err = bpf_map_get_info_by_fd(f.file->private_data, attr, uattr); + else if (f.file->f_op == &btf_fops) + err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); else err = -EINVAL; @@ -2032,6 +2173,158 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } +#define BPF_BTF_LOAD_LAST_FIELD btf_log_level + +static int bpf_btf_load(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_LOAD)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_new_fd(attr); +} + +#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id + +static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_get_fd_by_id(attr->btf_id); +} + +static int bpf_task_fd_query_copy(const union bpf_attr *attr, + union bpf_attr __user *uattr, + u32 prog_id, u32 fd_type, + const char *buf, u64 probe_offset, + u64 probe_addr) +{ + char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); + u32 len = buf ? strlen(buf) : 0, input_len; + int err = 0; + + if (put_user(len, &uattr->task_fd_query.buf_len)) + return -EFAULT; + input_len = attr->task_fd_query.buf_len; + if (input_len && ubuf) { + if (!len) { + /* nothing to copy, just make ubuf NULL terminated */ + char zero = '\0'; + + if (put_user(zero, ubuf)) + return -EFAULT; + } else if (input_len >= len + 1) { + /* ubuf can hold the string with NULL terminator */ + if (copy_to_user(ubuf, buf, len + 1)) + return -EFAULT; + } else { + /* ubuf cannot hold the string with NULL terminator, + * do a partial copy with NULL terminator. + */ + char zero = '\0'; + + err = -ENOSPC; + if (copy_to_user(ubuf, buf, input_len - 1)) + return -EFAULT; + if (put_user(zero, ubuf + input_len - 1)) + return -EFAULT; + } + } + + if (put_user(prog_id, &uattr->task_fd_query.prog_id) || + put_user(fd_type, &uattr->task_fd_query.fd_type) || + put_user(probe_offset, &uattr->task_fd_query.probe_offset) || + put_user(probe_addr, &uattr->task_fd_query.probe_addr)) + return -EFAULT; + + return err; +} + +#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr + +static int bpf_task_fd_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + pid_t pid = attr->task_fd_query.pid; + u32 fd = attr->task_fd_query.fd; + const struct perf_event *event; + struct files_struct *files; + struct task_struct *task; + struct file *file; + int err; + + if (CHECK_ATTR(BPF_TASK_FD_QUERY)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->task_fd_query.flags != 0) + return -EINVAL; + + task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + if (!task) + return -ENOENT; + + files = get_files_struct(task); + put_task_struct(task); + if (!files) + return -ENOENT; + + err = 0; + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (!file) + err = -EBADF; + else + get_file(file); + spin_unlock(&files->file_lock); + put_files_struct(files); + + if (err) + goto out; + + if (file->f_op == &bpf_raw_tp_fops) { + struct bpf_raw_tracepoint *raw_tp = file->private_data; + struct bpf_raw_event_map *btp = raw_tp->btp; + + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + + event = perf_get_event(file); + if (!IS_ERR(event)) { + u64 probe_offset, probe_addr; + u32 prog_id, fd_type; + const char *buf; + + err = bpf_get_perf_event_info(event, &prog_id, &fd_type, + &buf, &probe_offset, + &probe_addr); + if (!err) + err = bpf_task_fd_query_copy(attr, uattr, prog_id, + fd_type, buf, + probe_offset, + probe_addr); + goto put_file; + } + + err = -ENOTSUPP; +put_file: + fput(file); +out: + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2040,7 +2333,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; - err = check_uarg_tail_zero(uattr, sizeof(attr), size); + err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); @@ -2112,6 +2405,15 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; + case BPF_BTF_LOAD: + err = bpf_btf_load(&attr); + break; + case BPF_BTF_GET_FD_BY_ID: + err = bpf_btf_get_fd_by_id(&attr); + break; + case BPF_TASK_FD_QUERY: + err = bpf_task_fd_query(&attr, uattr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 1f4bf68c12db..938d41211be7 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -43,6 +43,16 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } +struct tnum tnum_arshift(struct tnum a, u8 min_shift) +{ + /* if a.value is negative, arithmetic shifting by minimum shift + * will have larger negative offset compared to more shifting. + * If a.value is nonnegative, arithmetic shifting by minimum shift + * will have larger positive offset compare to more shifting. + */ + return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); +} + struct tnum tnum_add(struct tnum a, struct tnum b) { u64 sm, sv, sigma, chi, mu; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1904e814f282..d6403b5166f4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -22,6 +22,7 @@ #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> +#include <linux/perf_event.h> #include "disasm.h" @@ -186,6 +187,8 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; + s64 msize_smax_value; + u64 msize_umax_value; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -760,18 +763,19 @@ enum reg_arg_type { static int cmp_subprogs(const void *a, const void *b) { - return *(int *)a - *(int *)b; + return ((struct bpf_subprog_info *)a)->start - + ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { - u32 *p; + struct bpf_subprog_info *p; - p = bsearch(&off, env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs); + p = bsearch(&off, env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; - return p - env->subprog_starts; + return p - env->subprog_info; } @@ -791,18 +795,24 @@ static int add_subprog(struct bpf_verifier_env *env, int off) verbose(env, "too many subprograms\n"); return -E2BIG; } - env->subprog_starts[env->subprog_cnt++] = off; - sort(env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs, NULL); + env->subprog_info[env->subprog_cnt++].start = off; + sort(env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; + /* Add entry function. */ + ret = add_subprog(env, 0); + if (ret < 0) + return ret; + /* determine subprog starts. The end is one before the next starts */ for (i = 0; i < insn_cnt; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) @@ -822,16 +832,18 @@ static int check_subprogs(struct bpf_verifier_env *env) return ret; } + /* Add a fake 'exit' subprog which could simplify subprog iteration + * logic. 'subprog_cnt' should not be increased. + */ + subprog[env->subprog_cnt].start = insn_cnt; + if (env->log.level > 1) for (i = 0; i < env->subprog_cnt; i++) - verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]); + verbose(env, "func#%d @%d\n", i, subprog[i].start); /* now check that all jumps are within the same subprog */ - subprog_start = 0; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + subprog_start = subprog[cur_subprog].start; + subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; @@ -856,10 +868,9 @@ next: return -EINVAL; } subprog_start = subprog_end; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + cur_subprog++; + if (cur_subprog < env->subprog_cnt) + subprog_end = subprog[cur_subprog + 1].start; } } return 0; @@ -1298,6 +1309,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, switch (env->prog->type) { case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: /* dst_input() and dst_output() can't write for now */ if (t == BPF_WRITE) return false; @@ -1517,13 +1529,13 @@ static int update_stack_depth(struct bpf_verifier_env *env, const struct bpf_func_state *func, int off) { - u16 stack = env->subprog_stack_depth[func->subprogno]; + u16 stack = env->subprog_info[func->subprogno].stack_depth; if (stack >= -off) return 0; /* update known max for given subprogram */ - env->subprog_stack_depth[func->subprogno] = -off; + env->subprog_info[func->subprogno].stack_depth = -off; return 0; } @@ -1535,9 +1547,9 @@ static int update_stack_depth(struct bpf_verifier_env *env, */ static int check_max_stack_depth(struct bpf_verifier_env *env) { - int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end; + int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; @@ -1545,17 +1557,14 @@ process_func: /* round up to 32-bytes, since this is granularity * of interpreter stack size */ - depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: - if (env->subprog_cnt == subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[subprog]; + subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) continue; @@ -1563,17 +1572,16 @@ continue_func: continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; - ret_prog[frame] = subprog; + ret_prog[frame] = idx; /* find the callee */ i = i + insn[i].imm + 1; - subprog = find_subprog(env, i); - if (subprog < 0) { + idx = find_subprog(env, i); + if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i); return -EFAULT; } - subprog++; frame++; if (frame >= MAX_CALL_FRAMES) { WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); @@ -1586,10 +1594,10 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); frame--; i = ret_insn[frame]; - subprog = ret_prog[frame]; + idx = ret_prog[frame]; goto continue_func; } @@ -1605,8 +1613,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, start); return -EFAULT; } - subprog++; - return env->subprog_stack_depth[subprog]; + return env->subprog_info[subprog].stack_depth; } #endif @@ -1961,7 +1968,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && + if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || @@ -2013,14 +2020,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->key_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->key_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->key_size, false, + NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -2030,17 +2032,18 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->value_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->value_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->value_size, false, + NULL); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); + /* remember the mem_size which may be used later + * to refine return values. + */ + meta->msize_smax_value = reg->smax_value; + meta->msize_umax_value = reg->umax_value; + /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ @@ -2118,8 +2121,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; - /* Restrict bpf side of cpumap, open when use-cases appear */ + /* Restrict bpf side of cpumap and xskmap, open when use-cases + * appear. + */ case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; @@ -2135,6 +2141,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_msg_redirect_map) goto error; break; + case BPF_MAP_TYPE_SOCKHASH: + if (func_id != BPF_FUNC_sk_redirect_hash && + func_id != BPF_FUNC_sock_hash_update && + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_msg_redirect_hash) + goto error; + break; default: break; } @@ -2144,7 +2157,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; - if (env->subprog_cnt) { + if (env->subprog_cnt > 1) { verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); return -EINVAL; } @@ -2166,16 +2179,20 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && - map->map_type != BPF_MAP_TYPE_CPUMAP) + map->map_type != BPF_MAP_TYPE_CPUMAP && + map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: + case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; - case BPF_FUNC_sock_map_update: - if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + case BPF_FUNC_sk_redirect_hash: + case BPF_FUNC_msg_redirect_hash: + case BPF_FUNC_sock_hash_update: + if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; default: @@ -2316,7 +2333,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* remember the callsite, it will be used by bpf_exit */ *insn_idx /* callsite */, state->curframe + 1 /* frameno within this callchain */, - subprog + 1 /* subprog number within this prog */); + subprog /* subprog number within this prog */); /* copy r1 - r5 args that callee can access */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) @@ -2380,6 +2397,23 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } +static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; + + if (ret_type != RET_INTEGER || + (func_id != BPF_FUNC_get_stack && + func_id != BPF_FUNC_probe_read_str)) + return; + + ret_reg->smax_value = meta->msize_smax_value; + ret_reg->umax_value = meta->msize_umax_value; + __reg_deduce_bounds(ret_reg); + __reg_bound_offset(ret_reg); +} + static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) @@ -2387,8 +2421,11 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; if (func_id != BPF_FUNC_tail_call && - func_id != BPF_FUNC_map_lookup_elem) + func_id != BPF_FUNC_map_lookup_elem && + func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return 0; + if (meta->map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; @@ -2428,7 +2465,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose(env, "cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } @@ -2516,10 +2553,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; + if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) { + const char *err_str; + +#ifdef CONFIG_PERF_EVENTS + err = get_callchain_buffers(sysctl_perf_event_max_stack); + err_str = "cannot get callchain buffer for func %s#%d\n"; +#else + err = -ENOTSUPP; + err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; +#endif + if (err) { + verbose(env, err_str, func_id_name(func_id), func_id); + return err; + } + + env->prog->has_callchain_buf = true; + } + if (changes_data) clear_all_pkt_pointers(env); return 0; @@ -2964,10 +3021,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } - if (src_known) - dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); - else - dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; @@ -2995,16 +3049,35 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; - if (src_known) - dst_reg->var_off = tnum_rshift(dst_reg->var_off, - umin_val); - else - dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; + case BPF_ARSH: + if (umax_val >= insn_bitness) { + /* Shifts greater than 31 or 63 are undefined. + * This includes shifts by a negative number. + */ + mark_reg_unknown(env, regs, insn->dst_reg); + break; + } + + /* Upon reaching here, src_known is true and + * umax_val is equal to umin_val. + */ + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + __update_reg_bounds(dst_reg); + break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; @@ -3888,7 +3961,12 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (env->subprog_cnt) { + if (!env->ops->gen_ld_abs) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (env->subprog_cnt > 1) { /* when program has LD_ABS insn JITs and interpreter assume * that r1 == ctx == skb which is not the case for callees * that can have arbitrary arguments. It's problematic @@ -4919,15 +4997,15 @@ process_bpf_exit: verbose(env, "processed %d insns (limit %d), stack depth ", insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); - for (i = 0; i < env->subprog_cnt + 1; i++) { - u32 depth = env->subprog_stack_depth[i]; + for (i = 0; i < env->subprog_cnt; i++) { + u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); - if (i + 1 < env->subprog_cnt + 1) + if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); - env->prog->aux->stack_depth = env->subprog_stack_depth[0]; + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -5051,7 +5129,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_bpf_prog_info() + * and all maps are released in free_used_maps() */ map = bpf_map_inc(map, false); if (IS_ERR(map)) { @@ -5133,10 +5211,11 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len if (len == 1) return; - for (i = 0; i < env->subprog_cnt; i++) { - if (env->subprog_starts[i] < off) + /* NOTE: fake 'exit' subprog should be updated as well. */ + for (i = 0; i <= env->subprog_cnt; i++) { + if (env->subprog_info[i].start < off) continue; - env->subprog_starts[i] += len - 1; + env->subprog_info[i].start += len - 1; } } @@ -5210,7 +5289,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access) + if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; @@ -5270,6 +5349,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) */ is_narrower_load = size < ctx_field_size; if (is_narrower_load) { + u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); u32 off = insn->off; u8 size_code; @@ -5284,7 +5364,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else if (ctx_field_size == 8) size_code = BPF_DW; - insn->off = off & ~(ctx_field_size - 1); + insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } @@ -5328,7 +5408,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) void *old_bpf_func; int err = -ENOMEM; - if (env->subprog_cnt == 0) + if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5344,7 +5424,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ - insn->off = subprog + 1; + insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ @@ -5353,16 +5433,13 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->imm = 1; } - func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL); + func = kzalloc(sizeof(prog) * env->subprog_cnt, GFP_KERNEL); if (!func) return -ENOMEM; - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; - if (env->subprog_cnt == i) - subprog_end = prog->len; - else - subprog_end = env->subprog_starts[i]; + subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER); @@ -5379,7 +5456,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; - func[i]->aux->stack_depth = env->subprog_stack_depth[i]; + func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { @@ -5392,20 +5469,33 @@ static int jit_subprogs(struct bpf_verifier_env *env) * now populate all bpf_calls with correct addresses and * run last pass of JIT */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; subprog = insn->off; - insn->off = 0; insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) func[subprog]->bpf_func - __bpf_call_base; } + + /* we use the aux data to keep a list of the start addresses + * of the JITed images for each function in the program + * + * for some architectures, such as powerpc64, the imm field + * might not be large enough to hold the offset of the start + * address of the callee's JITed image from __bpf_call_base + * + * in such cases, we can lookup the start address of a callee + * by using its subprog id, available from the off field of + * the call instruction, as an index for this list + */ + func[i]->aux->func = func; + func[i]->aux->func_cnt = env->subprog_cnt; } - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { @@ -5419,7 +5509,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* finally lock prog and jit images for all functions and * populate kallsysm */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } @@ -5429,26 +5519,21 @@ static int jit_subprogs(struct bpf_verifier_env *env) * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - unsigned long addr; - if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); - addr = (unsigned long)func[subprog + 1]->bpf_func; - addr &= PAGE_MASK; - insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) - addr - __bpf_call_base; + insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; - prog->aux->func_cnt = env->subprog_cnt + 1; + prog->aux->func_cnt = env->subprog_cnt; return 0; out_free: - for (i = 0; i <= env->subprog_cnt; i++) + for (i = 0; i < env->subprog_cnt; i++) if (func[i]) bpf_jit_free(func[i]); kfree(func); @@ -5505,6 +5590,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; + const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; @@ -5552,6 +5638,25 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (BPF_CLASS(insn->code) == BPF_LD && + (BPF_MODE(insn->code) == BPF_ABS || + BPF_MODE(insn->code) == BPF_IND)) { + cnt = env->ops->gen_ld_abs(insn, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) @@ -5615,35 +5720,61 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup - * handlers are currently limited to 64 bit only. + * and other inlining handlers are currently limited to 64 bit + * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && - insn->imm == BPF_FUNC_map_lookup_elem) { + (insn->imm == BPF_FUNC_map_lookup_elem || + insn->imm == BPF_FUNC_map_update_elem || + insn->imm == BPF_FUNC_map_delete_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = BPF_MAP_PTR(aux->map_state); - if (!map_ptr->ops->map_gen_lookup) - goto patch_call_imm; + ops = map_ptr->ops; + if (insn->imm == BPF_FUNC_map_lookup_elem && + ops->map_gen_lookup) { + cnt = ops->map_gen_lookup(map_ptr, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; - } + new_prog = bpf_patch_insn_data(env, i + delta, + insn_buf, cnt); + if (!new_prog) + return -ENOMEM; - new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, - cnt); - if (!new_prog) - return -ENOMEM; + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } - delta += cnt - 1; + BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_delete_elem, + (int (*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_update_elem, + (int (*)(struct bpf_map *map, void *key, void *value, + u64 flags))NULL)); + switch (insn->imm) { + case BPF_FUNC_map_lookup_elem: + insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_update_elem: + insn->imm = BPF_CAST_CALL(ops->map_update_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_delete_elem: + insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - + __bpf_call_base; + continue; + } - /* keep walking new program and skip insns we just inserted */ - env->prog = prog = new_prog; - insn = new_prog->insnsi + i + delta; - continue; + goto patch_call_imm; } if (insn->imm == BPF_FUNC_redirect_map) { @@ -5755,16 +5886,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + ret = replace_map_fd_with_map_ptr(env); + if (ret < 0) + goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env); if (ret) - goto err_unlock; + goto skip_full_check; } - ret = replace_map_fd_with_map_ptr(env); - if (ret < 0) - goto skip_full_check; - env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -5835,7 +5966,7 @@ skip_full_check: err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release - * them now. Otherwise free_bpf_prog_info() will release them. + * them now. Otherwise free_used_maps() will release them. */ release_maps(env); *prog = env->prog; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c new file mode 100644 index 000000000000..b3c557476a8d --- /dev/null +++ b/kernel/bpf/xskmap.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XSKMAP used for AF_XDP sockets + * Copyright(c) 2018 Intel Corporation. + */ + +#include <linux/bpf.h> +#include <linux/capability.h> +#include <net/xdp_sock.h> +#include <linux/slab.h> +#include <linux/sched.h> + +struct xsk_map { + struct bpf_map map; + struct xdp_sock **xsk_map; + struct list_head __percpu *flush_list; +}; + +static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) +{ + int cpu, err = -EINVAL; + struct xsk_map *m; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || + attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) + return ERR_PTR(-EINVAL); + + m = kzalloc(sizeof(*m), GFP_USER); + if (!m) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&m->map, attr); + + cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); + cost += sizeof(struct list_head) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_m; + + m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + err = bpf_map_precharge_memlock(m->map.pages); + if (err) + goto free_m; + + err = -ENOMEM; + + m->flush_list = alloc_percpu(struct list_head); + if (!m->flush_list) + goto free_m; + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); + + m->xsk_map = bpf_map_area_alloc(m->map.max_entries * + sizeof(struct xdp_sock *), + m->map.numa_node); + if (!m->xsk_map) + goto free_percpu; + return &m->map; + +free_percpu: + free_percpu(m->flush_list); +free_m: + kfree(m); + return ERR_PTR(err); +} + +static void xsk_map_free(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + int i; + + synchronize_net(); + + for (i = 0; i < map->max_entries; i++) { + struct xdp_sock *xs; + + xs = m->xsk_map[i]; + if (!xs) + continue; + + sock_put((struct sock *)xs); + } + + free_percpu(m->flush_list); + bpf_map_area_free(m->xsk_map); + kfree(m); +} + +static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= m->map.max_entries) { + *next = 0; + return 0; + } + + if (index == m->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs; + + if (key >= map->max_entries) + return NULL; + + xs = READ_ONCE(m->xsk_map[key]); + return xs; +} + +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + int err; + + err = xsk_rcv(xs, xdp); + if (err) + return err; + + if (!xs->flush_node.prev) + list_add(&xs->flush_node, flush_list); + + return 0; +} + +void __xsk_map_flush(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct xdp_sock *xs, *tmp; + + list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { + xsk_flush(xs); + __list_del(xs->flush_node.prev, xs->flush_node.next); + xs->flush_node.prev = NULL; + } +} + +static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 i = *(u32 *)key, fd = *(u32 *)value; + struct xdp_sock *xs, *old_xs; + struct socket *sock; + int err; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(i >= m->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + sock = sockfd_lookup(fd, &err); + if (!sock) + return err; + + if (sock->sk->sk_family != PF_XDP) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + xs = (struct xdp_sock *)sock->sk; + + if (!xsk_is_setup_for_bpf_map(xs)) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + sock_hold(sock->sk); + + old_xs = xchg(&m->xsk_map[i], xs); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + sockfd_put(sock); + return 0; +} + +static int xsk_map_delete_elem(struct bpf_map *map, void *key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *old_xs; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + old_xs = xchg(&m->xsk_map[k], NULL); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + return 0; +} + +const struct bpf_map_ops xsk_map_ops = { + .map_alloc = xsk_map_alloc, + .map_free = xsk_map_free, + .map_get_next_key = xsk_map_get_next_key, + .map_lookup_elem = xsk_map_lookup_elem, + .map_update_elem = xsk_map_update_elem, + .map_delete_elem = xsk_map_delete_elem, +}; + + diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index 2be89a003185..bfcdae896122 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := cgroup.o stat.o namespace.o cgroup-v1.o +obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o obj-$(CONFIG_CGROUP_FREEZER) += freezer.o obj-$(CONFIG_CGROUP_PIDS) += pids.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 0808a33d16d3..77ff1cd6a252 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -201,13 +201,12 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, int cgroup_task_count(const struct cgroup *cgrp); /* - * stat.c + * rstat.c */ -void cgroup_stat_flush(struct cgroup *cgrp); -int cgroup_stat_init(struct cgroup *cgrp); -void cgroup_stat_exit(struct cgroup *cgrp); -void cgroup_stat_show_cputime(struct seq_file *seq); -void cgroup_stat_boot(void); +int cgroup_rstat_init(struct cgroup *cgrp); +void cgroup_rstat_exit(struct cgroup *cgrp); +void cgroup_rstat_boot(void); +void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 12883656e63e..077370bf8964 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -54,6 +54,7 @@ #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> +#include <linux/sched/cputime.h> #include <net/sock.h> #define CREATE_TRACE_POINTS @@ -61,6 +62,8 @@ #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) +/* let's not notify more than 100 times per second */ +#define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * cgroup_mutex is the master lock. Any modification to cgroup or its @@ -142,14 +145,14 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = { }; #undef SUBSYS -static DEFINE_PER_CPU(struct cgroup_cpu_stat, cgrp_dfl_root_cpu_stat); +static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* * The default hierarchy, reserved for the subsystems that are otherwise * unattached - it never has more than a single cgroup, and all tasks are * part of that cgroup. */ -struct cgroup_root cgrp_dfl_root = { .cgrp.cpu_stat = &cgrp_dfl_root_cpu_stat }; +struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* @@ -1554,6 +1557,8 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); + + del_timer_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); @@ -1573,8 +1578,17 @@ static void css_clear_dir(struct cgroup_subsys_state *css) css->flags &= ~CSS_VISIBLE; - list_for_each_entry(cfts, &css->ss->cfts, node) + if (!css->ss) { + if (cgroup_on_dfl(cgrp)) + cfts = cgroup_base_files; + else + cfts = cgroup1_base_files; + cgroup_addrm_files(css, cgrp, cfts, false); + } else { + list_for_each_entry(cfts, &css->ss->cfts, node) + cgroup_addrm_files(css, cgrp, cfts, false); + } } /** @@ -1598,14 +1612,16 @@ static int css_populate_dir(struct cgroup_subsys_state *css) else cfts = cgroup1_base_files; - return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true); - } - - list_for_each_entry(cfts, &css->ss->cfts, node) { - ret = cgroup_addrm_files(css, cgrp, cfts, true); - if (ret < 0) { - failed_cfts = cfts; - goto err; + ret = cgroup_addrm_files(&cgrp->self, cgrp, cfts, true); + if (ret < 0) + return ret; + } else { + list_for_each_entry(cfts, &css->ss->cfts, node) { + ret = cgroup_addrm_files(css, cgrp, cfts, true); + if (ret < 0) { + failed_cfts = cfts; + goto err; + } } } @@ -1782,13 +1798,6 @@ static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; - spin_lock_irq(&css_set_lock); - - if (use_task_css_set_links) - goto out_unlock; - - use_task_css_set_links = true; - /* * We need tasklist_lock because RCU is not safe against * while_each_thread(). Besides, a forking task that has passed @@ -1797,6 +1806,13 @@ static void cgroup_enable_task_cg_lists(void) * tasklist if we walk through it with RCU. */ read_lock(&tasklist_lock); + spin_lock_irq(&css_set_lock); + + if (use_task_css_set_links) + goto out_unlock; + + use_task_css_set_links = true; + do_each_thread(g, p) { WARN_ON_ONCE(!list_empty(&p->cg_list) || task_css_set(p) != &init_css_set); @@ -1824,9 +1840,9 @@ static void cgroup_enable_task_cg_lists(void) } spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); - read_unlock(&tasklist_lock); out_unlock: spin_unlock_irq(&css_set_lock); + read_unlock(&tasklist_lock); } static void init_cgroup_housekeeping(struct cgroup *cgrp) @@ -1844,6 +1860,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; + INIT_LIST_HEAD(&cgrp->rstat_css_list); + prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); @@ -3381,7 +3399,7 @@ static int cpu_stat_show(struct seq_file *seq, void *v) struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; - cgroup_stat_show_cputime(seq); + cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id); #endif @@ -3521,6 +3539,12 @@ static int cgroup_kn_set_ugid(struct kernfs_node *kn) return kernfs_setattr(kn, &iattr); } +static void cgroup_file_notify_timer(struct timer_list *timer) +{ + cgroup_file_notify(container_of(timer, struct cgroup_file, + notify_timer)); +} + static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { @@ -3547,6 +3571,8 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; + timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); + spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); @@ -3796,8 +3822,17 @@ void cgroup_file_notify(struct cgroup_file *cfile) unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); - if (cfile->kn) - kernfs_notify(cfile->kn); + if (cfile->kn) { + unsigned long last = cfile->notified_at; + unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; + + if (time_in_range(jiffies, last, next)) { + timer_reduce(&cfile->notify_timer, next); + } else { + kernfs_notify(cfile->kn); + cfile->notified_at = jiffies; + } + } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } @@ -4560,7 +4595,7 @@ static void css_free_rwork_fn(struct work_struct *work) cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); if (cgroup_on_dfl(cgrp)) - cgroup_stat_exit(cgrp); + cgroup_rstat_exit(cgrp); kfree(cgrp); } else { /* @@ -4587,6 +4622,11 @@ static void css_release_work_fn(struct work_struct *work) if (ss) { /* css release path */ + if (!list_empty(&css->rstat_css_node)) { + cgroup_rstat_flush(cgrp); + list_del_rcu(&css->rstat_css_node); + } + cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); @@ -4597,7 +4637,7 @@ static void css_release_work_fn(struct work_struct *work) trace_cgroup_release(cgrp); if (cgroup_on_dfl(cgrp)) - cgroup_stat_flush(cgrp); + cgroup_rstat_flush(cgrp); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) @@ -4648,6 +4688,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); + INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); @@ -4656,6 +4697,9 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css_get(css->parent); } + if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush) + list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); + BUG_ON(cgroup_css(cgrp, ss)); } @@ -4757,6 +4801,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err_list_del: list_del_rcu(&css->sibling); err_free_css: + list_del_rcu(&css->rstat_css_node); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); @@ -4775,8 +4820,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ - cgrp = kzalloc(sizeof(*cgrp) + - sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL); + cgrp = kzalloc(struct_size(cgrp, ancestor_ids, (level + 1)), + GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); @@ -4785,7 +4830,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) goto out_free_cgrp; if (cgroup_on_dfl(parent)) { - ret = cgroup_stat_init(cgrp); + ret = cgroup_rstat_init(cgrp); if (ret) goto out_cancel_ref; } @@ -4850,7 +4895,7 @@ out_idr_free: cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_stat_exit: if (cgroup_on_dfl(parent)) - cgroup_stat_exit(cgrp); + cgroup_rstat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5090,10 +5135,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) for_each_css(css, ssid, cgrp) kill_css(css); - /* - * Remove @cgrp directory along with the base files. @cgrp has an - * extra ref on its kn. - */ + /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ + css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (parent && cgroup_is_threaded(cgrp)) @@ -5245,7 +5288,7 @@ int __init cgroup_init(void) BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); - cgroup_stat_boot(); + cgroup_rstat_boot(); /* * The latency of the synchronize_sched() is too high for cgroups, diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index defad3c5e7dc..d3bbb757ee49 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -362,35 +362,32 @@ EXPORT_SYMBOL(rdmacg_unregister_device); static int parse_resource(char *c, int *intval) { substring_t argstr; - const char **table = &rdmacg_resource_names[0]; char *name, *value = c; size_t len; - int ret, i = 0; + int ret, i; name = strsep(&value, "="); if (!name || !value) return -EINVAL; - len = strlen(value); + i = match_string(rdmacg_resource_names, RDMACG_RESOURCE_MAX, name); + if (i < 0) + return i; - for (i = 0; i < RDMACG_RESOURCE_MAX; i++) { - if (strcmp(table[i], name)) - continue; + len = strlen(value); - argstr.from = value; - argstr.to = value + len; + argstr.from = value; + argstr.to = value + len; - ret = match_int(&argstr, intval); - if (ret >= 0) { - if (*intval < 0) - break; - return i; - } - if (strncmp(value, RDMACG_MAX_STR, len) == 0) { - *intval = S32_MAX; - return i; - } - break; + ret = match_int(&argstr, intval); + if (ret >= 0) { + if (*intval < 0) + return -EINVAL; + return i; + } + if (strncmp(value, RDMACG_MAX_STR, len) == 0) { + *intval = S32_MAX; + return i; } return -EINVAL; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c new file mode 100644 index 000000000000..d503d1a9007c --- /dev/null +++ b/kernel/cgroup/rstat.c @@ -0,0 +1,416 @@ +#include "cgroup-internal.h" + +#include <linux/sched/cputime.h> + +static DEFINE_SPINLOCK(cgroup_rstat_lock); +static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); + +static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); + +static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) +{ + return per_cpu_ptr(cgrp->rstat_cpu, cpu); +} + +/** + * cgroup_rstat_updated - keep track of updated rstat_cpu + * @cgrp: target cgroup + * @cpu: cpu on which rstat_cpu was updated + * + * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching + * rstat_cpu->updated_children list. See the comment on top of + * cgroup_rstat_cpu definition for details. + */ +void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) +{ + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); + struct cgroup *parent; + unsigned long flags; + + /* nothing to do for root */ + if (!cgroup_parent(cgrp)) + return; + + /* + * Paired with the one in cgroup_rstat_cpu_pop_upated(). Either we + * see NULL updated_next or they see our updated stat. + */ + smp_mb(); + + /* + * Because @parent's updated_children is terminated with @parent + * instead of NULL, we can tell whether @cgrp is on the list by + * testing the next pointer for NULL. + */ + if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) + return; + + raw_spin_lock_irqsave(cpu_lock, flags); + + /* put @cgrp and all ancestors on the corresponding updated lists */ + for (parent = cgroup_parent(cgrp); parent; + cgrp = parent, parent = cgroup_parent(cgrp)) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); + + /* + * Both additions and removals are bottom-up. If a cgroup + * is already in the tree, all ancestors are. + */ + if (rstatc->updated_next) + break; + + rstatc->updated_next = prstatc->updated_children; + prstatc->updated_children = cgrp; + } + + raw_spin_unlock_irqrestore(cpu_lock, flags); +} +EXPORT_SYMBOL_GPL(cgroup_rstat_updated); + +/** + * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree + * @pos: current position + * @root: root of the tree to traversal + * @cpu: target cpu + * + * Walks the udpated 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. + * + * The only ordering guarantee is that, for a parent and a child pair + * covered by a given traversal, if a child is visited, its parent is + * guaranteed to be visited afterwards. + */ +static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, + struct cgroup *root, int cpu) +{ + struct cgroup_rstat_cpu *rstatc; + struct cgroup *parent; + + if (pos == root) + return NULL; + + /* + * We're gonna walk down to the first leaf and visit/remove it. We + * can pick whatever unvisited node as the starting point. + */ + if (!pos) + pos = root; + else + pos = cgroup_parent(pos); + + /* walk down to the first leaf */ + while (true) { + rstatc = cgroup_rstat_cpu(pos, cpu); + if (rstatc->updated_children == pos) + break; + pos = rstatc->updated_children; + } + + /* + * Unlink @pos from the tree. As the updated_children list is + * singly linked, we have to walk it to find the removal point. + * However, due to the way we traverse, @pos will be the first + * child in most cases. The only exception is @root. + */ + parent = cgroup_parent(pos); + if (parent && rstatc->updated_next) { + struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); + struct cgroup_rstat_cpu *nrstatc; + struct cgroup **nextp; + + nextp = &prstatc->updated_children; + while (true) { + nrstatc = cgroup_rstat_cpu(*nextp, cpu); + if (*nextp == pos) + break; + + WARN_ON_ONCE(*nextp == parent); + nextp = &nrstatc->updated_next; + } + + *nextp = rstatc->updated_next; + rstatc->updated_next = NULL; + + /* + * Paired with the one in cgroup_rstat_cpu_updated(). + * Either they see NULL updated_next or we see their + * updated stat. + */ + smp_mb(); + } + + return pos; +} + +/* see cgroup_rstat_flush() */ +static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) + __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) +{ + int cpu; + + lockdep_assert_held(&cgroup_rstat_lock); + + for_each_possible_cpu(cpu) { + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, + cpu); + struct cgroup *pos = NULL; + + raw_spin_lock(cpu_lock); + while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + struct cgroup_subsys_state *css; + + cgroup_base_stat_flush(pos, cpu); + + rcu_read_lock(); + list_for_each_entry_rcu(css, &pos->rstat_css_list, + rstat_css_node) + css->ss->css_rstat_flush(css, cpu); + rcu_read_unlock(); + } + raw_spin_unlock(cpu_lock); + + /* if @may_sleep, play nice and yield if necessary */ + if (may_sleep && (need_resched() || + spin_needbreak(&cgroup_rstat_lock))) { + spin_unlock_irq(&cgroup_rstat_lock); + if (!cond_resched()) + cpu_relax(); + spin_lock_irq(&cgroup_rstat_lock); + } + } +} + +/** + * cgroup_rstat_flush - flush stats in @cgrp's subtree + * @cgrp: target cgroup + * + * Collect all per-cpu stats in @cgrp's subtree into the global counters + * and propagate them upwards. After this function returns, all cgroups in + * the subtree have up-to-date ->stat. + * + * This also gets all cgroups in the subtree including @cgrp off the + * ->updated_children lists. + * + * This function may block. + */ +void cgroup_rstat_flush(struct cgroup *cgrp) +{ + might_sleep(); + + spin_lock_irq(&cgroup_rstat_lock); + cgroup_rstat_flush_locked(cgrp, true); + spin_unlock_irq(&cgroup_rstat_lock); +} + +/** + * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() + * @cgrp: target cgroup + * + * This function can be called from any context. + */ +void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_rstat_lock, flags); + cgroup_rstat_flush_locked(cgrp, false); + spin_unlock_irqrestore(&cgroup_rstat_lock, flags); +} + +/** + * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold + * @cgrp: target cgroup + * + * Flush stats in @cgrp's subtree and prevent further flushes. Must be + * paired with cgroup_rstat_flush_release(). + * + * This function may block. + */ +void cgroup_rstat_flush_hold(struct cgroup *cgrp) + __acquires(&cgroup_rstat_lock) +{ + might_sleep(); + spin_lock_irq(&cgroup_rstat_lock); + cgroup_rstat_flush_locked(cgrp, true); +} + +/** + * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() + */ +void cgroup_rstat_flush_release(void) + __releases(&cgroup_rstat_lock) +{ + spin_unlock_irq(&cgroup_rstat_lock); +} + +int cgroup_rstat_init(struct cgroup *cgrp) +{ + int cpu; + + /* the root cgrp has rstat_cpu preallocated */ + if (!cgrp->rstat_cpu) { + cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); + if (!cgrp->rstat_cpu) + return -ENOMEM; + } + + /* ->updated_children list is self terminated */ + for_each_possible_cpu(cpu) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + + rstatc->updated_children = cgrp; + u64_stats_init(&rstatc->bsync); + } + + return 0; +} + +void cgroup_rstat_exit(struct cgroup *cgrp) +{ + int cpu; + + cgroup_rstat_flush(cgrp); + + /* sanity check */ + for_each_possible_cpu(cpu) { + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + + if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || + WARN_ON_ONCE(rstatc->updated_next)) + return; + } + + free_percpu(cgrp->rstat_cpu); + cgrp->rstat_cpu = NULL; +} + +void __init cgroup_rstat_boot(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); + + BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp)); +} + +/* + * Functions for cgroup basic resource statistics implemented on top of + * rstat. + */ +static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat, + struct cgroup_base_stat *src_bstat) +{ + dst_bstat->cputime.utime += src_bstat->cputime.utime; + dst_bstat->cputime.stime += src_bstat->cputime.stime; + dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; +} + +static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); + struct task_cputime *last_cputime = &rstatc->last_bstat.cputime; + struct task_cputime cputime; + struct cgroup_base_stat delta; + unsigned seq; + + /* fetch the current per-cpu values */ + do { + seq = __u64_stats_fetch_begin(&rstatc->bsync); + cputime = rstatc->bstat.cputime; + } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); + + /* calculate the delta to propgate */ + delta.cputime.utime = cputime.utime - last_cputime->utime; + delta.cputime.stime = cputime.stime - last_cputime->stime; + delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime - + last_cputime->sum_exec_runtime; + *last_cputime = cputime; + + /* transfer the pending stat into delta */ + cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat); + memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat)); + + /* propagate delta into the global stat and the parent's pending */ + cgroup_base_stat_accumulate(&cgrp->bstat, &delta); + if (parent) + cgroup_base_stat_accumulate(&parent->pending_bstat, &delta); +} + +static struct cgroup_rstat_cpu * +cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) +{ + struct cgroup_rstat_cpu *rstatc; + + rstatc = get_cpu_ptr(cgrp->rstat_cpu); + u64_stats_update_begin(&rstatc->bsync); + return rstatc; +} + +static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, + struct cgroup_rstat_cpu *rstatc) +{ + u64_stats_update_end(&rstatc->bsync); + cgroup_rstat_updated(cgrp, smp_processor_id()); + put_cpu_ptr(rstatc); +} + +void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) +{ + struct cgroup_rstat_cpu *rstatc; + + rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + rstatc->bstat.cputime.sum_exec_runtime += delta_exec; + cgroup_base_stat_cputime_account_end(cgrp, rstatc); +} + +void __cgroup_account_cputime_field(struct cgroup *cgrp, + enum cpu_usage_stat index, u64 delta_exec) +{ + struct cgroup_rstat_cpu *rstatc; + + rstatc = cgroup_base_stat_cputime_account_begin(cgrp); + + switch (index) { + case CPUTIME_USER: + case CPUTIME_NICE: + rstatc->bstat.cputime.utime += delta_exec; + break; + case CPUTIME_SYSTEM: + case CPUTIME_IRQ: + case CPUTIME_SOFTIRQ: + rstatc->bstat.cputime.stime += delta_exec; + break; + default: + break; + } + + cgroup_base_stat_cputime_account_end(cgrp, rstatc); +} + +void cgroup_base_stat_cputime_show(struct seq_file *seq) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + u64 usage, utime, stime; + + if (!cgroup_parent(cgrp)) + return; + + cgroup_rstat_flush_hold(cgrp); + usage = cgrp->bstat.cputime.sum_exec_runtime; + cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); + cgroup_rstat_flush_release(); + + do_div(usage, NSEC_PER_USEC); + do_div(utime, NSEC_PER_USEC); + do_div(stime, NSEC_PER_USEC); + + seq_printf(seq, "usage_usec %llu\n" + "user_usec %llu\n" + "system_usec %llu\n", + usage, utime, stime); +} diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c deleted file mode 100644 index 1e111dd455c4..000000000000 --- a/kernel/cgroup/stat.c +++ /dev/null @@ -1,338 +0,0 @@ -#include "cgroup-internal.h" - -#include <linux/sched/cputime.h> - -static DEFINE_MUTEX(cgroup_stat_mutex); -static DEFINE_PER_CPU(raw_spinlock_t, cgroup_cpu_stat_lock); - -static struct cgroup_cpu_stat *cgroup_cpu_stat(struct cgroup *cgrp, int cpu) -{ - return per_cpu_ptr(cgrp->cpu_stat, cpu); -} - -/** - * cgroup_cpu_stat_updated - keep track of updated cpu_stat - * @cgrp: target cgroup - * @cpu: cpu on which cpu_stat was updated - * - * @cgrp's cpu_stat on @cpu was updated. Put it on the parent's matching - * cpu_stat->updated_children list. See the comment on top of - * cgroup_cpu_stat definition for details. - */ -static void cgroup_cpu_stat_updated(struct cgroup *cgrp, int cpu) -{ - raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu); - struct cgroup *parent; - unsigned long flags; - - /* - * Speculative already-on-list test. This may race leading to - * temporary inaccuracies, which is fine. - * - * Because @parent's updated_children is terminated with @parent - * instead of NULL, we can tell whether @cgrp is on the list by - * testing the next pointer for NULL. - */ - if (cgroup_cpu_stat(cgrp, cpu)->updated_next) - return; - - raw_spin_lock_irqsave(cpu_lock, flags); - - /* put @cgrp and all ancestors on the corresponding updated lists */ - for (parent = cgroup_parent(cgrp); parent; - cgrp = parent, parent = cgroup_parent(cgrp)) { - struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); - struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu); - - /* - * Both additions and removals are bottom-up. If a cgroup - * is already in the tree, all ancestors are. - */ - if (cstat->updated_next) - break; - - cstat->updated_next = pcstat->updated_children; - pcstat->updated_children = cgrp; - } - - raw_spin_unlock_irqrestore(cpu_lock, flags); -} - -/** - * cgroup_cpu_stat_pop_updated - iterate and dismantle cpu_stat updated tree - * @pos: current position - * @root: root of the tree to traversal - * @cpu: target cpu - * - * Walks the udpated cpu_stat 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_cpu_stat_lock held. - * - * The only ordering guarantee is that, for a parent and a child pair - * covered by a given traversal, if a child is visited, its parent is - * guaranteed to be visited afterwards. - */ -static struct cgroup *cgroup_cpu_stat_pop_updated(struct cgroup *pos, - struct cgroup *root, int cpu) -{ - struct cgroup_cpu_stat *cstat; - struct cgroup *parent; - - if (pos == root) - return NULL; - - /* - * We're gonna walk down to the first leaf and visit/remove it. We - * can pick whatever unvisited node as the starting point. - */ - if (!pos) - pos = root; - else - pos = cgroup_parent(pos); - - /* walk down to the first leaf */ - while (true) { - cstat = cgroup_cpu_stat(pos, cpu); - if (cstat->updated_children == pos) - break; - pos = cstat->updated_children; - } - - /* - * Unlink @pos from the tree. As the updated_children list is - * singly linked, we have to walk it to find the removal point. - * However, due to the way we traverse, @pos will be the first - * child in most cases. The only exception is @root. - */ - parent = cgroup_parent(pos); - if (parent && cstat->updated_next) { - struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu); - struct cgroup_cpu_stat *ncstat; - struct cgroup **nextp; - - nextp = &pcstat->updated_children; - while (true) { - ncstat = cgroup_cpu_stat(*nextp, cpu); - if (*nextp == pos) - break; - - WARN_ON_ONCE(*nextp == parent); - nextp = &ncstat->updated_next; - } - - *nextp = cstat->updated_next; - cstat->updated_next = NULL; - } - - return pos; -} - -static void cgroup_stat_accumulate(struct cgroup_stat *dst_stat, - struct cgroup_stat *src_stat) -{ - dst_stat->cputime.utime += src_stat->cputime.utime; - dst_stat->cputime.stime += src_stat->cputime.stime; - dst_stat->cputime.sum_exec_runtime += src_stat->cputime.sum_exec_runtime; -} - -static void cgroup_cpu_stat_flush_one(struct cgroup *cgrp, int cpu) -{ - struct cgroup *parent = cgroup_parent(cgrp); - struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); - struct task_cputime *last_cputime = &cstat->last_cputime; - struct task_cputime cputime; - struct cgroup_stat delta; - unsigned seq; - - lockdep_assert_held(&cgroup_stat_mutex); - - /* fetch the current per-cpu values */ - do { - seq = __u64_stats_fetch_begin(&cstat->sync); - cputime = cstat->cputime; - } while (__u64_stats_fetch_retry(&cstat->sync, seq)); - - /* accumulate the deltas to propgate */ - delta.cputime.utime = cputime.utime - last_cputime->utime; - delta.cputime.stime = cputime.stime - last_cputime->stime; - delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime - - last_cputime->sum_exec_runtime; - *last_cputime = cputime; - - /* transfer the pending stat into delta */ - cgroup_stat_accumulate(&delta, &cgrp->pending_stat); - memset(&cgrp->pending_stat, 0, sizeof(cgrp->pending_stat)); - - /* propagate delta into the global stat and the parent's pending */ - cgroup_stat_accumulate(&cgrp->stat, &delta); - if (parent) - cgroup_stat_accumulate(&parent->pending_stat, &delta); -} - -/* see cgroup_stat_flush() */ -static void cgroup_stat_flush_locked(struct cgroup *cgrp) -{ - int cpu; - - lockdep_assert_held(&cgroup_stat_mutex); - - for_each_possible_cpu(cpu) { - raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu); - struct cgroup *pos = NULL; - - raw_spin_lock_irq(cpu_lock); - while ((pos = cgroup_cpu_stat_pop_updated(pos, cgrp, cpu))) - cgroup_cpu_stat_flush_one(pos, cpu); - raw_spin_unlock_irq(cpu_lock); - } -} - -/** - * cgroup_stat_flush - flush stats in @cgrp's subtree - * @cgrp: target cgroup - * - * Collect all per-cpu stats in @cgrp's subtree into the global counters - * and propagate them upwards. After this function returns, all cgroups in - * the subtree have up-to-date ->stat. - * - * This also gets all cgroups in the subtree including @cgrp off the - * ->updated_children lists. - */ -void cgroup_stat_flush(struct cgroup *cgrp) -{ - mutex_lock(&cgroup_stat_mutex); - cgroup_stat_flush_locked(cgrp); - mutex_unlock(&cgroup_stat_mutex); -} - -static struct cgroup_cpu_stat *cgroup_cpu_stat_account_begin(struct cgroup *cgrp) -{ - struct cgroup_cpu_stat *cstat; - - cstat = get_cpu_ptr(cgrp->cpu_stat); - u64_stats_update_begin(&cstat->sync); - return cstat; -} - -static void cgroup_cpu_stat_account_end(struct cgroup *cgrp, - struct cgroup_cpu_stat *cstat) -{ - u64_stats_update_end(&cstat->sync); - cgroup_cpu_stat_updated(cgrp, smp_processor_id()); - put_cpu_ptr(cstat); -} - -void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) -{ - struct cgroup_cpu_stat *cstat; - - cstat = cgroup_cpu_stat_account_begin(cgrp); - cstat->cputime.sum_exec_runtime += delta_exec; - cgroup_cpu_stat_account_end(cgrp, cstat); -} - -void __cgroup_account_cputime_field(struct cgroup *cgrp, - enum cpu_usage_stat index, u64 delta_exec) -{ - struct cgroup_cpu_stat *cstat; - - cstat = cgroup_cpu_stat_account_begin(cgrp); - - switch (index) { - case CPUTIME_USER: - case CPUTIME_NICE: - cstat->cputime.utime += delta_exec; - break; - case CPUTIME_SYSTEM: - case CPUTIME_IRQ: - case CPUTIME_SOFTIRQ: - cstat->cputime.stime += delta_exec; - break; - default: - break; - } - - cgroup_cpu_stat_account_end(cgrp, cstat); -} - -void cgroup_stat_show_cputime(struct seq_file *seq) -{ - struct cgroup *cgrp = seq_css(seq)->cgroup; - u64 usage, utime, stime; - - if (!cgroup_parent(cgrp)) - return; - - mutex_lock(&cgroup_stat_mutex); - - cgroup_stat_flush_locked(cgrp); - - usage = cgrp->stat.cputime.sum_exec_runtime; - cputime_adjust(&cgrp->stat.cputime, &cgrp->stat.prev_cputime, - &utime, &stime); - - mutex_unlock(&cgroup_stat_mutex); - - do_div(usage, NSEC_PER_USEC); - do_div(utime, NSEC_PER_USEC); - do_div(stime, NSEC_PER_USEC); - - seq_printf(seq, "usage_usec %llu\n" - "user_usec %llu\n" - "system_usec %llu\n", - usage, utime, stime); -} - -int cgroup_stat_init(struct cgroup *cgrp) -{ - int cpu; - - /* the root cgrp has cpu_stat preallocated */ - if (!cgrp->cpu_stat) { - cgrp->cpu_stat = alloc_percpu(struct cgroup_cpu_stat); - if (!cgrp->cpu_stat) - return -ENOMEM; - } - - /* ->updated_children list is self terminated */ - for_each_possible_cpu(cpu) { - struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); - - cstat->updated_children = cgrp; - u64_stats_init(&cstat->sync); - } - - prev_cputime_init(&cgrp->stat.prev_cputime); - - return 0; -} - -void cgroup_stat_exit(struct cgroup *cgrp) -{ - int cpu; - - cgroup_stat_flush(cgrp); - - /* sanity check */ - for_each_possible_cpu(cpu) { - struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); - - if (WARN_ON_ONCE(cstat->updated_children != cgrp) || - WARN_ON_ONCE(cstat->updated_next)) - return; - } - - free_percpu(cgrp->cpu_stat); - cgrp->cpu_stat = NULL; -} - -void __init cgroup_stat_boot(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - raw_spin_lock_init(per_cpu_ptr(&cgroup_cpu_stat_lock, cpu)); - - BUG_ON(cgroup_stat_init(&cgrp_dfl_root.cgrp)); -} diff --git a/kernel/crash_core.c b/kernel/crash_core.c index f7674d676889..b66aced5e8c2 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -460,6 +460,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_hwpoison); #endif VMCOREINFO_NUMBER(PG_head_mask); +#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); #ifdef CONFIG_HUGETLB_PAGE VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); diff --git a/kernel/events/core.c b/kernel/events/core.c index 08f5e1b42b43..80cca2b30c4f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11212,6 +11212,14 @@ struct file *perf_event_get(unsigned int fd) return file; } +const struct perf_event *perf_get_event(struct file *file) +{ + if (file->f_op != &perf_fops) + return ERR_PTR(-EINVAL); + + return file->private_data; +} + const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { if (!event) diff --git a/kernel/fork.c b/kernel/fork.c index a5d21c42acfc..c6d1c1ce9ed7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -899,6 +899,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pinned_vm = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); + spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); @@ -1712,7 +1713,7 @@ static __latent_entropy struct task_struct *copy_process( p->start_time = ktime_get_ns(); p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; - p->audit_context = NULL; + audit_set_context(p, NULL); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 751593ed7c0b..32b479468e4d 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -44,6 +44,7 @@ int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; static bool hung_task_show_lock; +static bool hung_task_call_panic; static struct task_struct *watchdog_task; @@ -127,10 +128,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) touch_nmi_watchdog(); if (sysctl_hung_task_panic) { - if (hung_task_show_lock) - debug_show_all_locks(); - trigger_all_cpu_backtrace(); - panic("hung_task: blocked tasks"); + hung_task_show_lock = true; + hung_task_call_panic = true; } } @@ -193,6 +192,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) rcu_read_unlock(); if (hung_task_show_lock) debug_show_all_locks(); + if (hung_task_call_panic) { + trigger_all_cpu_backtrace(); + panic("hung_task: blocked tasks"); + } } static long hung_timeout_jiffies(unsigned long last_checked, diff --git a/kernel/iomem.c b/kernel/iomem.c new file mode 100644 index 000000000000..f7525e14ebc6 --- /dev/null +++ b/kernel/iomem.c @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/device.h> +#include <linux/types.h> +#include <linux/io.h> +#include <linux/mm.h> + +#ifndef ioremap_cache +/* temporary while we convert existing ioremap_cache users to memremap */ +__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) +{ + return ioremap(offset, size); +} +#endif + +#ifndef arch_memremap_wb +static void *arch_memremap_wb(resource_size_t offset, unsigned long size) +{ + return (__force void *)ioremap_cache(offset, size); +} +#endif + +#ifndef arch_memremap_can_ram_remap +static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + return true; +} +#endif + +static void *try_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + /* In the simple case just return the existing linear address */ + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) && + arch_memremap_can_ram_remap(offset, size, flags)) + return __va(offset); + + return NULL; /* fallback to arch_memremap_wb */ +} + +/** + * memremap() - remap an iomem_resource as cacheable memory + * @offset: iomem resource start address + * @size: size of remap + * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC, + * MEMREMAP_ENC, MEMREMAP_DEC + * + * memremap() is "ioremap" for cases where it is known that the resource + * being mapped does not have i/o side effects and the __iomem + * annotation is not applicable. In the case of multiple flags, the different + * mapping types will be attempted in the order listed below until one of + * them succeeds. + * + * MEMREMAP_WB - matches the default mapping for System RAM on + * the architecture. This is usually a read-allocate write-back cache. + * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM + * memremap() will bypass establishing a new mapping and instead return + * a pointer into the direct map. + * + * MEMREMAP_WT - establish a mapping whereby writes either bypass the + * cache or are written through to memory and never exist in a + * cache-dirty state with respect to program visibility. Attempts to + * map System RAM with this mapping type will fail. + * + * MEMREMAP_WC - establish a writecombine mapping, whereby writes may + * be coalesced together (e.g. in the CPU's write buffers), but is otherwise + * uncached. Attempts to map System RAM with this mapping type will fail. + */ +void *memremap(resource_size_t offset, size_t size, unsigned long flags) +{ + int is_ram = region_intersects(offset, size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); + void *addr = NULL; + + if (!flags) + return NULL; + + if (is_ram == REGION_MIXED) { + WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", + &offset, (unsigned long) size); + return NULL; + } + + /* Try all mapping types requested until one returns non-NULL */ + if (flags & MEMREMAP_WB) { + /* + * MEMREMAP_WB is special in that it can be satisifed + * from the direct map. Some archs depend on the + * capability of memremap() to autodetect cases where + * the requested range is potentially in System RAM. + */ + if (is_ram == REGION_INTERSECTS) + addr = try_ram_remap(offset, size, flags); + if (!addr) + addr = arch_memremap_wb(offset, size); + } + + /* + * If we don't have a mapping yet and other request flags are + * present then we will be attempting to establish a new virtual + * address mapping. Enforce that this mapping is not aliasing + * System RAM. + */ + if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { + WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", + &offset, (unsigned long) size); + return NULL; + } + + if (!addr && (flags & MEMREMAP_WT)) + addr = ioremap_wt(offset, size); + + if (!addr && (flags & MEMREMAP_WC)) + addr = ioremap_wc(offset, size); + + return addr; +} +EXPORT_SYMBOL(memremap); + +void memunmap(void *addr) +{ + if (is_vmalloc_addr(addr)) + iounmap((void __iomem *) addr); +} +EXPORT_SYMBOL(memunmap); + +static void devm_memremap_release(struct device *dev, void *res) +{ + memunmap(*(void **)res); +} + +static int devm_memremap_match(struct device *dev, void *res, void *match_data) +{ + return *(void **)res == match_data; +} + +void *devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags) +{ + void **ptr, *addr; + + ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL, + dev_to_node(dev)); + if (!ptr) + return ERR_PTR(-ENOMEM); + + addr = memremap(offset, size, flags); + if (addr) { + *ptr = addr; + devres_add(dev, ptr); + } else { + devres_free(ptr); + return ERR_PTR(-ENXIO); + } + + return addr; +} +EXPORT_SYMBOL(devm_memremap); + +void devm_memunmap(struct device *dev, void *addr) +{ + WARN_ON(devres_release(dev, devm_memremap_release, + devm_memremap_match, addr)); +} +EXPORT_SYMBOL(devm_memunmap); diff --git a/kernel/memremap.c b/kernel/memremap.c index 895e6b76b25e..5857267a4af5 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -1,15 +1,5 @@ -/* - * Copyright(c) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2015 Intel Corporation. All rights reserved. */ #include <linux/radix-tree.h> #include <linux/device.h> #include <linux/types.h> @@ -19,170 +9,8 @@ #include <linux/memory_hotplug.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/wait_bit.h> -#ifndef ioremap_cache -/* temporary while we convert existing ioremap_cache users to memremap */ -__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) -{ - return ioremap(offset, size); -} -#endif - -#ifndef arch_memremap_wb -static void *arch_memremap_wb(resource_size_t offset, unsigned long size) -{ - return (__force void *)ioremap_cache(offset, size); -} -#endif - -#ifndef arch_memremap_can_ram_remap -static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, - unsigned long flags) -{ - return true; -} -#endif - -static void *try_ram_remap(resource_size_t offset, size_t size, - unsigned long flags) -{ - unsigned long pfn = PHYS_PFN(offset); - - /* In the simple case just return the existing linear address */ - if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) && - arch_memremap_can_ram_remap(offset, size, flags)) - return __va(offset); - - return NULL; /* fallback to arch_memremap_wb */ -} - -/** - * memremap() - remap an iomem_resource as cacheable memory - * @offset: iomem resource start address - * @size: size of remap - * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC, - * MEMREMAP_ENC, MEMREMAP_DEC - * - * memremap() is "ioremap" for cases where it is known that the resource - * being mapped does not have i/o side effects and the __iomem - * annotation is not applicable. In the case of multiple flags, the different - * mapping types will be attempted in the order listed below until one of - * them succeeds. - * - * MEMREMAP_WB - matches the default mapping for System RAM on - * the architecture. This is usually a read-allocate write-back cache. - * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM - * memremap() will bypass establishing a new mapping and instead return - * a pointer into the direct map. - * - * MEMREMAP_WT - establish a mapping whereby writes either bypass the - * cache or are written through to memory and never exist in a - * cache-dirty state with respect to program visibility. Attempts to - * map System RAM with this mapping type will fail. - * - * MEMREMAP_WC - establish a writecombine mapping, whereby writes may - * be coalesced together (e.g. in the CPU's write buffers), but is otherwise - * uncached. Attempts to map System RAM with this mapping type will fail. - */ -void *memremap(resource_size_t offset, size_t size, unsigned long flags) -{ - int is_ram = region_intersects(offset, size, - IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); - void *addr = NULL; - - if (!flags) - return NULL; - - if (is_ram == REGION_MIXED) { - WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", - &offset, (unsigned long) size); - return NULL; - } - - /* Try all mapping types requested until one returns non-NULL */ - if (flags & MEMREMAP_WB) { - /* - * MEMREMAP_WB is special in that it can be satisifed - * from the direct map. Some archs depend on the - * capability of memremap() to autodetect cases where - * the requested range is potentially in System RAM. - */ - if (is_ram == REGION_INTERSECTS) - addr = try_ram_remap(offset, size, flags); - if (!addr) - addr = arch_memremap_wb(offset, size); - } - - /* - * If we don't have a mapping yet and other request flags are - * present then we will be attempting to establish a new virtual - * address mapping. Enforce that this mapping is not aliasing - * System RAM. - */ - if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { - WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", - &offset, (unsigned long) size); - return NULL; - } - - if (!addr && (flags & MEMREMAP_WT)) - addr = ioremap_wt(offset, size); - - if (!addr && (flags & MEMREMAP_WC)) - addr = ioremap_wc(offset, size); - - return addr; -} -EXPORT_SYMBOL(memremap); - -void memunmap(void *addr) -{ - if (is_vmalloc_addr(addr)) - iounmap((void __iomem *) addr); -} -EXPORT_SYMBOL(memunmap); - -static void devm_memremap_release(struct device *dev, void *res) -{ - memunmap(*(void **)res); -} - -static int devm_memremap_match(struct device *dev, void *res, void *match_data) -{ - return *(void **)res == match_data; -} - -void *devm_memremap(struct device *dev, resource_size_t offset, - size_t size, unsigned long flags) -{ - void **ptr, *addr; - - ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL, - dev_to_node(dev)); - if (!ptr) - return ERR_PTR(-ENOMEM); - - addr = memremap(offset, size, flags); - if (addr) { - *ptr = addr; - devres_add(dev, ptr); - } else { - devres_free(ptr); - return ERR_PTR(-ENXIO); - } - - return addr; -} -EXPORT_SYMBOL(devm_memremap); - -void devm_memunmap(struct device *dev, void *addr) -{ - WARN_ON(devres_release(dev, devm_memremap_release, - devm_memremap_match, addr)); -} -EXPORT_SYMBOL(devm_memunmap); - -#ifdef CONFIG_ZONE_DEVICE static DEFINE_MUTEX(pgmap_lock); static RADIX_TREE(pgmap_radix, GFP_KERNEL); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) @@ -473,10 +301,32 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, return pgmap; } -#endif /* CONFIG_ZONE_DEVICE */ +EXPORT_SYMBOL_GPL(get_dev_pagemap); + +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL_GPL(devmap_managed_key); +static atomic_t devmap_enable; + +/* + * Toggle the static key for ->page_free() callbacks when dev_pagemap + * pages go idle. + */ +void dev_pagemap_get_ops(void) +{ + if (atomic_inc_return(&devmap_enable) == 1) + static_branch_enable(&devmap_managed_key); +} +EXPORT_SYMBOL_GPL(dev_pagemap_get_ops); + +void dev_pagemap_put_ops(void) +{ + if (atomic_dec_and_test(&devmap_enable)) + static_branch_disable(&devmap_managed_key); +} +EXPORT_SYMBOL_GPL(dev_pagemap_put_ops); -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) -void put_zone_device_private_or_public_page(struct page *page) +void __put_devmap_managed_page(struct page *page) { int count = page_ref_dec_return(page); @@ -496,5 +346,5 @@ void put_zone_device_private_or_public_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL(put_zone_device_private_or_public_page); -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +EXPORT_SYMBOL_GPL(__put_devmap_managed_page); +#endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/module.c b/kernel/module.c index c9bea7f2b43e..68469b37d61a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1604,8 +1604,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) if (notes == 0) return; - notes_attrs = kzalloc(sizeof(*notes_attrs) - + notes * sizeof(notes_attrs->attrs[0]), + notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), GFP_KERNEL); if (notes_attrs == NULL) return; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2f4af216bd6e..247808333ba4 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1908,6 +1908,7 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } + wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); @@ -2289,9 +2290,7 @@ void console_unlock(void) { static char ext_text[CONSOLE_EXT_LOG_MAX]; static char text[LOG_LINE_MAX + PREFIX_MAX]; - static u64 seen_seq; unsigned long flags; - bool wake_klogd = false; bool do_cond_resched, retry; if (console_suspended) { @@ -2335,11 +2334,6 @@ again: printk_safe_enter_irqsave(flags); raw_spin_lock(&logbuf_lock); - if (seen_seq != log_next_seq) { - wake_klogd = true; - seen_seq = log_next_seq; - } - if (console_seq < log_first_seq) { len = sprintf(text, "** %u printk messages dropped **\n", (unsigned)(log_first_seq - console_seq)); @@ -2397,7 +2391,7 @@ skip: if (console_lock_spinning_disable_and_check()) { printk_safe_exit_irqrestore(flags); - goto out; + return; } printk_safe_exit_irqrestore(flags); @@ -2429,10 +2423,6 @@ skip: if (retry && console_trylock()) goto again; - -out: - if (wake_klogd) - wake_up_klogd(); } EXPORT_SYMBOL(console_unlock); diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 3e3c2004bb23..d7d091309054 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -82,6 +82,7 @@ static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s, { int add; size_t len; + va_list ap; again: len = atomic_read(&s->len); @@ -100,7 +101,9 @@ again: if (!len) smp_rmb(); - add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args); + va_copy(ap, args); + add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap); + va_end(ap); if (!add) return 0; @@ -278,7 +281,7 @@ void printk_safe_flush_on_panic(void) * Make sure that we could access the main ring buffer. * Do not risk a double release when more CPUs are up. */ - if (in_nmi() && raw_spin_is_locked(&logbuf_lock)) { + if (raw_spin_is_locked(&logbuf_lock)) { if (num_online_cpus() > 1) return; diff --git a/kernel/resource.c b/kernel/resource.c index b589dda910b3..30e1bc68503b 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -415,6 +415,7 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, return __walk_iomem_res_desc(&res, desc, false, arg, func); } +EXPORT_SYMBOL_GPL(walk_iomem_res_desc); /* * This function calls the @func callback against all memory ranges of type diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e691d9a6c58d..fd023ac24e10 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -593,18 +593,15 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, } /* - * Force an audit message to be emitted when the action is RET_KILL_*, - * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is - * allowed to be logged by the admin. + * Emit an audit message when the action is RET_KILL_*, RET_LOG, or the + * FILTER_FLAG_LOG bit was set. The admin has the ability to silence + * any action from being logged by removing the action name from the + * seccomp_actions_logged sysctl. */ - if (log) - return __audit_seccomp(syscall, signr, action); + if (!log) + return; - /* - * Let the audit subsystem decide if the action should be audited based - * on whether the current task itself is being audited. - */ - return audit_seccomp(syscall, signr, action); + audit_seccomp(syscall, signr, action); } /* @@ -1144,10 +1141,11 @@ static const struct seccomp_log_name seccomp_log_names[] = { }; static bool seccomp_names_from_actions_logged(char *names, size_t size, - u32 actions_logged) + u32 actions_logged, + const char *sep) { const struct seccomp_log_name *cur; - bool append_space = false; + bool append_sep = false; for (cur = seccomp_log_names; cur->name && size; cur++) { ssize_t ret; @@ -1155,15 +1153,15 @@ static bool seccomp_names_from_actions_logged(char *names, size_t size, if (!(actions_logged & cur->log)) continue; - if (append_space) { - ret = strscpy(names, " ", size); + if (append_sep) { + ret = strscpy(names, sep, size); if (ret < 0) return false; names += ret; size -= ret; } else - append_space = true; + append_sep = true; ret = strscpy(names, cur->name, size); if (ret < 0) @@ -1208,46 +1206,102 @@ static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) return true; } -static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +static int read_actions_logged(struct ctl_table *ro_table, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + char names[sizeof(seccomp_actions_avail)]; + struct ctl_table table; + + memset(names, 0, sizeof(names)); + + if (!seccomp_names_from_actions_logged(names, sizeof(names), + seccomp_actions_logged, " ")) + return -EINVAL; + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + return proc_dostring(&table, 0, buffer, lenp, ppos); +} + +static int write_actions_logged(struct ctl_table *ro_table, void __user *buffer, + size_t *lenp, loff_t *ppos, u32 *actions_logged) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; int ret; - if (write && !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(names, 0, sizeof(names)); - if (!write) { - if (!seccomp_names_from_actions_logged(names, sizeof(names), - seccomp_actions_logged)) - return -EINVAL; - } - table = *ro_table; table.data = names; table.maxlen = sizeof(names); - ret = proc_dostring(&table, write, buffer, lenp, ppos); + ret = proc_dostring(&table, 1, buffer, lenp, ppos); if (ret) return ret; - if (write) { - u32 actions_logged; + if (!seccomp_actions_logged_from_names(actions_logged, table.data)) + return -EINVAL; - if (!seccomp_actions_logged_from_names(&actions_logged, - table.data)) - return -EINVAL; + if (*actions_logged & SECCOMP_LOG_ALLOW) + return -EINVAL; - if (actions_logged & SECCOMP_LOG_ALLOW) - return -EINVAL; + seccomp_actions_logged = *actions_logged; + return 0; +} - seccomp_actions_logged = actions_logged; - } +static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged, + int ret) +{ + char names[sizeof(seccomp_actions_avail)]; + char old_names[sizeof(seccomp_actions_avail)]; + const char *new = names; + const char *old = old_names; - return 0; + if (!audit_enabled) + return; + + memset(names, 0, sizeof(names)); + memset(old_names, 0, sizeof(old_names)); + + if (ret) + new = "?"; + else if (!actions_logged) + new = "(none)"; + else if (!seccomp_names_from_actions_logged(names, sizeof(names), + actions_logged, ",")) + new = "?"; + + if (!old_actions_logged) + old = "(none)"; + else if (!seccomp_names_from_actions_logged(old_names, + sizeof(old_names), + old_actions_logged, ",")) + old = "?"; + + return audit_seccomp_actions_logged(new, old, !ret); +} + +static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + if (write) { + u32 actions_logged = 0; + u32 old_actions_logged = seccomp_actions_logged; + + ret = write_actions_logged(ro_table, buffer, lenp, ppos, + &actions_logged); + audit_actions_logged(actions_logged, old_actions_logged, ret); + } else + ret = read_actions_logged(ro_table, buffer, lenp, ppos); + + return ret; } static struct ctl_path seccomp_sysctl_path[] = { diff --git a/kernel/sys.c b/kernel/sys.c index d1b2b8d934bb..38509dc1f77b 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2018,7 +2018,11 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data return error; } - down_write(&mm->mmap_sem); + /* + * arg_lock protects concurent updates but we still need mmap_sem for + * read to exclude races with sys_brk. + */ + down_read(&mm->mmap_sem); /* * We don't validate if these members are pointing to @@ -2032,6 +2036,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data * to any problem in kernel itself */ + spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; @@ -2043,6 +2048,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; + spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus @@ -2055,7 +2061,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 183169c2a75b..06b4ccee0047 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -367,7 +367,7 @@ COND_SYSCALL(s390_pci_mmio_write); COND_SYSCALL_COMPAT(s390_ipc); /* powerpc */ -cond_syscall(ppc_rtas); +COND_SYSCALL(rtas); COND_SYSCALL(spu_run); COND_SYSCALL(spu_create); COND_SYSCALL(subpage_prot); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c4f0f2e4126e..dd6c0a2ad969 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -110,11 +110,7 @@ config GENERIC_TRACER # config TRACING_SUPPORT bool - # PPC32 has no irqflags tracing support, but it can use most of the - # tracers anyway, they were tested to build and work. Note that new - # exceptions to this list aren't welcomed, better implement the - # irqflags tracing for your architecture. - depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on TRACE_IRQFLAGS_SUPPORT depends on STACKTRACE_SUPPORT default y diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 56ba0f2a01db..0ae6829804bc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,12 +14,14 @@ #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> +#include <linux/syscalls.h> #include <linux/error-injection.h> #include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /** * trace_call_bpf - invoke BPF program @@ -474,8 +476,6 @@ BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; - if (unlikely(in_interrupt())) - return -EINVAL; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; @@ -564,6 +564,10 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; +#endif default: return NULL; } @@ -577,6 +581,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE @@ -664,6 +670,25 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, + u64, flags) +{ + struct pt_regs *regs = *(struct pt_regs **)tp_buff; + + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_tp = { + .func = bpf_get_stack_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -672,6 +697,8 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; default: return tracing_func_proto(func_id, prog); } @@ -734,6 +761,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; default: @@ -744,7 +773,7 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output and/or bpf_get_stack_id + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack */ static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, @@ -787,6 +816,26 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, + void *, buf, u32, size, u64, flags) +{ + struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + + perf_fetch_caller_regs(regs); + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { + .func = bpf_get_stack_raw_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -795,6 +844,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_raw_tp; default: return tracing_func_proto(func_id, prog); } @@ -833,8 +884,14 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type return false; if (type != BPF_READ) return false; - if (off % size != 0) - return false; + if (off % size != 0) { + if (sizeof(unsigned long) != 4) + return false; + if (size != 8) + return false; + if (off % size != 4) + return false; + } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): @@ -959,6 +1016,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = event->tp_event->prog_array; ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + if (ret == -ENOENT) + goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { @@ -1117,3 +1176,50 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) mutex_unlock(&bpf_event_mutex); return err; } + +int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, + u32 *fd_type, const char **buf, + u64 *probe_offset, u64 *probe_addr) +{ + bool is_tracepoint, is_syscall_tp; + struct bpf_prog *prog; + int flags, err = 0; + + prog = event->prog; + if (!prog) + return -ENOENT; + + /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ + if (prog->type == BPF_PROG_TYPE_PERF_EVENT) + return -EOPNOTSUPP; + + *prog_id = prog->aux->id; + flags = event->tp_event->flags; + is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; + is_syscall_tp = is_syscall_trace_event(event->tp_event); + + if (is_tracepoint || is_syscall_tp) { + *buf = is_tracepoint ? event->tp_event->tp->name + : event->tp_event->name; + *fd_type = BPF_FD_TYPE_TRACEPOINT; + *probe_offset = 0x0; + *probe_addr = 0x0; + } else { + /* kprobe/uprobe */ + err = -EOPNOTSUPP; +#ifdef CONFIG_KPROBE_EVENTS + if (flags & TRACE_EVENT_FL_KPROBE) + err = bpf_get_kprobe_info(event, fd_type, buf, + probe_offset, probe_addr, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif +#ifdef CONFIG_UPROBE_EVENTS + if (flags & TRACE_EVENT_FL_UPROBE) + err = bpf_get_uprobe_info(event, fd_type, buf, + probe_offset, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif + } + + return err; +} diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c9cb9767d49b..6a46af21765c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -809,7 +809,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); * * You can see, it is legitimate for the previous pointer of * the head (or any page) not to point back to itself. But only - * temporarially. + * temporarily. */ #define RB_PAGE_NORMAL 0UL @@ -906,7 +906,7 @@ static void rb_list_head_clear(struct list_head *list) } /* - * rb_head_page_dactivate - clears head page ptr (for free list) + * rb_head_page_deactivate - clears head page ptr (for free list) */ static void rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) @@ -1780,7 +1780,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, put_online_cpus(); } else { - /* Make sure this CPU has been intitialized */ + /* Make sure this CPU has been initialized */ if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) goto out; @@ -2325,7 +2325,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, /* * If we need to add a timestamp, then we - * add it to the start of the resevered space. + * add it to the start of the reserved space. */ if (unlikely(info->add_timestamp)) { bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer); @@ -2681,7 +2681,7 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) * ring_buffer_nest_start - Allow to trace while nested * @buffer: The ring buffer to modify * - * The ring buffer has a safty mechanism to prevent recursion. + * The ring buffer has a safety mechanism to prevent recursion. * But there may be a case where a trace needs to be done while * tracing something else. In this case, calling this function * will allow this function to nest within a currently active @@ -2699,7 +2699,7 @@ void ring_buffer_nest_start(struct ring_buffer *buffer) preempt_disable_notrace(); cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest += NESTED_BITS; } @@ -2718,7 +2718,7 @@ void ring_buffer_nest_end(struct ring_buffer *buffer) /* disabled by ring_buffer_nest_start() */ cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest -= NESTED_BITS; preempt_enable_notrace(); } @@ -2907,7 +2907,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * @buffer: the ring buffer to reserve from * @length: the length of the data to reserve (excluding event header) * - * Returns a reseverd event on the ring buffer to copy directly to. + * Returns a reserved event on the ring buffer to copy directly to. * The user of this interface will need to get the body to write into * and can use the ring_buffer_event_data() interface. * @@ -3009,7 +3009,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, * This function lets the user discard an event in the ring buffer * and then that event will not be read later. * - * This function only works if it is called before the the item has been + * This function only works if it is called before the item has been * committed. It will try to free the event from the ring buffer * if another event has not been added behind it. * @@ -4127,7 +4127,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * through the buffer. Memory is allocated, buffer recording * is disabled, and the iterator pointer is returned to the caller. * - * Disabling buffer recordng prevents the reading from being + * Disabling buffer recording prevents the reading from being * corrupted. This is not a consuming read, so a producer is not * expected. * diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bcd93031d042..108ce3e1dc13 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4395,8 +4395,7 @@ static int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; - int ret = -ENODEV; - int i; + int ret; size_t orig_len = strlen(option); cmp = strstrip(option); @@ -4408,16 +4407,12 @@ static int trace_set_options(struct trace_array *tr, char *option) mutex_lock(&trace_types_lock); - for (i = 0; trace_options[i]; i++) { - if (strcmp(cmp, trace_options[i]) == 0) { - ret = set_tracer_flag(tr, 1 << i, !neg); - break; - } - } - + ret = match_string(trace_options, -1, cmp); /* If no option could be set, test the specific tracer options */ - if (!trace_options[i]) + if (ret < 0) ret = set_tracer_option(tr, cmp, neg); + else + ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); @@ -6074,6 +6069,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; + enum event_trigger_type tt = ETT_NONE; struct ring_buffer *buffer; struct print_entry *entry; unsigned long irq_flags; @@ -6122,6 +6118,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, written = cnt; len = cnt; + if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { + /* do not add \n before testing triggers, but add \0 */ + entry->buf[cnt] = '\0'; + tt = event_triggers_call(tr->trace_marker_file, entry, event); + } + if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; entry->buf[cnt + 1] = '\0'; @@ -6130,6 +6132,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, __buffer_unlock_commit(buffer, event); + if (tt) + event_triggers_post_call(tr->trace_marker_file, tt); + if (written > 0) *fpos += written; @@ -7896,6 +7901,7 @@ static __init void create_trace_instances(struct dentry *d_tracer) static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { + struct trace_event_file *file; int cpu; trace_create_file("available_tracers", 0444, d_tracer, @@ -7928,6 +7934,12 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); + file = __find_event_file(tr, "ftrace", "print"); + if (file && file->dir) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); + tr->trace_marker_file = file; + trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); @@ -8111,6 +8123,8 @@ static __init int tracer_init_tracefs(void) if (IS_ERR(d_tracer)) return 0; + event_trace_init(); + init_tracer_tracefs(&global_trace, d_tracer); ftrace_init_tracefs_toplevel(&global_trace, d_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 507954b4e058..630c5a24b2b2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -259,6 +259,7 @@ struct trace_array { struct trace_options *topts; struct list_head systems; struct list_head events; + struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; #ifdef CONFIG_FUNCTION_TRACER @@ -1334,7 +1335,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } /** @@ -1367,7 +1368,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file, irq_flags, pc, regs); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } #define FILTER_PRED_INVALID ((unsigned short)-1) @@ -1451,9 +1452,13 @@ trace_find_event_field(struct trace_event_call *call, char *name); extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); +extern int event_trace_init(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); +extern struct trace_event_file *__find_event_file(struct trace_array *tr, + const char *system, + const char *event); extern struct trace_event_file *find_event_file(struct trace_array *tr, const char *system, const char *event); diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e3a658bac10f..1d67464ed95e 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -230,7 +230,7 @@ FTRACE_ENTRY(bprint, bprint_entry, FILTER_OTHER ); -FTRACE_ENTRY(print, print_entry, +FTRACE_ENTRY_REG(print, print_entry, TRACE_PRINT, @@ -242,7 +242,9 @@ FTRACE_ENTRY(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER + FILTER_OTHER, + + ftrace_event_register ); FTRACE_ENTRY(raw_data, raw_data_entry, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05c7172c6667..14ff4ff3caab 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2007,16 +2007,18 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) return -1; } } - trace_create_file("filter", 0644, file->dir, file, - &ftrace_event_filter_fops); /* * Only event directories that can be enabled should have - * triggers. + * triggers or filters. */ - if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { + trace_create_file("filter", 0644, file->dir, file, + &ftrace_event_filter_fops); + trace_create_file("trigger", 0644, file->dir, file, &event_trigger_fops); + } #ifdef CONFIG_HIST_TRIGGERS trace_create_file("hist", 0444, file->dir, file, @@ -2473,8 +2475,9 @@ __trace_add_event_dirs(struct trace_array *tr) } } +/* Returns any file that matches the system and event */ struct trace_event_file * -find_event_file(struct trace_array *tr, const char *system, const char *event) +__find_event_file(struct trace_array *tr, const char *system, const char *event) { struct trace_event_file *file; struct trace_event_call *call; @@ -2485,10 +2488,7 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) call = file->event_call; name = trace_event_name(call); - if (!name || !call->class || !call->class->reg) - continue; - - if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + if (!name || !call->class) continue; if (strcmp(event, name) == 0 && @@ -2498,6 +2498,20 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) return NULL; } +/* Returns valid trace event files that match system and event */ +struct trace_event_file * +find_event_file(struct trace_array *tr, const char *system, const char *event) +{ + struct trace_event_file *file; + + file = __find_event_file(tr, system, event); + if (!file || !file->event_call->class->reg || + file->event_call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + return NULL; + + return file; +} + #ifdef CONFIG_DYNAMIC_FTRACE /* Avoid typos */ @@ -3132,7 +3146,7 @@ static __init int event_trace_enable_again(void) early_initcall(event_trace_enable_again); -static __init int event_trace_init(void) +__init int event_trace_init(void) { struct trace_array *tr; struct dentry *d_tracer; @@ -3177,8 +3191,6 @@ void __init trace_event_init(void) event_trace_enable(); } -fs_initcall(event_trace_init); - #ifdef CONFIG_FTRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 7d306b74230f..0171407d231f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -750,31 +750,32 @@ static int filter_pred_none(struct filter_pred *pred, void *event) * * Note: * - @str might not be NULL-terminated if it's of type DYN_STRING - * or STATIC_STRING + * or STATIC_STRING, unless @len is zero. */ static int regex_match_full(char *str, struct regex *r, int len) { - if (strncmp(str, r->pattern, len) == 0) - return 1; - return 0; + /* len of zero means str is dynamic and ends with '\0' */ + if (!len) + return strcmp(str, r->pattern) == 0; + + return strncmp(str, r->pattern, len) == 0; } static int regex_match_front(char *str, struct regex *r, int len) { - if (len < r->len) + if (len && len < r->len) return 0; - if (strncmp(str, r->pattern, r->len) == 0) - return 1; - return 0; + return strncmp(str, r->pattern, r->len) == 0; } static int regex_match_middle(char *str, struct regex *r, int len) { - if (strnstr(str, r->pattern, len)) - return 1; - return 0; + if (!len) + return strstr(str, r->pattern) != NULL; + + return strnstr(str, r->pattern, len) != NULL; } static int regex_match_end(char *str, struct regex *r, int len) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index b9061ed59bbd..046c716a6536 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2865,7 +2865,7 @@ static struct trace_event_file *event_file(struct trace_array *tr, { struct trace_event_file *file; - file = find_event_file(tr, system, event_name); + file = __find_event_file(tr, system, event_name); if (!file) return ERR_PTR(-EINVAL); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8b5bdcf64871..d18249683682 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -97,7 +97,6 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke - * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -108,8 +107,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt, - void *rec, struct ring_buffer_event *event) + enum event_trigger_type tt) { struct event_trigger_data *data; @@ -117,7 +115,7 @@ event_triggers_post_call(struct trace_event_file *file, if (data->paused) continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data, rec, event); + data->ops->func(data, NULL, NULL); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 548e62eb5c46..45630a76ed3a 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -14,6 +14,13 @@ #include "trace_output.h" +/* Stub function for events with triggers */ +static int ftrace_event_register(struct trace_event_call *call, + enum trace_reg type, void *data) +{ + return 0; +} + #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace @@ -117,7 +124,7 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __dynamic_array #define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ + ret = trace_define_field(event_call, #type "[]", #item, \ offsetof(typeof(field), item), \ 0, is_signed_type(type), filter_type);\ if (ret) \ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 02aed76e0978..daa81571b22a 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1287,6 +1287,35 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, head, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); + +int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, + const char **symbol, u64 *probe_offset, + u64 *probe_addr, bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_kprobe *tk; + + if (perf_type_tracepoint) + tk = find_trace_kprobe(pevent, group); + else + tk = event->tp_event->data; + if (!tk) + return -EINVAL; + + *fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE + : BPF_FD_TYPE_KPROBE; + if (tk->symbol) { + *symbol = tk->symbol; + *probe_offset = tk->rp.kp.offset; + *probe_addr = 0; + } else { + *symbol = NULL; + *probe_offset = 0; + *probe_addr = (unsigned long)tk->rp.kp.addr; + } + return 0; +} #endif /* CONFIG_PERF_EVENTS */ /* diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index ac892878dbe6..bf89a51e740d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1161,6 +1161,28 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, { __uprobe_perf_func(tu, func, regs, ucb, dsize); } + +int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, + const char **filename, u64 *probe_offset, + bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_uprobe *tu; + + if (perf_type_tracepoint) + tu = find_probe_event(pevent, group); + else + tu = event->tp_event->data; + if (!tu) + return -EINVAL; + + *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE + : BPF_FD_TYPE_UPROBE; + *filename = tu->filename; + *probe_offset = tu->offset; + return 0; +} #endif /* CONFIG_PERF_EVENTS */ static int diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 1e37da2e0c25..6dc6356c3327 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -257,7 +257,7 @@ static int tracepoint_remove_func(struct tracepoint *tp, } /** - * tracepoint_probe_register - Connect a probe to a tracepoint + * tracepoint_probe_register_prio - Connect a probe to a tracepoint with priority * @tp: tracepoint * @probe: probe handler * @data: tracepoint data @@ -290,7 +290,6 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio); * @tp: tracepoint * @probe: probe handler * @data: tracepoint data - * @prio: priority of this function over other registered functions * * Returns 0 if ok, error value on error. * Note: if @tp is within a module, the caller is responsible for diff --git a/kernel/umh.c b/kernel/umh.c index f76b3ff876cf..30db93fd7e39 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -25,6 +25,8 @@ #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> +#include <linux/shmem_fs.h> +#include <linux/pipe_fs_i.h> #include <trace/events/module.h> @@ -97,9 +99,13 @@ static int call_usermodehelper_exec_async(void *data) commit_creds(new); - retval = do_execve(getname_kernel(sub_info->path), - (const char __user *const __user *)sub_info->argv, - (const char __user *const __user *)sub_info->envp); + if (sub_info->file) + retval = do_execve_file(sub_info->file, + sub_info->argv, sub_info->envp); + else + retval = do_execve(getname_kernel(sub_info->path), + (const char __user *const __user *)sub_info->argv, + (const char __user *const __user *)sub_info->envp); out: sub_info->retval = retval; /* @@ -185,6 +191,8 @@ static void call_usermodehelper_exec_work(struct work_struct *work) if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); + } else { + sub_info->pid = pid; } } } @@ -393,6 +401,117 @@ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, } EXPORT_SYMBOL(call_usermodehelper_setup); +struct subprocess_info *call_usermodehelper_setup_file(struct file *file, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *info), void *data) +{ + struct subprocess_info *sub_info; + + sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL); + if (!sub_info) + return NULL; + + INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); + sub_info->path = "none"; + sub_info->file = file; + sub_info->init = init; + sub_info->cleanup = cleanup; + sub_info->data = data; + return sub_info; +} + +static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) +{ + struct umh_info *umh_info = info->data; + struct file *from_umh[2]; + struct file *to_umh[2]; + int err; + + /* create pipe to send data to umh */ + err = create_pipe_files(to_umh, 0); + if (err) + return err; + err = replace_fd(0, to_umh[0], 0); + fput(to_umh[0]); + if (err < 0) { + fput(to_umh[1]); + return err; + } + + /* create pipe to receive data from umh */ + err = create_pipe_files(from_umh, 0); + if (err) { + fput(to_umh[1]); + replace_fd(0, NULL, 0); + return err; + } + err = replace_fd(1, from_umh[1], 0); + fput(from_umh[1]); + if (err < 0) { + fput(to_umh[1]); + replace_fd(0, NULL, 0); + fput(from_umh[0]); + return err; + } + + umh_info->pipe_to_umh = to_umh[1]; + umh_info->pipe_from_umh = from_umh[0]; + return 0; +} + +static void umh_save_pid(struct subprocess_info *info) +{ + struct umh_info *umh_info = info->data; + + umh_info->pid = info->pid; +} + +/** + * fork_usermode_blob - fork a blob of bytes as a usermode process + * @data: a blob of bytes that can be do_execv-ed as a file + * @len: length of the blob + * @info: information about usermode process (shouldn't be NULL) + * + * Returns either negative error or zero which indicates success + * in executing a blob of bytes as a usermode process. In such + * case 'struct umh_info *info' is populated with two pipes + * and a pid of the process. The caller is responsible for health + * check of the user process, killing it via pid, and closing the + * pipes when user process is no longer needed. + */ +int fork_usermode_blob(void *data, size_t len, struct umh_info *info) +{ + struct subprocess_info *sub_info; + struct file *file; + ssize_t written; + loff_t pos = 0; + int err; + + file = shmem_kernel_file_setup("", len, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + + written = kernel_write(file, data, len, &pos); + if (written != len) { + err = written; + if (err >= 0) + err = -ENOMEM; + goto out; + } + + err = -ENOMEM; + sub_info = call_usermodehelper_setup_file(file, umh_pipe_setup, + umh_save_pid, info); + if (!sub_info) + goto out; + + err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); +out: + fput(file); + return err; +} +EXPORT_SYMBOL_GPL(fork_usermode_blob); + /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocessa diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 246d4d4ce5c7..492c255e6c5a 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -1235,6 +1235,7 @@ bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } +EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ca7959be8aaa..9f9983b0a27d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -66,7 +66,7 @@ enum { * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding - * attach_mutex to avoid changing binding state while + * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ @@ -123,7 +123,7 @@ enum { * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * - * A: pool->attach_mutex protected. + * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * @@ -166,7 +166,6 @@ struct worker_pool { /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ - struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ struct completion *detach_completion; /* all workers detached */ @@ -297,6 +296,7 @@ static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ +static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ @@ -399,14 +399,14 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); * @worker: iteration cursor * @pool: worker_pool to iterate workers of * - * This must be called with @pool->attach_mutex. + * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ - if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \ + if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** @@ -1724,7 +1724,7 @@ static struct worker *alloc_worker(int node) static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { - mutex_lock(&pool->attach_mutex); + mutex_lock(&wq_pool_attach_mutex); /* * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any @@ -1733,37 +1733,40 @@ static void worker_attach_to_pool(struct worker *worker, set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); /* - * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains - * stable across this function. See the comments above the - * flag definition for details. + * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains + * stable across this function. See the comments above the flag + * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; list_add_tail(&worker->node, &pool->workers); + worker->pool = pool; - mutex_unlock(&pool->attach_mutex); + mutex_unlock(&wq_pool_attach_mutex); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool - * @pool: the pool @worker is attached to * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ -static void worker_detach_from_pool(struct worker *worker, - struct worker_pool *pool) +static void worker_detach_from_pool(struct worker *worker) { + struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; - mutex_lock(&pool->attach_mutex); + mutex_lock(&wq_pool_attach_mutex); + list_del(&worker->node); + worker->pool = NULL; + if (list_empty(&pool->workers)) detach_completion = pool->detach_completion; - mutex_unlock(&pool->attach_mutex); + mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); @@ -1799,7 +1802,6 @@ static struct worker *create_worker(struct worker_pool *pool) if (!worker) goto fail; - worker->pool = pool; worker->id = id; if (pool->cpu >= 0) @@ -2086,6 +2088,12 @@ __acquires(&pool->lock) worker->current_pwq = pwq; work_color = get_work_color(work); + /* + * Record wq name for cmdline and debug reporting, may get + * overridden through set_worker_desc(). + */ + strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); + list_del_init(&work->entry); /* @@ -2181,7 +2189,6 @@ __acquires(&pool->lock) worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; - worker->desc_valid = false; pwq_dec_nr_in_flight(pwq, work_color); } @@ -2206,6 +2213,16 @@ static void process_scheduled_works(struct worker *worker) } } +static void set_pf_worker(bool val) +{ + mutex_lock(&wq_pool_attach_mutex); + if (val) + current->flags |= PF_WQ_WORKER; + else + current->flags &= ~PF_WQ_WORKER; + mutex_unlock(&wq_pool_attach_mutex); +} + /** * worker_thread - the worker thread function * @__worker: self @@ -2224,7 +2241,7 @@ static int worker_thread(void *__worker) struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ - worker->task->flags |= PF_WQ_WORKER; + set_pf_worker(true); woke_up: spin_lock_irq(&pool->lock); @@ -2232,11 +2249,11 @@ woke_up: if (unlikely(worker->flags & WORKER_DIE)) { spin_unlock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&worker->entry)); - worker->task->flags &= ~PF_WQ_WORKER; + set_pf_worker(false); set_task_comm(worker->task, "kworker/dying"); ida_simple_remove(&pool->worker_ida, worker->id); - worker_detach_from_pool(worker, pool); + worker_detach_from_pool(worker); kfree(worker); return 0; } @@ -2335,7 +2352,7 @@ static int rescuer_thread(void *__rescuer) * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ - rescuer->task->flags |= PF_WQ_WORKER; + set_pf_worker(true); repeat: set_current_state(TASK_IDLE); @@ -2367,7 +2384,6 @@ repeat: worker_attach_to_pool(rescuer, pool); spin_lock_irq(&pool->lock); - rescuer->pool = pool; /* * Slurp in all works issued via this workqueue and @@ -2417,10 +2433,9 @@ repeat: if (need_more_worker(pool)) wake_up_worker(pool); - rescuer->pool = NULL; spin_unlock_irq(&pool->lock); - worker_detach_from_pool(rescuer, pool); + worker_detach_from_pool(rescuer); spin_lock_irq(&wq_mayday_lock); } @@ -2429,7 +2444,7 @@ repeat: if (should_stop) { __set_current_state(TASK_RUNNING); - rescuer->task->flags &= ~PF_WQ_WORKER; + set_pf_worker(false); return 0; } @@ -3271,7 +3286,6 @@ static int init_worker_pool(struct worker_pool *pool) timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); - mutex_init(&pool->attach_mutex); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); @@ -3354,10 +3368,10 @@ static void put_unbound_pool(struct worker_pool *pool) WARN_ON(pool->nr_workers || pool->nr_idle); spin_unlock_irq(&pool->lock); - mutex_lock(&pool->attach_mutex); + mutex_lock(&wq_pool_attach_mutex); if (!list_empty(&pool->workers)) pool->detach_completion = &detach_completion; - mutex_unlock(&pool->attach_mutex); + mutex_unlock(&wq_pool_attach_mutex); if (pool->detach_completion) wait_for_completion(pool->detach_completion); @@ -3700,8 +3714,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, lockdep_assert_held(&wq_pool_mutex); - ctx = kzalloc(sizeof(*ctx) + nr_node_ids * sizeof(ctx->pwq_tbl[0]), - GFP_KERNEL); + ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(GFP_KERNEL); tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); @@ -4347,7 +4360,6 @@ void set_worker_desc(const char *fmt, ...) va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); - worker->desc_valid = true; } } @@ -4371,7 +4383,6 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; - bool desc_valid = false; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) @@ -4384,22 +4395,18 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) worker = kthread_probe_data(task); /* - * Carefully copy the associated workqueue's workfn and name. Keep - * the original last '\0' in case the original contains garbage. + * Carefully copy the associated workqueue's workfn, name and desc. + * Keep the original last '\0' in case the original is garbage. */ probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); probe_kernel_read(name, wq->name, sizeof(name) - 1); - - /* copy worker description */ - probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid)); - if (desc_valid) - probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %pf", log_lvl, name, fn); - if (desc[0]) + if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } @@ -4579,6 +4586,47 @@ void show_workqueue_state(void) rcu_read_unlock_sched(); } +/* used to show worker information through /proc/PID/{comm,stat,status} */ +void wq_worker_comm(char *buf, size_t size, struct task_struct *task) +{ + int off; + + /* always show the actual comm */ + off = strscpy(buf, task->comm, size); + if (off < 0) + return; + + /* stabilize PF_WQ_WORKER and worker pool association */ + mutex_lock(&wq_pool_attach_mutex); + + if (task->flags & PF_WQ_WORKER) { + struct worker *worker = kthread_data(task); + struct worker_pool *pool = worker->pool; + + if (pool) { + spin_lock_irq(&pool->lock); + /* + * ->desc tracks information (wq name or + * set_worker_desc()) for the latest execution. If + * current, prepend '+', otherwise '-'. + */ + if (worker->desc[0] != '\0') { + if (worker->current_work) + scnprintf(buf + off, size - off, "+%s", + worker->desc); + else + scnprintf(buf + off, size - off, "-%s", + worker->desc); + } + spin_unlock_irq(&pool->lock); + } + } + + mutex_unlock(&wq_pool_attach_mutex); +} + +#ifdef CONFIG_SMP + /* * CPU hotplug. * @@ -4600,7 +4648,7 @@ static void unbind_workers(int cpu) struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { - mutex_lock(&pool->attach_mutex); + mutex_lock(&wq_pool_attach_mutex); spin_lock_irq(&pool->lock); /* @@ -4616,7 +4664,7 @@ static void unbind_workers(int cpu) pool->flags |= POOL_DISASSOCIATED; spin_unlock_irq(&pool->lock); - mutex_unlock(&pool->attach_mutex); + mutex_unlock(&wq_pool_attach_mutex); /* * Call schedule() so that we cross rq->lock and thus can @@ -4657,7 +4705,7 @@ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; - lockdep_assert_held(&pool->attach_mutex); + lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should @@ -4727,7 +4775,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) static cpumask_t cpumask; struct worker *worker; - lockdep_assert_held(&pool->attach_mutex); + lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) @@ -4762,14 +4810,14 @@ int workqueue_online_cpu(unsigned int cpu) mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { - mutex_lock(&pool->attach_mutex); + mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); - mutex_unlock(&pool->attach_mutex); + mutex_unlock(&wq_pool_attach_mutex); } /* update NUMA affinity of unbound workqueues */ @@ -4799,8 +4847,6 @@ int workqueue_offline_cpu(unsigned int cpu) return 0; } -#ifdef CONFIG_SMP - struct work_for_cpu { struct work_struct work; long (*fn)(void *); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index d390d1be3748..66fbb5a9e633 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -31,13 +31,12 @@ struct worker { struct work_struct *current_work; /* L: work being processed */ work_func_t current_func; /* L: current_work's fn */ struct pool_workqueue *current_pwq; /* L: current_work's pwq */ - bool desc_valid; /* ->desc is valid */ struct list_head scheduled; /* L: scheduled works */ /* 64 bytes boundary on 64bit, 32 on 32bit */ struct task_struct *task; /* I: worker task */ - struct worker_pool *pool; /* I: the associated pool */ + struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ |