diff --git a/init/main.c b/init/main.c index f5b8246e8a..8d97aba78c 100644 --- a/init/main.c +++ b/init/main.c @@ -397,6 +397,12 @@ static int __init bootconfig_params(char *param, char *val, return 0; } +static int __init warn_bootconfig(char *str) +{ + /* The 'bootconfig' has been handled by bootconfig_params(). */ + return 0; +} + static void __init setup_boot_config(void) { static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata; @@ -475,9 +481,8 @@ static int __init warn_bootconfig(char *str) pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOT_CONFIG is not set.\n"); return 0; } -early_param("bootconfig", warn_bootconfig); - #endif +early_param("bootconfig", warn_bootconfig); /* Change NUL term back to "=", to make "param" the whole string. */ static void __init repair_env_string(char *param, char *val) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 7a97b2f474..55f83ea09d 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -353,9 +353,15 @@ const struct bpf_func_proto bpf_jiffies64_proto = { #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; + u64 cgrp_id; - return cgroup_id(cgrp); + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + cgrp_id = cgroup_id(cgrp); + rcu_read_unlock(); + + return cgrp_id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { @@ -366,13 +372,17 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) { - struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *cgrp; struct cgroup *ancestor; + u64 cgrp_id; + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); ancestor = cgroup_ancestor(cgrp, ancestor_level); - if (!ancestor) - return 0; - return cgroup_id(ancestor); + cgrp_id = ancestor ? cgroup_id(ancestor) : 0; + rcu_read_unlock(); + + return cgrp_id; } const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f9bda5476e..9d94ac6ff5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5150,8 +5150,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && - func_id != BPF_FUNC_ringbuf_submit && - func_id != BPF_FUNC_ringbuf_discard && func_id != BPF_FUNC_ringbuf_query) goto error; break; @@ -5260,6 +5258,12 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; + case BPF_FUNC_ringbuf_output: + case BPF_FUNC_ringbuf_reserve: + case BPF_FUNC_ringbuf_query: + if (map->map_type != BPF_MAP_TYPE_RINGBUF) + goto error; + break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; @@ -11410,10 +11414,11 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ -static int adjust_insn_aux_data(struct bpf_verifier_env *env, - struct bpf_prog *new_prog, u32 off, u32 cnt) +static void adjust_insn_aux_data(struct bpf_verifier_env *env, + struct bpf_insn_aux_data *new_data, + struct bpf_prog *new_prog, u32 off, u32 cnt) { - struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + struct bpf_insn_aux_data *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; u32 old_seen = old_data[off].seen; u32 prog_len; @@ -11426,12 +11431,9 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); if (cnt == 1) - return 0; + return; prog_len = new_prog->len; - new_data = vzalloc(array_size(prog_len, - sizeof(struct bpf_insn_aux_data))); - if (!new_data) - return -ENOMEM; + memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); @@ -11442,7 +11444,6 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, } env->insn_aux_data = new_data; vfree(old_data); - return 0; } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) @@ -11477,6 +11478,14 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; + struct bpf_insn_aux_data *new_data = NULL; + + if (len > 1) { + new_data = vzalloc(array_size(env->prog->len + len - 1, + sizeof(struct bpf_insn_aux_data))); + if (!new_data) + return NULL; + } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { @@ -11484,10 +11493,10 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); + vfree(new_data); return NULL; } - if (adjust_insn_aux_data(env, new_prog, off, len)) - return NULL; + adjust_insn_aux_data(env, new_data, new_prog, off, len); adjust_subprog_starts(env, off, len); adjust_poke_descs(new_prog, off, len); return new_prog; @@ -11663,6 +11672,7 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); + aux_data[i].zext_dst = false; } } @@ -12003,6 +12013,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; + if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier narrow ctx load misconfigured\n"); + return -EINVAL; + } if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, diff --git a/kernel/cfi.c b/kernel/cfi.c index e17a566397..9594cfd1cf 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -248,9 +248,9 @@ static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr) { cfi_check_fn fn; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); fn = ptr_to_check_fn(rcu_dereference_sched(cfi_shadow), ptr); - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } @@ -269,11 +269,11 @@ static inline cfi_check_fn find_module_check_fn(unsigned long ptr) cfi_check_fn fn = NULL; struct module *mod; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); mod = __module_address(ptr); if (mod) fn = mod->cfi_check; - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index adb5190c44..13b5be6df4 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1114,7 +1114,7 @@ enum subparts_cmd { * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition - * root back to a non-partition root. any CPUs in cpus_allowed that are in + * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * @@ -1148,6 +1148,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ + int new_prs; bool part_error = false; /* Partition error? */ percpu_rwsem_assert_held(&cpuset_rwsem); @@ -1183,6 +1184,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; + new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; @@ -1225,7 +1227,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, /* * partcmd_update w/o newmask: * - * addmask = cpus_allowed & parent->effectiveb_cpus + * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. @@ -1247,11 +1249,11 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) - cpuset->partition_root_state = PRS_ERROR; + new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) - cpuset->partition_root_state = PRS_ENABLED; + new_prs = PRS_ENABLED; break; } /* @@ -1260,10 +1262,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, part_error = (prev_prs == PRS_ERROR); } - if (!part_error && (cpuset->partition_root_state == PRS_ERROR)) + if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ - if (cpuset->partition_root_state == PRS_ERROR) { + if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ @@ -1272,7 +1274,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); } - if (!adding && !deleting) + if (!adding && !deleting && (new_prs == cpuset->partition_root_state)) return 0; /* @@ -1299,6 +1301,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); + + if (cpuset->partition_root_state != new_prs) + cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); return cmd == partcmd_update; @@ -1321,6 +1326,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; + int new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { @@ -1360,17 +1366,18 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ - if ((cp != cs) && cp->partition_root_state) { + new_prs = cp->partition_root_state; + if ((cp != cs) && new_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an - * invalid partition root, clear the state - * state and the CS_CPU_EXCLUSIVE flag. + * invalid partition root, clear its state + * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); - cp->partition_root_state = 0; + new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and @@ -1391,11 +1398,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) /* * When parent is invalid, it has to be too. */ - cp->partition_root_state = PRS_ERROR; - if (cp->nr_subparts_cpus) { - cp->nr_subparts_cpus = 0; - cpumask_clear(cp->subparts_cpus); - } + new_prs = PRS_ERROR; break; } } @@ -1407,8 +1410,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); - if (cp->nr_subparts_cpus && - (cp->partition_root_state != PRS_ENABLED)) { + if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { @@ -1435,6 +1437,10 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) = cpumask_weight(cp->subparts_cpus); } } + + if (new_prs != cp->partition_root_state) + cp->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && @@ -1937,34 +1943,32 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, /* * update_prstate - update partititon_root_state - * cs: the cpuset to update - * val: 0 - disabled, 1 - enabled + * cs: the cpuset to update + * new_prs: new partition root state * * Call with cpuset_mutex held. */ -static int update_prstate(struct cpuset *cs, int val) +static int update_prstate(struct cpuset *cs, int new_prs) { - int err; + int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); - struct tmpmasks tmp; + struct tmpmasks tmpmask; - if ((val != 0) && (val != 1)) - return -EINVAL; - if (val == cs->partition_root_state) + if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ - if (val && cs->partition_root_state) + if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; - if (alloc_cpumasks(NULL, &tmp)) + if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; - if (!cs->partition_root_state) { + if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed @@ -1978,31 +1982,27 @@ static int update_prstate(struct cpuset *cs, int val) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, - NULL, &tmp); + NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } - cs->partition_root_state = PRS_ENABLED; } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ - if (cs->partition_root_state == PRS_ERROR) { - cs->partition_root_state = 0; + if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, - NULL, &tmp); + NULL, &tmpmask); if (err) goto out; - cs->partition_root_state = 0; - /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } @@ -2015,11 +2015,17 @@ static int update_prstate(struct cpuset *cs, int val) update_tasks_cpumask(parent); if (parent->child_ecpus_count) - update_sibling_cpumasks(parent, cs, &tmp); + update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: - free_cpumasks(NULL, &tmp); + if (!err) { + spin_lock_irq(&callback_lock); + cs->partition_root_state = new_prs; + spin_unlock_irq(&callback_lock); + } + + free_cpumasks(NULL, &tmpmask); return err; } @@ -3060,7 +3066,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) goto retry; } - parent = parent_cs(cs); + parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); @@ -3082,8 +3088,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { + spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); + spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } @@ -3097,7 +3105,9 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) cpumask_empty(&new_cpus)) { update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); + spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; + spin_unlock_irq(&callback_lock); } cpuset_force_rebuild(); } @@ -3168,6 +3178,13 @@ static void cpuset_hotplug_workfn(struct work_struct *work) cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + /* + * In the rare case that hotplug removes all the cpus in subparts_cpus, + * we assumed that cpus are updated. + */ + if (!cpus_updated && top_cpuset.nr_subparts_cpus) + cpus_updated = true; + /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c index f7e1d0eccd..246efc74e3 100644 --- a/kernel/cpu_pm.c +++ b/kernel/cpu_pm.c @@ -13,19 +13,32 @@ #include #include -static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain); +/* + * atomic_notifiers use a spinlock_t, which can block under PREEMPT_RT. + * Notifications for cpu_pm will be issued by the idle task itself, which can + * never block, IOW it requires using a raw_spinlock_t. + */ +static struct { + struct raw_notifier_head chain; + raw_spinlock_t lock; +} cpu_pm_notifier = { + .chain = RAW_NOTIFIER_INIT(cpu_pm_notifier.chain), + .lock = __RAW_SPIN_LOCK_UNLOCKED(cpu_pm_notifier.lock), +}; static int cpu_pm_notify(enum cpu_pm_event event) { int ret; /* - * atomic_notifier_call_chain has a RCU read critical section, which - * could be disfunctional in cpu idle. Copy RCU_NONIDLE code to let - * RCU know this. + * This introduces a RCU read critical section, which could be + * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know + * this. */ rcu_irq_enter_irqson(); - ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL); + rcu_read_lock(); + ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL); + rcu_read_unlock(); rcu_irq_exit_irqson(); return notifier_to_errno(ret); @@ -33,10 +46,13 @@ static int cpu_pm_notify(enum cpu_pm_event event) static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event event_down) { + unsigned long flags; int ret; rcu_irq_enter_irqson(); - ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL); + raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags); + ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL); + raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags); rcu_irq_exit_irqson(); return notifier_to_errno(ret); @@ -49,12 +65,17 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev * Add a driver to a list of drivers that are notified about * CPU and CPU cluster low power entry and exit. * - * This function may sleep, and has the same return conditions as - * raw_notifier_chain_register. + * This function has the same return conditions as raw_notifier_chain_register. */ int cpu_pm_register_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_register(&cpu_pm_notifier_chain, nb); + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags); + ret = raw_notifier_chain_register(&cpu_pm_notifier.chain, nb); + raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags); + return ret; } EXPORT_SYMBOL_GPL(cpu_pm_register_notifier); @@ -64,12 +85,17 @@ EXPORT_SYMBOL_GPL(cpu_pm_register_notifier); * * Remove a driver from the CPU PM notifier list. * - * This function may sleep, and has the same return conditions as - * raw_notifier_chain_unregister. + * This function has the same return conditions as raw_notifier_chain_unregister. */ int cpu_pm_unregister_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&cpu_pm_notifier_chain, nb); + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags); + ret = raw_notifier_chain_unregister(&cpu_pm_notifier.chain, nb); + raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags); + return ret; } EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier); diff --git a/kernel/fork.c b/kernel/fork.c index bc94b2cc59..44f4c2d837 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -828,10 +828,10 @@ void __init fork_init(void) for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, task_rlimit(&init_task, RLIMIT_NPROC)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, task_rlimit(&init_task, RLIMIT_MSGQUEUE)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, task_rlimit(&init_task, RLIMIT_SIGPENDING)); - set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, task_rlimit(&init_task, RLIMIT_MEMLOCK)); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index 4d2a702d7a..c43e2ac2f8 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -799,12 +799,14 @@ static int __init irq_timings_test_irqs(struct timings_intervals *ti) __irq_timings_store(irq, irqs, ti->intervals[i]); if (irqs->circ_timings[i & IRQ_TIMINGS_MASK] != index) { + ret = -EBADSLT; pr_err("Failed to store in the circular buffer\n"); goto out; } } if (irqs->count != ti->count) { + ret = -ERANGE; pr_err("Count differs\n"); goto out; } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index d2df5e68b5..fb30e1436d 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -928,7 +928,6 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) { struct mutex_waiter waiter; - bool first = false; struct ww_mutex *ww; int ret; @@ -1007,6 +1006,8 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas set_current_state(state); for (;;) { + bool first; + /* * Once we hold wait_lock, we're serialized against * mutex_unlock() handing the lock off to us, do a trylock @@ -1035,15 +1036,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas spin_unlock(&lock->wait_lock); schedule_preempt_disabled(); - /* - * ww_mutex needs to always recheck its position since its waiter - * list is not FIFO ordered. - */ - if (ww_ctx || !first) { - first = __mutex_waiter_is_first(lock, &waiter); - if (first) - __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); - } + first = __mutex_waiter_is_first(lock, &waiter); + if (first) + __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); set_current_state(state); /* diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 0f4530b3a8..a332ccd829 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -170,7 +170,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, /* Compute the cost of each performance state. */ fmax = (u64) table[nr_states - 1].frequency; for (i = 0; i < nr_states; i++) { - table[i].cost = div64_u64(fmax * table[i].power, + unsigned long power_res = em_scale_power(table[i].power); + + table[i].cost = div64_u64(fmax * power_res, table[i].frequency); } diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 6c76988cc0..0e7a60706d 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -7,6 +7,8 @@ * Author: Paul E. McKenney */ +#include + ////////////////////////////////////////////////////////////////////////////// // // Controlling CPU stall warnings, including delay calculation. @@ -267,8 +269,10 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) struct task_struct *ts[8]; lockdep_assert_irqs_disabled(); - if (!rcu_preempt_blocked_readers_cgp(rnp)) + if (!rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; + } pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", rnp->level, rnp->grplo, rnp->grphi); t = list_entry(rnp->gp_tasks->prev, @@ -280,8 +284,8 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) break; } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - for (i--; i; i--) { - t = ts[i]; + while (i) { + t = ts[--i]; if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr)) pr_cont(" P%d", t->pid); else @@ -696,6 +700,14 @@ static void check_cpu_stall(struct rcu_data *rdp) (READ_ONCE(rnp->qsmask) & rdp->grpmask) && cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like an RCU stall. Check to see if the host + * stopped the vm. + */ + if (kvm_check_and_clear_guest_paused()) + return; + /* We haven't checked in, so go dump stack. */ print_cpu_stall(gps); if (READ_ONCE(rcu_cpu_stall_ftrace_dump)) @@ -705,6 +717,14 @@ static void check_cpu_stall(struct rcu_data *rdp) ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like an RCU stall. Check to see if the host + * stopped the vm. + */ + if (kvm_check_and_clear_guest_paused()) + return; + /* They had a few time units to dump stack, so complain. */ print_other_cpu_stall(gs2, gps); if (READ_ONCE(rcu_cpu_stall_ftrace_dump)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 20ffcc0441..a2403432f3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -237,9 +237,30 @@ static DEFINE_MUTEX(sched_core_mutex); static atomic_t sched_core_count; static struct cpumask sched_core_mask; +static void sched_core_lock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t, i = 0; + + local_irq_save(*flags); + for_each_cpu(t, smt_mask) + raw_spin_lock_nested(&cpu_rq(t)->__lock, i++); +} + +static void sched_core_unlock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t; + + for_each_cpu(t, smt_mask) + raw_spin_unlock(&cpu_rq(t)->__lock); + local_irq_restore(*flags); +} + static void __sched_core_flip(bool enabled) { - int cpu, t, i; + unsigned long flags; + int cpu, t; cpus_read_lock(); @@ -250,19 +271,12 @@ static void __sched_core_flip(bool enabled) for_each_cpu(cpu, &sched_core_mask) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); - i = 0; - local_irq_disable(); - for_each_cpu(t, smt_mask) { - /* supports up to SMT8 */ - raw_spin_lock_nested(&cpu_rq(t)->__lock, i++); - } + sched_core_lock(cpu, &flags); for_each_cpu(t, smt_mask) cpu_rq(t)->core_enabled = enabled; - for_each_cpu(t, smt_mask) - raw_spin_unlock(&cpu_rq(t)->__lock); - local_irq_enable(); + sched_core_unlock(cpu, &flags); cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask); } @@ -1619,6 +1633,23 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) uclamp_rq_dec_id(rq, p, clamp_id); } +static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p, + enum uclamp_id clamp_id) +{ + if (!p->uclamp[clamp_id].active) + return; + + uclamp_rq_dec_id(rq, p, clamp_id); + uclamp_rq_inc_id(rq, p, clamp_id); + + /* + * Make sure to clear the idle flag if we've transiently reached 0 + * active tasks on rq. + */ + if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE)) + rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; +} + static inline void uclamp_update_active(struct task_struct *p) { @@ -1642,12 +1673,8 @@ uclamp_update_active(struct task_struct *p) * affecting a valid clamp bucket, the next time it's enqueued, * it will already see the updated clamp bucket value. */ - for_each_clamp_id(clamp_id) { - if (p->uclamp[clamp_id].active) { - uclamp_rq_dec_id(rq, p, clamp_id); - uclamp_rq_inc_id(rq, p, clamp_id); - } - } + for_each_clamp_id(clamp_id) + uclamp_rq_reinc_id(rq, p, clamp_id); task_rq_unlock(rq, p, &rf); } @@ -5736,35 +5763,109 @@ void queue_core_balance(struct rq *rq) queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance); } -static inline void sched_core_cpu_starting(unsigned int cpu) +static void sched_core_cpu_starting(unsigned int cpu) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); - struct rq *rq, *core_rq = NULL; - int i; + struct rq *rq = cpu_rq(cpu), *core_rq = NULL; + unsigned long flags; + int t; - core_rq = cpu_rq(cpu)->core; + sched_core_lock(cpu, &flags); - if (!core_rq) { - for_each_cpu(i, smt_mask) { - rq = cpu_rq(i); - if (rq->core && rq->core == rq) - core_rq = rq; - } + WARN_ON_ONCE(rq->core != rq); - if (!core_rq) - core_rq = cpu_rq(cpu); + /* if we're the first, we'll be our own leader */ + if (cpumask_weight(smt_mask) == 1) + goto unlock; - for_each_cpu(i, smt_mask) { - rq = cpu_rq(i); - - WARN_ON_ONCE(rq->core && rq->core != core_rq); - rq->core = core_rq; + /* find the leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + rq = cpu_rq(t); + if (rq->core == rq) { + core_rq = rq; + break; } } + + if (WARN_ON_ONCE(!core_rq)) /* whoopsie */ + goto unlock; + + /* install and validate core_rq */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); + + if (t == cpu) + rq->core = core_rq; + + WARN_ON_ONCE(rq->core != core_rq); + } + +unlock: + sched_core_unlock(cpu, &flags); } + +static void sched_core_cpu_deactivate(unsigned int cpu) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + struct rq *rq = cpu_rq(cpu), *core_rq = NULL; + unsigned long flags; + int t; + + sched_core_lock(cpu, &flags); + + /* if we're the last man standing, nothing to do */ + if (cpumask_weight(smt_mask) == 1) { + WARN_ON_ONCE(rq->core != rq); + goto unlock; + } + + /* if we're not the leader, nothing to do */ + if (rq->core != rq) + goto unlock; + + /* find a new leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + core_rq = cpu_rq(t); + break; + } + + if (WARN_ON_ONCE(!core_rq)) /* impossible */ + goto unlock; + + /* copy the shared state to the new leader */ + core_rq->core_task_seq = rq->core_task_seq; + core_rq->core_pick_seq = rq->core_pick_seq; + core_rq->core_cookie = rq->core_cookie; + core_rq->core_forceidle = rq->core_forceidle; + core_rq->core_forceidle_seq = rq->core_forceidle_seq; + + /* install new leader */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); + rq->core = core_rq; + } + +unlock: + sched_core_unlock(cpu, &flags); +} + +static inline void sched_core_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->core != rq) + rq->core = rq; +} + #else /* !CONFIG_SCHED_CORE */ static inline void sched_core_cpu_starting(unsigned int cpu) {} +static inline void sched_core_cpu_deactivate(unsigned int cpu) {} +static inline void sched_core_cpu_dying(unsigned int cpu) {} static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) @@ -8707,6 +8808,8 @@ int sched_cpu_deactivate(unsigned int cpu) */ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) static_branch_dec_cpuslocked(&sched_smt_present); + + sched_core_cpu_deactivate(cpu); #endif if (!sched_smp_initialized) @@ -8811,6 +8914,7 @@ int sched_cpu_dying(unsigned int cpu) calc_load_migrate(rq); update_max_interval(); hrtick_clear(rq); + sched_core_cpu_dying(cpu); return 0; } #endif @@ -9022,7 +9126,7 @@ void __init sched_init(void) atomic_set(&rq->nr_iowait, 0); #ifdef CONFIG_SCHED_CORE - rq->core = NULL; + rq->core = rq; rq->core_pick = NULL; rq->core_enabled = 0; rq->core_tree = RB_ROOT; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index aaacd6cfd4..e94314633b 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1733,6 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused */ raw_spin_rq_lock(rq); if (p->dl.dl_non_contending) { + update_rq_clock(rq); sub_running_bw(&p->dl, &rq->dl); p->dl.dl_non_contending = 0; /* @@ -2741,7 +2742,7 @@ void __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_runtime = attr->sched_runtime; dl_se->dl_deadline = attr->sched_deadline; dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; - dl_se->flags = attr->sched_flags; + dl_se->flags = attr->sched_flags & SCHED_DL_FLAGS; dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime); } @@ -2754,7 +2755,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr) attr->sched_runtime = dl_se->dl_runtime; attr->sched_deadline = dl_se->dl_deadline; attr->sched_period = dl_se->dl_period; - attr->sched_flags = dl_se->flags; + attr->sched_flags &= ~SCHED_DL_FLAGS; + attr->sched_flags |= dl_se->flags; } /* @@ -2851,7 +2853,7 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) if (dl_se->dl_runtime != attr->sched_runtime || dl_se->dl_deadline != attr->sched_deadline || dl_se->dl_period != attr->sched_period || - dl_se->flags != attr->sched_flags) + dl_se->flags != (attr->sched_flags & SCHED_DL_FLAGS)) return true; return false; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 0c5ec2776d..7e08e3d947 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -388,6 +388,13 @@ void update_sched_domain_debugfs(void) { int cpu, i; + /* + * This can unfortunately be invoked before sched_debug_init() creates + * the debug directory. Don't touch sd_sysctl_cpus until then. + */ + if (!debugfs_sched) + return; + if (!cpumask_available(sd_sysctl_cpus)) { if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL)) return; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 44c452072a..30a6984a58 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1486,7 +1486,7 @@ static inline bool is_core_idle(int cpu) if (cpu == sibling) continue; - if (!idle_cpu(cpu)) + if (!idle_cpu(sibling)) return false; } #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 14a41a243f..d53d197708 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -227,6 +227,8 @@ static inline void update_avg(u64 *avg, u64 sample) */ #define SCHED_FLAG_SUGOV 0x10000000 +#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV) + static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se) { #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL @@ -1093,7 +1095,7 @@ struct rq { unsigned int core_sched_seq; struct rb_root core_tree; - /* shared state */ + /* shared state -- careful with sched_core_cpu_deactivate() */ unsigned int core_task_seq; unsigned int core_pick_seq; unsigned long core_cookie; @@ -2255,6 +2257,9 @@ static inline struct task_struct *get_push_task(struct rq *rq) if (p->nr_cpus_allowed == 1) return NULL; + if (p->migration_disabled) + return NULL; + rq->push_busy = true; return get_task_struct(p); } diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index b77ad49dc1..4e8698e62f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1482,6 +1482,8 @@ int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; + +static unsigned long __read_mostly *sched_numa_onlined_nodes; #endif /* @@ -1833,6 +1835,16 @@ void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; for_each_node(k) { + /* + * Distance information can be unreliable for + * offline nodes, defer building the node + * masks to its bringup. + * This relies on all unique distance values + * still being visible at init time. + */ + if (!node_online(j)) + continue; + if (sched_debug() && (node_distance(j, k) != node_distance(k, j))) sched_numa_warn("Node-distance not symmetric"); @@ -1886,6 +1898,53 @@ void sched_init_numa(void) sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1]; init_numa_topology_type(); + + sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL); + if (!sched_numa_onlined_nodes) + return; + + bitmap_zero(sched_numa_onlined_nodes, nr_node_ids); + for_each_online_node(i) + bitmap_set(sched_numa_onlined_nodes, i, 1); +} + +static void __sched_domains_numa_masks_set(unsigned int node) +{ + int i, j; + + /* + * NUMA masks are not built for offline nodes in sched_init_numa(). + * Thus, when a CPU of a never-onlined-before node gets plugged in, + * adding that new CPU to the right NUMA masks is not sufficient: the + * masks of that CPU's node must also be updated. + */ + if (test_bit(node, sched_numa_onlined_nodes)) + return; + + bitmap_set(sched_numa_onlined_nodes, node, 1); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (!node_online(j) || node == j) + continue; + + if (node_distance(j, node) > sched_domains_numa_distance[i]) + continue; + + /* Add remote nodes in our masks */ + cpumask_or(sched_domains_numa_masks[i][node], + sched_domains_numa_masks[i][node], + sched_domains_numa_masks[0][j]); + } + } + + /* + * A new node has been brought up, potentially changing the topology + * classification. + * + * Note that this is racy vs any use of sched_numa_topology_type :/ + */ + init_numa_topology_type(); } void sched_domains_numa_masks_set(unsigned int cpu) @@ -1893,8 +1952,14 @@ void sched_domains_numa_masks_set(unsigned int cpu) int node = cpu_to_node(cpu); int i, j; + __sched_domains_numa_masks_set(node); + for (i = 0; i < sched_domains_numa_levels; i++) { for (j = 0; j < nr_node_ids; j++) { + if (!node_online(j)) + continue; + + /* Set ourselves in the remote node's masks */ if (node_distance(j, node) <= sched_domains_numa_distance[i]) cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 4a66725b1d..5af7584734 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -758,22 +758,6 @@ static void hrtimer_switch_to_hres(void) retrigger_next_event(NULL); } -static void clock_was_set_work(struct work_struct *work) -{ - clock_was_set(); -} - -static DECLARE_WORK(hrtimer_work, clock_was_set_work); - -/* - * Called from timekeeping and resume code to reprogram the hrtimer - * interrupt device on all cpus. - */ -void clock_was_set_delayed(void) -{ - schedule_work(&hrtimer_work); -} - #else static inline int hrtimer_is_hres_enabled(void) { return 0; } @@ -891,6 +875,22 @@ void clock_was_set(void) timerfd_clock_was_set(); } +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + +/* + * Called from timekeeping and resume code to reprogram the hrtimer + * interrupt device on all cpus and to notify timerfd. + */ +void clock_was_set_delayed(void) +{ + schedule_work(&hrtimer_work); +} + /* * During resume we might have to reprogram the high resolution timer * interrupt on all online CPUs. However, all other CPUs will be @@ -1030,12 +1030,13 @@ static void __remove_hrtimer(struct hrtimer *timer, * remove hrtimer, called with base lock held */ static inline int -remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) +remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, + bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { - int reprogram; + bool reprogram; /* * Remove the timer and force reprogramming when high @@ -1048,8 +1049,16 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); + /* + * If the timer is not restarted then reprogramming is + * required if the timer is local. If it is local and about + * to be restarted, avoid programming it twice (on removal + * and a moment later when it's requeued). + */ if (!restart) state = HRTIMER_STATE_INACTIVE; + else + reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; @@ -1103,9 +1112,31 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, struct hrtimer_clock_base *base) { struct hrtimer_clock_base *new_base; + bool force_local, first; - /* Remove an active timer from the queue: */ - remove_hrtimer(timer, base, true); + /* + * If the timer is on the local cpu base and is the first expiring + * timer then this might end up reprogramming the hardware twice + * (on removal and on enqueue). To avoid that by prevent the + * reprogram on removal, keep the timer local to the current CPU + * and enforce reprogramming after it is queued no matter whether + * it is the new first expiring timer again or not. + */ + force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); + force_local &= base->cpu_base->next_timer == timer; + + /* + * Remove an active timer from the queue. In case it is not queued + * on the current CPU, make sure that remove_hrtimer() updates the + * remote data correctly. + * + * If it's on the current CPU and the first expiring timer, then + * skip reprogramming, keep the timer local and enforce + * reprogramming later if it was the first expiring timer. This + * avoids programming the underlying clock event twice (once at + * removal and once after enqueue). + */ + remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); @@ -1115,9 +1146,24 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ - new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + if (!force_local) { + new_base = switch_hrtimer_base(timer, base, + mode & HRTIMER_MODE_PINNED); + } else { + new_base = base; + } - return enqueue_hrtimer(timer, new_base, mode); + first = enqueue_hrtimer(timer, new_base, mode); + if (!force_local) + return first; + + /* + * Timer was forced to stay on the current CPU to avoid + * reprogramming on removal and enqueue. Force reprogram the + * hardware by evaluating the new first expiring timer. + */ + hrtimer_force_reprogram(new_base->cpu_base, 1); + return 0; } /** @@ -1183,7 +1229,7 @@ int hrtimer_try_to_cancel(struct hrtimer *timer) base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) - ret = remove_hrtimer(timer, base, false); + ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 29a5e54e6e..a002685f68 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -991,6 +991,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) if (!p) goto out; + /* Protect timer list r/w in arm_timer() */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) + goto out; + /* * Fetch the current sample and update the timer's expiry time. */ @@ -1001,11 +1006,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) bump_cpu_timer(timer, now); - /* Protect timer list r/w in arm_timer() */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) - goto out; - /* * Now re-arm for the new expiry time. */ @@ -1346,8 +1346,6 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, } } - if (!*newval) - return; *newval += now; } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 6a742a29e5..cd610faa25 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -165,3 +165,6 @@ DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); void timer_clear_idle(void); + +void clock_was_set(void); +void clock_was_set_delayed(void); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d567b1717c..3ee23f4d43 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -219,6 +219,11 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +config DYNAMIC_FTRACE_WITH_ARGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 33899a71fd..a1adb29ef5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2897,14 +2897,26 @@ int tracepoint_printk_sysctl(struct ctl_table *table, int write, void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { + enum event_trigger_type tt = ETT_NONE; + struct trace_event_file *file = fbuffer->trace_file; + + if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, + fbuffer->entry, &tt)) + goto discard; + if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); if (static_branch_unlikely(&trace_event_exports_enabled)) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); - event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, - fbuffer->event, fbuffer->entry, - fbuffer->trace_ctx, fbuffer->regs); + + trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, + fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); + +discard: + if (tt) + event_triggers_post_call(file, tt); + } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a180abf76d..4a0e693000 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1389,38 +1389,6 @@ event_trigger_unlock_commit(struct trace_event_file *file, event_triggers_post_call(file, tt); } -/** - * event_trigger_unlock_commit_regs - handle triggers and finish event commit - * @file: The file pointer associated with the event - * @buffer: The ring buffer that the event is being written to - * @event: The event meta data in the ring buffer - * @entry: The event itself - * @trace_ctx: The tracing context flags. - * - * This is a helper function to handle triggers that require data - * from the event itself. It also tests the event against filters and - * if the event is soft disabled and should be discarded. - * - * Same as event_trigger_unlock_commit() but calls - * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). - */ -static inline void -event_trigger_unlock_commit_regs(struct trace_event_file *file, - struct trace_buffer *buffer, - struct ring_buffer_event *event, - void *entry, unsigned int trace_ctx, - struct pt_regs *regs) -{ - enum event_trigger_type tt = ETT_NONE; - - if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit_regs(file->tr, buffer, event, - trace_ctx, regs); - - if (tt) - event_triggers_post_call(file, tt); -} - #define FILTER_PRED_INVALID ((unsigned short)-1) #define FILTER_PRED_IS_RIGHT (1 << 15) #define FILTER_PRED_FOLD (1 << 15) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 949ef09dc5..a48aa2a287 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3430,6 +3430,8 @@ trace_action_create_field_var(struct hist_trigger_data *hist_data, event = data->match_data.event; } + if (!event) + goto free; /* * At this point, we're looking at a field on another * event. Because we can't modify a hist trigger on diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index a7e3c24dee..b61eefe5cc 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -253,10 +253,40 @@ static struct osnoise_data { */ static bool osnoise_busy; +#ifdef CONFIG_PREEMPT_RT /* * Print the osnoise header info. */ static void print_osnoise_headers(struct seq_file *s) +{ + if (osnoise_data.tainted) + seq_puts(s, "# osnoise is tainted!\n"); + + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + + seq_puts(s, "# |||||| / "); + seq_puts(s, " MAX\n"); + + seq_puts(s, "# ||||| / "); + seq_puts(s, " SINGLE Interference counters:\n"); + + seq_puts(s, "# ||||||| RUNTIME "); + seq_puts(s, " NOISE %% OF CPU NOISE +-----------------------------+\n"); + + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP IN US "); + seq_puts(s, " IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD\n"); + + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | | | | | | | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ +static void print_osnoise_headers(struct seq_file *s) { if (osnoise_data.tainted) seq_puts(s, "# osnoise is tainted!\n"); @@ -279,6 +309,7 @@ static void print_osnoise_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | | | | | | | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * osnoise_taint - report an osnoise error. @@ -323,6 +354,24 @@ static void trace_osnoise_sample(struct osnoise_sample *sample) /* * Print the timerlat header info. */ +#ifdef CONFIG_PREEMPT_RT +static void print_timerlat_headers(struct seq_file *s) +{ + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + seq_puts(s, "# |||||| /\n"); + seq_puts(s, "# ||||||| ACTIVATION\n"); + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP ID "); + seq_puts(s, " CONTEXT LATENCY\n"); + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ static void print_timerlat_headers(struct seq_file *s) { seq_puts(s, "# _-----=> irqs-off\n"); @@ -336,6 +385,7 @@ static void print_timerlat_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * Record an timerlat_sample into the tracer buffer. @@ -1025,9 +1075,13 @@ diff_osn_sample_stats(struct osnoise_variables *osn_var, struct osnoise_sample * /* * osnoise_stop_tracing - Stop tracing and the tracer. */ -static void osnoise_stop_tracing(void) +static __always_inline void osnoise_stop_tracing(void) { struct trace_array *tr = osnoise_trace; + + trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, + "stop tracing hit on cpu %d\n", smp_processor_id()); + tracer_tracing_off(tr); } diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c index 3c63710c20..bc81419f40 100644 --- a/lib/mpi/mpiutil.c +++ b/lib/mpi/mpiutil.c @@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(mpi_const); /**************** * Note: It was a bad idea to use the number of limbs to allocate * because on a alpha the limbs are large but we normally need - * integers of n bits - So we should chnage this to bits (or bytes). + * integers of n bits - So we should change this to bits (or bytes). * * But mpi_alloc is used in a lot of places :-) */ @@ -148,7 +148,7 @@ int mpi_resize(MPI a, unsigned nlimbs) return 0; /* no need to do it */ if (a->d) { - p = kmalloc_array(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL); + p = kcalloc(nlimbs, sizeof(mpi_limb_t), GFP_KERNEL); if (!p) return -ENOMEM; memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t)); diff --git a/lib/test_scanf.c b/lib/test_scanf.c index 84fe09eaf5..abae888489 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -271,7 +271,7 @@ static u32 __init next_test_random(u32 max_bits) { u32 n_bits = hweight32(prandom_u32_state(&rnd_state)) % (max_bits + 1); - return prandom_u32_state(&rnd_state) & (UINT_MAX >> (32 - n_bits)); + return prandom_u32_state(&rnd_state) & GENMASK(n_bits, 0); } static unsigned long long __init next_test_random_ull(void) @@ -280,7 +280,7 @@ static unsigned long long __init next_test_random_ull(void) u32 n_bits = (hweight32(rand1) * 3) % 64; u64 val = (u64)prandom_u32_state(&rnd_state) * rand1; - return val & (ULLONG_MAX >> (64 - n_bits)); + return val & GENMASK_ULL(n_bits, 0); } #define random_for_type(T) \ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dfc940d522..8ea35ba669 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2476,7 +2476,7 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, if (!rc) { /* * This indicates there is an entry in the reserve map - * added by alloc_huge_page. We know it was added + * not added by alloc_huge_page. We know it was added * before the alloc_huge_page call, otherwise * HPageRestoreReserve would be set on the page. * Remove the entry so that a subsequent allocation @@ -4660,7 +4660,9 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: - restore_reserve_on_error(h, vma, haddr, new_page); + /* No restore in case of successful pagetable update (Break COW) */ + if (new_page != old_page) + restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); out_release_old: put_page(old_page); @@ -4776,7 +4778,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); - bool new_page = false; + bool new_page, new_pagecache_page = false; /* * Currently, we are forced to kill the process in the event the @@ -4799,6 +4801,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, goto out; retry: + new_page = false; page = find_lock_page(mapping, idx); if (!page) { /* Check for page in userfault range */ @@ -4842,6 +4845,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, goto retry; goto out; } + new_pagecache_page = true; } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { @@ -4926,7 +4930,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, spin_unlock(ptl); backout_unlocked: unlock_page(page); - restore_reserve_on_error(h, vma, haddr, page); + /* restore reserve for newly allocated pages not in page cache */ + if (new_page && !new_pagecache_page) + restore_reserve_on_error(h, vma, haddr, page); put_page(page); goto out; } @@ -5135,6 +5141,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, int ret = -ENOMEM; struct page *page; int writable; + bool new_pagecache_page = false; if (is_continue) { ret = -EFAULT; @@ -5228,6 +5235,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, ret = huge_add_to_page_cache(page, mapping, idx); if (ret) goto out_release_nounlock; + new_pagecache_page = true; } ptl = huge_pte_lockptr(h, dst_mm, dst_pte); @@ -5291,7 +5299,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: - restore_reserve_on_error(h, dst_vma, dst_addr, page); + if (!new_pagecache_page) + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index eefd823deb..470400cc75 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1146,7 +1146,7 @@ static int __get_hwpoison_page(struct page *page) * unexpected races caused by taking a page refcount. */ if (!HWPoisonHandlable(head)) - return 0; + return -EBUSY; if (PageTransHuge(head)) { /* @@ -1199,9 +1199,15 @@ static int get_any_page(struct page *p, unsigned long flags) } goto out; } else if (ret == -EBUSY) { - /* We raced with freeing huge page to buddy, retry. */ - if (pass++ < 3) + /* + * We raced with (possibly temporary) unhandlable + * page, retry. + */ + if (pass++ < 3) { + shake_page(p, 1); goto try_again; + } + ret = -EIO; goto out; } } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8cb75b26ea..86c3af79e8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1731,6 +1731,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); memory_notify(MEM_CANCEL_OFFLINE, &arg); failed_removal_pcplists_disabled: + lru_cache_enable(); zone_pcp_enable(zone); failed_removal: pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n", diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 856b175c15..eeb3a9cb36 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3453,19 +3453,10 @@ void free_unref_page_list(struct list_head *list) * comment in free_unref_page. */ migratetype = get_pcppage_migratetype(page); - if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { - if (unlikely(is_migrate_isolate(migratetype))) { - list_del(&page->lru); - free_one_page(page_zone(page), page, pfn, 0, - migratetype, FPI_NONE); - continue; - } - - /* - * Non-isolated types over MIGRATE_PCPTYPES get added - * to the MIGRATE_MOVABLE pcp list. - */ - set_pcppage_migratetype(page, MIGRATE_MOVABLE); + if (unlikely(is_migrate_isolate(migratetype))) { + list_del(&page->lru); + free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE); + continue; } set_page_private(page, pfn); @@ -3475,7 +3466,15 @@ void free_unref_page_list(struct list_head *list) list_for_each_entry_safe(page, next, list, lru) { pfn = page_private(page); set_page_private(page, 0); + + /* + * Non-isolated types over MIGRATE_PCPTYPES get added + * to the MIGRATE_MOVABLE pcp list. + */ migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) + migratetype = MIGRATE_MOVABLE; + trace_mm_page_free_batched(page); free_unref_page_commit(page, pfn, migratetype, 0); diff --git a/mm/shmem.c b/mm/shmem.c index 70d9ce294b..dacda7463d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1696,8 +1696,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; - struct swap_info_struct *si; - struct page *page = NULL; + struct page *page; swp_entry_t swap; int error; @@ -1705,12 +1704,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap = radix_to_swp_entry(*pagep); *pagep = NULL; - /* Prevent swapoff from happening to us. */ - si = get_swap_device(swap); - if (!si) { - error = EINVAL; - goto failed; - } /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { @@ -1772,8 +1765,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap_free(swap); *pagep = page; - if (si) - put_swap_device(si); return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) @@ -1784,9 +1775,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, put_page(page); } - if (si) - put_swap_device(si); - return error; } diff --git a/mm/swap_state.c b/mm/swap_state.c index c56aa9ac05..bc7cee6b2e 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -628,13 +628,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, if (!mask) goto skip; - /* Test swap type to make sure the dereference is safe */ - if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) { - struct inode *inode = si->swap_file->f_mapping->host; - if (inode_read_congested(inode)) - goto skip; - } - do_poll = false; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; diff --git a/mm/vmscan.c b/mm/vmscan.c index 4620df62f0..eeae2f6bc5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -100,9 +100,12 @@ struct scan_control { unsigned int may_swap:1; /* - * Cgroups are not reclaimed below their configured memory.low, - * unless we threaten to OOM. If any cgroups are skipped due to - * memory.low and nothing was reclaimed, go back for memory.low. + * Cgroup memory below memory.low is protected as long as we + * don't threaten to OOM. If any cgroup is reclaimed at + * reduced force or passed over entirely due to its memory.low + * setting (memcg_low_skipped), and nothing is reclaimed as a + * result, then go back for one more cycle that reclaims the protected + * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; @@ -2537,15 +2540,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; + unsigned long low, min; unsigned long scan; - unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(sc->target_mem_cgroup, - memcg, - sc->memcg_low_reclaim); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); - if (protection) { + if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min @@ -2576,6 +2578,15 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); + unsigned long protection; + + /* memory.low scaling, make sure we retry before OOM */ + if (!sc->memcg_low_reclaim && low > min) { + protection = low; + sc->memcg_low_skipped = 1; + } else { + protection = min; + } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); @@ -4413,11 +4424,13 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; + unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); + psi_memstall_enter(&pflags); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP @@ -4442,6 +4455,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in current->flags &= ~PF_SWAPWRITE; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); + psi_memstall_leave(&pflags); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c index 1c140af06d..600b9563bf 100644 --- a/net/6lowpan/debugfs.c +++ b/net/6lowpan/debugfs.c @@ -170,7 +170,8 @@ static void lowpan_dev_debugfs_ctx_init(struct net_device *dev, struct dentry *root; char buf[32]; - WARN_ON_ONCE(id > LOWPAN_IPHC_CTX_TABLE_SIZE); + if (WARN_ON_ONCE(id >= LOWPAN_IPHC_CTX_TABLE_SIZE)) + return; sprintf(buf, "%d", id); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e1a545c8a6..4c25bcd1ac 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1343,6 +1343,12 @@ int hci_inquiry(void __user *arg) goto done; } + /* Restrict maximum inquiry length to 60 seconds */ + if (ir.length > 60) { + err = -EINVAL; + goto done; + } + hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { @@ -1727,6 +1733,14 @@ int hci_dev_do_close(struct hci_dev *hdev) hci_request_cancel_all(hdev); hci_req_sync_lock(hdev); + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + test_bit(HCI_UP, &hdev->flags)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + hdev->shutdown(hdev); + } + if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { cancel_delayed_work_sync(&hdev->cmd_timer); hci_req_sync_unlock(hdev); @@ -1798,14 +1812,6 @@ int hci_dev_do_close(struct hci_dev *hdev) clear_bit(HCI_INIT, &hdev->flags); } - if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - test_bit(HCI_UP, &hdev->flags)) { - /* Execute vendor specific shutdown routine */ - if (hdev->shutdown) - hdev->shutdown(hdev); - } - /* flush cmd work */ flush_work(&hdev->cmd_work); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 3bd41563f1..b5ab842c7c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -85,7 +85,6 @@ static void sco_sock_timeout(struct timer_list *t) sk->sk_state_change(sk); bh_unlock_sock(sk); - sco_sock_kill(sk); sock_put(sk); } @@ -177,7 +176,6 @@ static void sco_conn_del(struct hci_conn *hcon, int err) sco_sock_clear_timer(sk); sco_chan_del(sk, err); bh_unlock_sock(sk); - sco_sock_kill(sk); sock_put(sk); } @@ -310,7 +308,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) if (!sk) goto drop; - BT_DBG("sk %p len %d", sk, skb->len); + BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; @@ -394,8 +392,7 @@ static void sco_sock_cleanup_listen(struct sock *parent) */ static void sco_sock_kill(struct sock *sk) { - if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || - sock_flag(sk, SOCK_DEAD)) + if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); @@ -447,7 +444,6 @@ static void sco_sock_close(struct sock *sk) lock_sock(sk); __sco_sock_close(sk); release_sock(sk); - sco_sock_kill(sk); } static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg, @@ -773,6 +769,11 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; + default: + /* use CVSD settings as fallback */ + cp.max_latency = cpu_to_le16(0xffff); + cp.retrans_effort = 0xff; + break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, @@ -905,7 +906,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, opts.mtu = sco_pi(sk)->conn->mtu; - BT_DBG("mtu %d", opts.mtu); + BT_DBG("mtu %u", opts.mtu); len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) @@ -1167,7 +1168,7 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; - BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); + BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; @@ -1196,7 +1197,7 @@ void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) if (!conn) goto drop; - BT_DBG("conn %p len %d", conn, skb->len); + BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); diff --git a/net/core/devlink.c b/net/core/devlink.c index 85032626de..5a85a7b0fe 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3801,10 +3801,12 @@ static void devlink_param_notify(struct devlink *devlink, struct devlink_param_item *param_item, enum devlink_command cmd); -static void devlink_reload_netns_change(struct devlink *devlink, - struct net *dest_net) +static void devlink_ns_change_notify(struct devlink *devlink, + struct net *dest_net, struct net *curr_net, + bool new) { struct devlink_param_item *param_item; + enum devlink_command cmd; /* Userspace needs to be notified about devlink objects * removed from original and entering new network namespace. @@ -3812,17 +3814,18 @@ static void devlink_reload_netns_change(struct devlink *devlink, * reload process so the notifications are generated separatelly. */ - list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_DEL); - devlink_notify(devlink, DEVLINK_CMD_DEL); + if (!dest_net || net_eq(dest_net, curr_net)) + return; - __devlink_net_set(devlink, dest_net); + if (new) + devlink_notify(devlink, DEVLINK_CMD_NEW); - devlink_notify(devlink, DEVLINK_CMD_NEW); + cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL; list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, cmd); + + if (!new) + devlink_notify(devlink, DEVLINK_CMD_DEL); } static bool devlink_reload_supported(const struct devlink_ops *ops) @@ -3902,6 +3905,7 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, u32 *actions_performed, struct netlink_ext_ack *extack) { u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; int err; if (!devlink->reload_enabled) @@ -3909,18 +3913,22 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); + + curr_net = devlink_net(devlink); + devlink_ns_change_notify(devlink, dest_net, curr_net, false); err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); if (err) return err; - if (dest_net && !net_eq(dest_net, devlink_net(devlink))) - devlink_reload_netns_change(devlink, dest_net); + if (dest_net && !net_eq(dest_net, curr_net)) + __devlink_net_set(devlink, dest_net); err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); if (err) return err; + devlink_ns_change_notify(devlink, dest_net, curr_net, true); WARN_ON(!(*actions_performed & BIT(action))); /* Catch driver on updating the remote action within devlink reload */ WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, @@ -4117,7 +4125,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink, static void devlink_flash_update_begin_notify(struct devlink *devlink) { - struct devlink_flash_notify params = { 0 }; + struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE, @@ -4126,7 +4134,7 @@ static void devlink_flash_update_begin_notify(struct devlink *devlink) static void devlink_flash_update_end_notify(struct devlink *devlink) { - struct devlink_flash_notify params = { 0 }; + struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_END, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f6af3e74fc..662eb1c37f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2608,6 +2608,7 @@ static int do_setlink(const struct sk_buff *skb, return err; if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) { + const char *pat = ifname && ifname[0] ? ifname : NULL; struct net *net; int new_ifindex; @@ -2623,7 +2624,7 @@ static int do_setlink(const struct sk_buff *skb, else new_ifindex = 0; - err = __dev_change_net_namespace(dev, net, ifname, new_ifindex); + err = __dev_change_net_namespace(dev, net, pat, new_ifindex); put_net(net); if (err) goto errout; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 00bb89b2d8..970906eb5b 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -18,16 +18,6 @@ if NET_DSA # Drivers must select the appropriate tagging format(s) -config NET_DSA_TAG_8021Q - tristate - select VLAN_8021Q - help - Unlike the other tagging protocols, the 802.1Q config option simply - provides helpers for other tagging implementations that might rely on - VLAN in one way or another. It is not a complete solution. - - Drivers which use these helpers should select this as dependency. - config NET_DSA_TAG_AR9331 tristate "Tag driver for Atheros AR9331 SoC with built-in switch" help @@ -126,7 +116,6 @@ config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" depends on MSCC_OCELOT_SWITCH_LIB || \ (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) - select NET_DSA_TAG_8021Q help Say Y or M if you want to enable support for tagging frames with a custom VLAN-based header. Frames that require timestamping, such as @@ -149,7 +138,7 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - select NET_DSA_TAG_8021Q + depends on (NET_DSA_SJA1105 && NET_DSA_SJA1105_PTP) || !NET_DSA_SJA1105 || !NET_DSA_SJA1105_PTP select PACKING help Say Y or M if you want to enable support for tagging frames with the diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 44bc79952b..67ea009f24 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o +dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o tag_8021q.o # tagging formats -obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index f201c33980..cddf7cb0f3 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -234,8 +234,6 @@ int dsa_port_pre_bridge_flags(const struct dsa_port *dp, int dsa_port_bridge_flags(const struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); -int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct netlink_ext_ack *extack); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); diff --git a/net/dsa/port.c b/net/dsa/port.c index 28b45b7e66..23e30198a9 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -186,10 +186,6 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = dsa_port_mrouter(dp->cpu_dp, br_multicast_router(br), extack); - if (err && err != -EOPNOTSUPP) - return err; - err = dsa_port_ageing_time(dp, br_get_ageing_time(br)); if (err && err != -EOPNOTSUPP) return err; @@ -272,12 +268,6 @@ static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) /* VLAN filtering is handled by dsa_switch_bridge_leave */ - /* Some drivers treat the notification for having a local multicast - * router by allowing multicast to be flooded to the CPU, so we should - * allow this in standalone mode too. - */ - dsa_port_mrouter(dp->cpu_dp, true, NULL); - /* Ageing time may be global to the switch chip, so don't change it * here because we have no good reason (or value) to change it to. */ @@ -607,17 +597,6 @@ int dsa_port_bridge_flags(const struct dsa_port *dp, return ds->ops->port_bridge_flags(ds, dp->index, flags, extack); } -int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->port_set_mrouter) - return -EOPNOTSUPP; - - return ds->ops->port_set_mrouter(ds, dp->index, mrouter, extack); -} - int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, bool targeted_match) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 23be8e0102..b34116b15d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -314,12 +314,6 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; - case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: - if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) - return -EOPNOTSUPP; - - ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); - break; default: ret = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 4aa29f90ec..0d1db3e376 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -493,5 +493,3 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } EXPORT_SYMBOL_GPL(dsa_8021q_rcv); - -MODULE_LICENSE("GPL v2"); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 099259fc82..7fbd0b532f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -465,14 +465,16 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) if (!doi_def) return; - switch (doi_def->type) { - case CIPSO_V4_MAP_TRANS: - kfree(doi_def->map.std->lvl.cipso); - kfree(doi_def->map.std->lvl.local); - kfree(doi_def->map.std->cat.cipso); - kfree(doi_def->map.std->cat.local); - kfree(doi_def->map.std); - break; + if (doi_def->map.std) { + switch (doi_def->type) { + case CIPSO_V4_MAP_TRANS: + kfree(doi_def->map.std->lvl.cipso); + kfree(doi_def->map.std->lvl.local); + kfree(doi_def->map.std->cat.cipso); + kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); + break; + } } kfree(doi_def); } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 00576bae18..0c321996c6 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2720,6 +2720,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2730,6 +2731,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 12dca0c85f..95419b7adf 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -473,6 +473,8 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, static int gre_handle_offloads(struct sk_buff *skb, bool csum) { + if (csum && skb_checksum_start(skb) < skb->data) + return -EINVAL; return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 99c0694450..94e33d3eaf 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -586,28 +586,35 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe) } } -static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) +static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { - struct fib_nh_exception *fnhe, *oldest; + struct fib_nh_exception __rcu **fnhe_p, **oldest_p; + struct fib_nh_exception *fnhe, *oldest = NULL; - oldest = rcu_dereference(hash->chain); - for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; - fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) + for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { + fnhe = rcu_dereference_protected(*fnhe_p, + lockdep_is_held(&fnhe_lock)); + if (!fnhe) + break; + if (!oldest || + time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; + oldest_p = fnhe_p; + } } fnhe_flush_routes(oldest); - return oldest; + *oldest_p = oldest->fnhe_next; + kfree_rcu(oldest, rcu); } -static inline u32 fnhe_hashfun(__be32 daddr) +static u32 fnhe_hashfun(__be32 daddr) { - static u32 fnhe_hashrnd __read_mostly; - u32 hval; + static siphash_key_t fnhe_hash_key __read_mostly; + u64 hval; - net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32)daddr, fnhe_hashrnd); - return hash_32(hval, FNHE_HASH_SHIFT); + net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); + hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); + return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) @@ -676,16 +683,21 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, if (rt) fill_route_from_fnhe(rt, fnhe); } else { - if (depth > FNHE_RECLAIM_DEPTH) - fnhe = fnhe_oldest(hash); - else { - fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); - if (!fnhe) - goto out_unlock; + /* Randomize max depth to avoid some side channels attacks. */ + int max_depth = FNHE_RECLAIM_DEPTH + + prandom_u32_max(FNHE_RECLAIM_DEPTH); - fnhe->fnhe_next = hash->chain; - rcu_assign_pointer(hash->chain, fnhe); + while (depth > max_depth) { + fnhe_remove_oldest(hash); + depth--; } + + fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); + if (!fnhe) + goto out_unlock; + + fnhe->fnhe_next = hash->chain; + fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; @@ -693,6 +705,8 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); + rcu_assign_pointer(hash->chain, fnhe); + /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. @@ -3170,7 +3184,7 @@ static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; - udph->len = sizeof(struct udphdr); + udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a692626c19..db07c05736 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2451,6 +2451,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_seek_last_pos(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; + int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; @@ -2461,7 +2462,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) break; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_next(seq, NULL); - while (offset-- && rc) + while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; @@ -2472,7 +2473,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) if (st->bucket > tcp_hashinfo.ehash_mask) break; rc = established_get_first(seq); - while (offset-- && rc) + while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2d650dc243..ef75c9b05f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1341,7 +1341,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); - /* paired with smp_rmb() in rt6_get_cookie_safe() */ + /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { fn->fn_sernum = sernum; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index bc224f917b..7a5e90e093 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -629,6 +629,8 @@ static int gre_rcv(struct sk_buff *skb) static int gre_handle_offloads(struct sk_buff *skb, bool csum) { + if (csum && skb_checksum_start(skb) < skb->data) + return -EINVAL; return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b6ddf23d38..6033403021 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -1484,17 +1485,24 @@ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { - static u32 seed __read_mostly; - u32 val; + static siphash_key_t rt6_exception_key __read_mostly; + struct { + struct in6_addr dst; + struct in6_addr src; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .dst = *dst, + }; + u64 val; - net_get_random_once(&seed, sizeof(seed)); - val = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), seed); + net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) - val = jhash2((const u32 *)src, sizeof(*src)/sizeof(u32), val); + combined.src = *src; #endif - return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); + val = siphash(&combined, sizeof(combined), &rt6_exception_key); + + return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table @@ -1649,6 +1657,7 @@ static int rt6_insert_exception(struct rt6_info *nrt, struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; + int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); @@ -1703,7 +1712,9 @@ static int rt6_insert_exception(struct rt6_info *nrt, bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; - if (bucket->depth > FIB6_MAX_DEPTH) + /* Randomize max depth to avoid some side channels attacks. */ + max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH); + while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 05f4c3c726..45fb517591 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -260,6 +260,8 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); + /* we might do interface manipulations, so need both */ + wiphy_lock(local->hw.wiphy); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); @@ -1018,7 +1020,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) iftd = &sband->iftype_data[i]; - supp_he = supp_he || (iftd && iftd->he_cap.has_he); + supp_he = supp_he || iftd->he_cap.has_he; } /* HT, VHT, HE require QoS, thus >= 4 queues */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 8509778ff3..fa09a36921 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3242,7 +3242,9 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) + if (!ieee80211_amsdu_realloc_pad(local, skb, + sizeof(*amsdu_hdr) + + local->hw.extra_tx_headroom)) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4452455aef..7adcbc1f7d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -885,20 +885,16 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return subflow->mp_capable; } - if (mp_opt->dss && mp_opt->use_ack) { + if ((mp_opt->dss && mp_opt->use_ack) || + (mp_opt->add_addr && !mp_opt->echo)) { /* subflows are fully established as soon as we get any - * additional ack. + * additional ack, including ADD_ADDR. */ subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); goto fully_established; } - if (mp_opt->add_addr) { - WRITE_ONCE(msk->fully_established, true); - return true; - } - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP. Fallback scenarios requires a reset for * MP_JOIN subflows. diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 56263c2c40..7b37944597 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1135,36 +1135,12 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, return 0; } -struct addr_entry_release_work { - struct rcu_work rwork; - struct mptcp_pm_addr_entry *entry; -}; - -static void mptcp_pm_release_addr_entry(struct work_struct *work) +/* caller must ensure the RCU grace period is already elapsed */ +static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { - struct addr_entry_release_work *w; - struct mptcp_pm_addr_entry *entry; - - w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork); - entry = w->entry; - if (entry) { - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); - } - kfree(w); -} - -static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry) -{ - struct addr_entry_release_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry); - w->entry = entry; - queue_rcu_work(system_wq, &w->rwork); - } + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); } static int mptcp_nl_remove_id_zero_address(struct net *net, @@ -1244,7 +1220,8 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); - mptcp_pm_free_addr_entry(entry); + synchronize_rcu(); + __mptcp_pm_release_addr_entry(entry); return ret; } @@ -1297,6 +1274,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net, } } +/* caller must ensure the RCU grace period is already elapsed */ static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { @@ -1305,7 +1283,7 @@ static void __flush_addrs(struct list_head *list) cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); list_del_rcu(&cur->list); - mptcp_pm_free_addr_entry(cur); + __mptcp_pm_release_addr_entry(cur); } } @@ -1329,6 +1307,7 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list); + synchronize_rcu(); __flush_addrs(&free_list); return 0; } @@ -1939,7 +1918,8 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); /* net is removed from namespace list, can't race with - * other modifiers + * other modifiers, also netns core already waited for a + * RCU grace period. */ __flush_addrs(&pernet->local_addr_list); } diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c index eababc354f..fb0169a8f9 100644 --- a/net/netfilter/xt_dscp.c +++ b/net/netfilter/xt_dscp.c @@ -1,11 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only -/* x_tables module for setting the IPv4/IPv6 DSCP field, Version 1.8 +/* IP tables module for matching the value of the IPv4/IPv6 DSCP field * * (C) 2002 by Harald Welte - * based on ipt_FTOS.c (C) 2000 by Matthew G. Marsh - * - * See RFC2474 for a description of the DSCP field within the IP Header. -*/ + */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include @@ -14,148 +11,100 @@ #include #include -#include +#include MODULE_AUTHOR("Harald Welte "); -MODULE_DESCRIPTION("Xtables: DSCP/TOS field modification"); +MODULE_DESCRIPTION("Xtables: DSCP/TOS field match"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ipt_DSCP"); -MODULE_ALIAS("ip6t_DSCP"); -MODULE_ALIAS("ipt_TOS"); -MODULE_ALIAS("ip6t_TOS"); +MODULE_ALIAS("ipt_dscp"); +MODULE_ALIAS("ip6t_dscp"); +MODULE_ALIAS("ipt_tos"); +MODULE_ALIAS("ip6t_tos"); -static unsigned int -dscp_tg(struct sk_buff *skb, const struct xt_action_param *par) +static bool +dscp_mt(const struct sk_buff *skb, struct xt_action_param *par) { - const struct xt_DSCP_info *dinfo = par->targinfo; + const struct xt_dscp_info *info = par->matchinfo; u_int8_t dscp = ipv4_get_dsfield(ip_hdr(skb)) >> XT_DSCP_SHIFT; - if (dscp != dinfo->dscp) { - if (skb_ensure_writable(skb, sizeof(struct iphdr))) - return NF_DROP; - - ipv4_change_dsfield(ip_hdr(skb), - (__force __u8)(~XT_DSCP_MASK), - dinfo->dscp << XT_DSCP_SHIFT); - - } - return XT_CONTINUE; + return (dscp == info->dscp) ^ !!info->invert; } -static unsigned int -dscp_tg6(struct sk_buff *skb, const struct xt_action_param *par) +static bool +dscp_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - const struct xt_DSCP_info *dinfo = par->targinfo; + const struct xt_dscp_info *info = par->matchinfo; u_int8_t dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> XT_DSCP_SHIFT; - if (dscp != dinfo->dscp) { - if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) - return NF_DROP; - - ipv6_change_dsfield(ipv6_hdr(skb), - (__force __u8)(~XT_DSCP_MASK), - dinfo->dscp << XT_DSCP_SHIFT); - } - return XT_CONTINUE; + return (dscp == info->dscp) ^ !!info->invert; } -static int dscp_tg_check(const struct xt_tgchk_param *par) +static int dscp_mt_check(const struct xt_mtchk_param *par) { - const struct xt_DSCP_info *info = par->targinfo; + const struct xt_dscp_info *info = par->matchinfo; if (info->dscp > XT_DSCP_MAX) return -EDOM; + return 0; } -static unsigned int -tos_tg(struct sk_buff *skb, const struct xt_action_param *par) +static bool tos_mt(const struct sk_buff *skb, struct xt_action_param *par) { - const struct xt_tos_target_info *info = par->targinfo; - struct iphdr *iph = ip_hdr(skb); - u_int8_t orig, nv; + const struct xt_tos_match_info *info = par->matchinfo; - orig = ipv4_get_dsfield(iph); - nv = (orig & ~info->tos_mask) ^ info->tos_value; - - if (orig != nv) { - if (skb_ensure_writable(skb, sizeof(struct iphdr))) - return NF_DROP; - iph = ip_hdr(skb); - ipv4_change_dsfield(iph, 0, nv); - } - - return XT_CONTINUE; + if (xt_family(par) == NFPROTO_IPV4) + return ((ip_hdr(skb)->tos & info->tos_mask) == + info->tos_value) ^ !!info->invert; + else + return ((ipv6_get_dsfield(ipv6_hdr(skb)) & info->tos_mask) == + info->tos_value) ^ !!info->invert; } -static unsigned int -tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct xt_tos_target_info *info = par->targinfo; - struct ipv6hdr *iph = ipv6_hdr(skb); - u_int8_t orig, nv; - - orig = ipv6_get_dsfield(iph); - nv = (orig & ~info->tos_mask) ^ info->tos_value; - - if (orig != nv) { - if (skb_ensure_writable(skb, sizeof(struct iphdr))) - return NF_DROP; - iph = ipv6_hdr(skb); - ipv6_change_dsfield(iph, 0, nv); - } - - return XT_CONTINUE; -} - -static struct xt_target dscp_tg_reg[] __read_mostly = { +static struct xt_match dscp_mt_reg[] __read_mostly = { { - .name = "DSCP", + .name = "dscp", .family = NFPROTO_IPV4, - .checkentry = dscp_tg_check, - .target = dscp_tg, - .targetsize = sizeof(struct xt_DSCP_info), - .table = "mangle", + .checkentry = dscp_mt_check, + .match = dscp_mt, + .matchsize = sizeof(struct xt_dscp_info), .me = THIS_MODULE, }, { - .name = "DSCP", + .name = "dscp", .family = NFPROTO_IPV6, - .checkentry = dscp_tg_check, - .target = dscp_tg6, - .targetsize = sizeof(struct xt_DSCP_info), - .table = "mangle", + .checkentry = dscp_mt_check, + .match = dscp_mt6, + .matchsize = sizeof(struct xt_dscp_info), .me = THIS_MODULE, }, { - .name = "TOS", + .name = "tos", .revision = 1, .family = NFPROTO_IPV4, - .table = "mangle", - .target = tos_tg, - .targetsize = sizeof(struct xt_tos_target_info), + .match = tos_mt, + .matchsize = sizeof(struct xt_tos_match_info), .me = THIS_MODULE, }, { - .name = "TOS", + .name = "tos", .revision = 1, .family = NFPROTO_IPV6, - .table = "mangle", - .target = tos_tg6, - .targetsize = sizeof(struct xt_tos_target_info), + .match = tos_mt, + .matchsize = sizeof(struct xt_tos_match_info), .me = THIS_MODULE, }, }; -static int __init dscp_tg_init(void) +static int __init dscp_mt_init(void) { - return xt_register_targets(dscp_tg_reg, ARRAY_SIZE(dscp_tg_reg)); + return xt_register_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg)); } -static void __exit dscp_tg_exit(void) +static void __exit dscp_mt_exit(void) { - xt_unregister_targets(dscp_tg_reg, ARRAY_SIZE(dscp_tg_reg)); + xt_unregister_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg)); } -module_init(dscp_tg_init); -module_exit(dscp_tg_exit); +module_init(dscp_mt_init); +module_exit(dscp_mt_exit); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index baf235721c..000bb3da4f 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -187,14 +187,14 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, } doi_def->map.std->lvl.local = kcalloc(doi_def->map.std->lvl.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; } doi_def->map.std->lvl.cipso = kcalloc(doi_def->map.std->lvl.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -263,7 +263,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.local = kcalloc( doi_def->map.std->cat.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -271,7 +271,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.cipso = kcalloc( doi_def->map.std->cat.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 88deb5b414..cf2ce58124 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -507,6 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto) } skb->dev = vport->dev; + skb->tstamp = 0; vport->ops->send(skb); return; diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index 1dc955ca57..fa611678af 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -15,7 +15,6 @@ struct qrtr_mhi_dev { struct qrtr_endpoint ep; struct mhi_device *mhi_dev; struct device *dev; - struct completion ready; }; /* From MHI to QRTR */ @@ -51,10 +50,6 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb) struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep); int rc; - rc = wait_for_completion_interruptible(&qdev->ready); - if (rc) - goto free_skb; - if (skb->sk) sock_hold(skb->sk); @@ -84,7 +79,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev, 0); + rc = mhi_prepare_for_transfer(mhi_dev); if (rc) return rc; @@ -101,15 +96,6 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, if (rc) return rc; - /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); - if (rc) { - qrtr_endpoint_unregister(&qdev->ep); - dev_set_drvdata(&mhi_dev->dev, NULL); - return rc; - } - - complete_all(&qdev->ready); dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n"); return 0; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 171b7f3be6..bdbda61db8 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -493,7 +493,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) goto err; } - if (len != ALIGN(size, 4) + hdrlen) + if (!size || size & 3 || len != size + hdrlen) goto err; if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && @@ -506,8 +506,12 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (cb->type == QRTR_TYPE_NEW_SERVER) { /* Remote node endpoint can bridge other distant nodes */ - const struct qrtr_ctrl_pkt *pkt = data + hdrlen; + const struct qrtr_ctrl_pkt *pkt; + if (size < sizeof(*pkt)) + goto err; + + pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 9b6ffff72f..28c1b00221 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) cpu_relax(); } - ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len, + ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_len)) + if (unlikely(ret != ibmr->sg_dma_len)) return ret < 0 ? ret : -EINVAL; if (cmpxchg(&frmr->fr_state, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 951542843c..28af8b1e1b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -720,7 +720,7 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, skip_hash: if (flow_override) flow_hash = flow_override - 1; - else if (use_skbhash) + else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index b79a7e27bb..38a3a8394b 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1614,7 +1614,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); - return err; + goto failure; } if (tca[TCA_RATE]) { diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index c1e84d1eea..c76701ac35 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -660,6 +660,13 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); q->nbands = nbands; + for (i = nstrict; i < q->nstrict; i++) { + INIT_LIST_HEAD(&q->classes[i].alist); + if (q->classes[i].qdisc->q.qlen) { + list_add_tail(&q->classes[i].alist, &q->active); + q->classes[i].deficit = quanta[i]; + } + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5f7ac27a52..f22d26a2c8 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -125,6 +125,7 @@ struct htb_class { struct htb_class_leaf { int deficit[TC_HTB_MAXDEPTH]; struct Qdisc *q; + struct netdev_queue *offload_queue; } leaf; struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; @@ -1411,24 +1412,47 @@ htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q) return old_q; } -static void htb_offload_move_qdisc(struct Qdisc *sch, u16 qid_old, u16 qid_new) +static struct netdev_queue *htb_offload_get_queue(struct htb_class *cl) +{ + struct netdev_queue *queue; + + queue = cl->leaf.offload_queue; + if (!(cl->leaf.q->flags & TCQ_F_BUILTIN)) + WARN_ON(cl->leaf.q->dev_queue != queue); + + return queue; +} + +static void htb_offload_move_qdisc(struct Qdisc *sch, struct htb_class *cl_old, + struct htb_class *cl_new, bool destroying) { struct netdev_queue *queue_old, *queue_new; struct net_device *dev = qdisc_dev(sch); - struct Qdisc *qdisc; - queue_old = netdev_get_tx_queue(dev, qid_old); - queue_new = netdev_get_tx_queue(dev, qid_new); + queue_old = htb_offload_get_queue(cl_old); + queue_new = htb_offload_get_queue(cl_new); - if (dev->flags & IFF_UP) - dev_deactivate(dev); - qdisc = dev_graft_qdisc(queue_old, NULL); - qdisc->dev_queue = queue_new; - qdisc = dev_graft_qdisc(queue_new, qdisc); - if (dev->flags & IFF_UP) - dev_activate(dev); + if (!destroying) { + struct Qdisc *qdisc; - WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); + if (dev->flags & IFF_UP) + dev_deactivate(dev); + qdisc = dev_graft_qdisc(queue_old, NULL); + WARN_ON(qdisc != cl_old->leaf.q); + } + + if (!(cl_old->leaf.q->flags & TCQ_F_BUILTIN)) + cl_old->leaf.q->dev_queue = queue_new; + cl_old->leaf.offload_queue = queue_new; + + if (!destroying) { + struct Qdisc *qdisc; + + qdisc = dev_graft_qdisc(queue_new, cl_old->leaf.q); + if (dev->flags & IFF_UP) + dev_activate(dev); + WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); + } } static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, @@ -1442,10 +1466,8 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level) return -EINVAL; - if (q->offload) { - dev_queue = new->dev_queue; - WARN_ON(dev_queue != cl->leaf.q->dev_queue); - } + if (q->offload) + dev_queue = htb_offload_get_queue(cl); if (!new) { new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, @@ -1514,6 +1536,8 @@ static void htb_parent_to_leaf(struct Qdisc *sch, struct htb_class *cl, parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); parent->cmode = HTB_CAN_SEND; + if (q->offload) + parent->leaf.offload_queue = cl->leaf.offload_queue; } static void htb_parent_to_leaf_offload(struct Qdisc *sch, @@ -1534,6 +1558,7 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, struct netlink_ext_ack *extack) { struct tc_htb_qopt_offload offload_opt; + struct netdev_queue *dev_queue; struct Qdisc *q = cl->leaf.q; struct Qdisc *old = NULL; int err; @@ -1542,16 +1567,15 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, return -EINVAL; WARN_ON(!q); - if (!destroying) { - /* On destroy of HTB, two cases are possible: - * 1. q is a normal qdisc, but q->dev_queue has noop qdisc. - * 2. q is a noop qdisc (for nodes that were inner), - * q->dev_queue is noop_netdev_queue. + dev_queue = htb_offload_get_queue(cl); + old = htb_graft_helper(dev_queue, NULL); + if (destroying) + /* Before HTB is destroyed, the kernel grafts noop_qdisc to + * all queues. */ - old = htb_graft_helper(q->dev_queue, NULL); - WARN_ON(!old); + WARN_ON(!(old->flags & TCQ_F_BUILTIN)); + else WARN_ON(old != q); - } if (cl->parent) { cl->parent->bstats_bias.bytes += q->bstats.bytes; @@ -1570,18 +1594,17 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, if (!err || destroying) qdisc_put(old); else - htb_graft_helper(q->dev_queue, old); + htb_graft_helper(dev_queue, old); if (last_child) return err; - if (!err && offload_opt.moved_qid != 0) { - if (destroying) - q->dev_queue = netdev_get_tx_queue(qdisc_dev(sch), - offload_opt.qid); - else - htb_offload_move_qdisc(sch, offload_opt.moved_qid, - offload_opt.qid); + if (!err && offload_opt.classid != TC_H_MIN(cl->common.classid)) { + u32 classid = TC_H_MAJ(sch->handle) | + TC_H_MIN(offload_opt.classid); + struct htb_class *moved_cl = htb_find(classid, sch); + + htb_offload_move_qdisc(sch, moved_cl, cl, destroying); } return err; @@ -1704,9 +1727,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, } if (last_child) { - struct netdev_queue *dev_queue; + struct netdev_queue *dev_queue = sch->dev_queue; + + if (q->offload) + dev_queue = htb_offload_get_queue(cl); - dev_queue = q->offload ? cl->leaf.q->dev_queue : sch->dev_queue; new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid, NULL); @@ -1878,7 +1903,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } dev_queue = netdev_get_tx_queue(dev, offload_opt.qid); } else { /* First child. */ - dev_queue = parent->leaf.q->dev_queue; + dev_queue = htb_offload_get_queue(parent); old_q = htb_graft_helper(dev_queue, NULL); WARN_ON(old_q != parent->leaf.q); offload_opt = (struct tc_htb_qopt_offload) { @@ -1935,6 +1960,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* leaf (we) needs elementary qdisc */ cl->leaf.q = new_q ? new_q : &noop_qdisc; + if (q->offload) + cl->leaf.offload_queue = dev_queue; cl->parent = parent; diff --git a/net/socket.c b/net/socket.c index 0b2dad3bdf..8808b3617d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1109,7 +1109,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, rtnl_unlock(); if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) err = -EFAULT; - } else { + } else if (is_socket_ioctl_cmd(cmd)) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) @@ -1118,6 +1118,8 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; + } else { + err = -ENOTTY; } return err; } @@ -3306,6 +3308,8 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct ifreq ifreq; u32 data32; + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) return -EFAULT; if (get_user(data32, &u_ifreq32->ifr_data)) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0de918cb3d..a47e290b06 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1629,6 +1629,21 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_max_payload); +/** + * svc_proc_name - Return RPC procedure name in string form + * @rqstp: svc_rqst to operate on + * + * Return value: + * Pointer to a NUL-terminated string + */ +const char *svc_proc_name(const struct svc_rqst *rqstp) +{ + if (rqstp && rqstp->rq_procinfo) + return rqstp->rq_procinfo->pc_name; + return "unknown"; +} + + /** * svc_encode_result_payload - mark a range of bytes as a result payload * @rqstp: svc_rqst to operate on diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d66a8e44a1..dbb41821b1 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -835,7 +835,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) rqstp->rq_stime = ktime_get(); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); - } + } else + svc_xprt_received(xprt); out: trace_svc_handle_xprt(xprt, len); return len; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 75b99b7eda..8754bd8851 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1518,7 +1518,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(syn && !rc)) { tipc_set_sk_state(sk, TIPC_CONNECTING); - if (timeout) { + if (dlen && timeout) { timeout = msecs_to_jiffies(timeout); tipc_wait_for_connect(sock, &timeout); } diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 5764116125..c7d7d35867 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -831,7 +831,7 @@ int main(int argc, char **argv) memset(cpu, 0, n_cpus * sizeof(int)); /* Parse commands line args */ - while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:", + while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:n", long_options, &longindex)) != -1) { switch (opt) { case 'd': diff --git a/samples/pktgen/pktgen_sample04_many_flows.sh b/samples/pktgen/pktgen_sample04_many_flows.sh index 56c5f5af35..cff51f8615 100644 --- a/samples/pktgen/pktgen_sample04_many_flows.sh +++ b/samples/pktgen/pktgen_sample04_many_flows.sh @@ -13,13 +13,15 @@ root_check_run_with_sudo "$@" # Parameter parsing via include source ${basedir}/parameters.sh # Set some default params, if they didn't get set -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" [ -z "$CLONE_SKB" ] && CLONE_SKB="0" [ -z "$COUNT" ] && COUNT="0" # Zero means indefinitely if [ -n "$DEST_IP" ]; then - validate_addr $DEST_IP - read -r DST_MIN DST_MAX <<< $(parse_addr $DEST_IP) + validate_addr${IP6} $DEST_IP + read -r DST_MIN DST_MAX <<< $(parse_addr${IP6} $DEST_IP) fi if [ -n "$DST_PORT" ]; then read -r UDP_DST_MIN UDP_DST_MAX <<< $(parse_ports $DST_PORT) @@ -62,8 +64,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do # Single destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst_min $DST_MIN" - pg_set $dev "dst_max $DST_MAX" + pg_set $dev "dst${IP6}_min $DST_MIN" + pg_set $dev "dst${IP6}_max $DST_MAX" if [ -n "$DST_PORT" ]; then # Single destination port or random port range diff --git a/samples/pktgen/pktgen_sample05_flow_per_thread.sh b/samples/pktgen/pktgen_sample05_flow_per_thread.sh index 6e0effabca..3578d0aa4a 100644 --- a/samples/pktgen/pktgen_sample05_flow_per_thread.sh +++ b/samples/pktgen/pktgen_sample05_flow_per_thread.sh @@ -17,14 +17,16 @@ root_check_run_with_sudo "$@" # Parameter parsing via include source ${basedir}/parameters.sh # Set some default params, if they didn't get set -[ -z "$DEST_IP" ] && DEST_IP="198.18.0.42" +if [ -z "$DEST_IP" ]; then + [ -z "$IP6" ] && DEST_IP="198.18.0.42" || DEST_IP="FD00::1" +fi [ -z "$DST_MAC" ] && DST_MAC="90:e2:ba:ff:ff:ff" [ -z "$CLONE_SKB" ] && CLONE_SKB="0" [ -z "$BURST" ] && BURST=32 [ -z "$COUNT" ] && COUNT="0" # Zero means indefinitely if [ -n "$DEST_IP" ]; then - validate_addr $DEST_IP - read -r DST_MIN DST_MAX <<< $(parse_addr $DEST_IP) + validate_addr${IP6} $DEST_IP + read -r DST_MIN DST_MAX <<< $(parse_addr${IP6} $DEST_IP) fi if [ -n "$DST_PORT" ]; then read -r UDP_DST_MIN UDP_DST_MAX <<< $(parse_ports $DST_PORT) @@ -52,8 +54,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do # Single destination pg_set $dev "dst_mac $DST_MAC" - pg_set $dev "dst_min $DST_MIN" - pg_set $dev "dst_max $DST_MAX" + pg_set $dev "dst${IP6}_min $DST_MIN" + pg_set $dev "dst${IP6}_max $DST_MAX" if [ -n "$DST_PORT" ]; then # Single destination port or random port range diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index d0ceada992..f3a9cc201c 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -6,7 +6,6 @@ config IMA select SECURITYFS select CRYPTO select CRYPTO_HMAC - select CRYPTO_MD5 select CRYPTO_SHA1 select CRYPTO_HASH_INFO select TCG_TPM if HAS_IOMEM && !UML diff --git a/security/integrity/ima/ima_mok.c b/security/integrity/ima/ima_mok.c index 1e5c019161..95cc31525c 100644 --- a/security/integrity/ima/ima_mok.c +++ b/security/integrity/ima/ima_mok.c @@ -21,7 +21,7 @@ struct key *ima_blacklist_keyring; /* * Allocate the IMA blacklist keyring */ -__init int ima_mok_init(void) +static __init int ima_mok_init(void) { struct key_restriction *restriction; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 7d58834320..a144a3f68e 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1746,7 +1746,7 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream, channels = params_channels(params); frame_size = snd_pcm_format_size(format, channels); if (frame_size > 0) - params->fifo_size /= (unsigned)frame_size; + params->fifo_size /= frame_size; } return 0; } diff --git a/sound/firewire/oxfw/oxfw-stream.c b/sound/firewire/oxfw/oxfw-stream.c index 0ef242fdd3..fff18b5d4e 100644 --- a/sound/firewire/oxfw/oxfw-stream.c +++ b/sound/firewire/oxfw/oxfw-stream.c @@ -153,7 +153,7 @@ static int init_stream(struct snd_oxfw *oxfw, struct amdtp_stream *stream) struct cmp_connection *conn; enum cmp_direction c_dir; enum amdtp_stream_direction s_dir; - unsigned int flags = CIP_UNAWARE_SYT; + unsigned int flags = 0; int err; if (!(oxfw->quirks & SND_OXFW_QUIRK_BLOCKING_TRANSMISSION)) @@ -161,6 +161,13 @@ static int init_stream(struct snd_oxfw *oxfw, struct amdtp_stream *stream) else flags |= CIP_BLOCKING; + // OXFW 970/971 has no function to generate playback timing according to the sequence + // of value in syt field, thus the packet should include NO_INFO value in the field. + // However, some models just ignore data blocks in packet with NO_INFO for audio data + // processing. + if (!(oxfw->quirks & SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET)) + flags |= CIP_UNAWARE_SYT; + if (stream == &oxfw->tx_stream) { conn = &oxfw->out_conn; c_dir = CMP_OUTPUT; diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 84971d78d1..cb5b5e3a48 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -159,8 +159,10 @@ static int detect_quirks(struct snd_oxfw *oxfw, const struct ieee1394_device_id return snd_oxfw_scs1x_add(oxfw); } - if (entry->vendor_id == OUI_APOGEE && entry->model_id == MODEL_DUET_FW) - oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION; + if (entry->vendor_id == OUI_APOGEE && entry->model_id == MODEL_DUET_FW) { + oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION | + SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET; + } /* * TASCAM FireOne has physical control and requires a pair of additional diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h index ee47abcb0c..c13034f6c2 100644 --- a/sound/firewire/oxfw/oxfw.h +++ b/sound/firewire/oxfw/oxfw.h @@ -42,6 +42,11 @@ enum snd_oxfw_quirk { SND_OXFW_QUIRK_BLOCKING_TRANSMISSION = 0x04, // Stanton SCS1.d and SCS1.m support unique transaction. SND_OXFW_QUIRK_SCS_TRANSACTION = 0x08, + // Apogee Duet FireWire ignores data blocks in packet with NO_INFO for audio data + // processing, while output level meter moves. Any value in syt field of packet takes + // the device to process audio data even if the value is invalid in a point of + // IEC 61883-1/6. + SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET = 0x10, }; /* This is an arbitrary number for convinience. */ diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index e97d00585e..481d8f8d33 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3460,7 +3460,7 @@ static int cap_put_caller(struct snd_kcontrol *kcontrol, struct hda_gen_spec *spec = codec->spec; const struct hda_input_mux *imux; struct nid_path *path; - int i, adc_idx, err = 0; + int i, adc_idx, ret, err = 0; imux = &spec->input_mux; adc_idx = kcontrol->id.index; @@ -3470,9 +3470,13 @@ static int cap_put_caller(struct snd_kcontrol *kcontrol, if (!path || !path->ctls[type]) continue; kcontrol->private_value = path->ctls[type]; - err = func(kcontrol, ucontrol); - if (err < 0) + ret = func(kcontrol, ucontrol); + if (ret < 0) { + err = ret; break; + } + if (ret > 0) + err = 1; } mutex_unlock(&codec->control_mutex); if (err >= 0 && spec->cap_sync_hook) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 0322b28950..0062c18b64 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -883,10 +883,11 @@ static unsigned int azx_get_pos_skl(struct azx *chip, struct azx_dev *azx_dev) return azx_get_pos_posbuf(chip, azx_dev); } -static void azx_shutdown_chip(struct azx *chip) +static void __azx_shutdown_chip(struct azx *chip, bool skip_link_reset) { azx_stop_chip(chip); - azx_enter_link_reset(chip); + if (!skip_link_reset) + azx_enter_link_reset(chip); azx_clear_irq_pending(chip); display_power(chip, false); } @@ -895,6 +896,11 @@ static void azx_shutdown_chip(struct azx *chip) static DEFINE_MUTEX(card_list_lock); static LIST_HEAD(card_list); +static void azx_shutdown_chip(struct azx *chip) +{ + __azx_shutdown_chip(chip, false); +} + static void azx_add_card_list(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -2385,7 +2391,7 @@ static void azx_shutdown(struct pci_dev *pci) return; chip = card->private_data; if (chip && chip->running) - azx_shutdown_chip(chip); + __azx_shutdown_chip(chip, true); } /* PCI IDs */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a065260d0d..70516527eb 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6658,6 +6658,7 @@ enum { ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, ALC623_FIXUP_LENOVO_THINKSTATION_P340, ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, + ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST, }; static const struct hda_fixup alc269_fixups[] = { @@ -8242,6 +8243,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_XIAOMI_HEADSET_MIC }, + [ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8332,6 +8339,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a61, "Dell XPS 15 9510", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -8430,6 +8438,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x87f2, "HP ProBook 640 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), @@ -8437,8 +8446,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8847, "HP EliteBook x360 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x884b, "HP EliteBook 840 Aero G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8862, "HP ProBook 445 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), - SND_PCI_QUIRK(0x103c, 0x8863, "HP ProBook 445 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8862, "HP ProBook 445 G8 Notebook PC", ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x103c, 0x8863, "HP ProBook 445 G8 Notebook PC", ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x886d, "HP ZBook Fury 17.3 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), @@ -9513,6 +9522,16 @@ static int patch_alc269(struct hda_codec *codec) snd_hda_pick_fixup(codec, alc269_fixup_models, alc269_fixup_tbl, alc269_fixups); + /* FIXME: both TX300 and ROG Strix G17 have the same SSID, and + * the quirk breaks the latter (bko#214101). + * Clear the wrong entry. + */ + if (codec->fixup_id == ALC282_FIXUP_ASUS_TX300 && + codec->core.vendor_id == 0x10ec0294) { + codec_dbg(codec, "Clear wrong fixup for ASUS ROG Strix G17\n"); + codec->fixup_id = HDA_FIXUP_ID_NOT_SET; + } + snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups, true); snd_hda_pick_pin_fixup(codec, alc269_fallback_pin_fixup_tbl, alc269_fixups, false); snd_hda_pick_fixup(codec, NULL, alc269_fixup_vendor_tbl, diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index a5c1a2c4ea..773a136161 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -1041,6 +1041,7 @@ static const struct hda_fixup via_fixups[] = { }; static const struct snd_pci_quirk vt2002p_fixups[] = { + SND_PCI_QUIRK(0x1043, 0x13f7, "Asus B23E", VIA_FIXUP_POWER_SAVE), SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75), SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo", VIA_FIXUP_POWER_SAVE), diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index 4a56a52ada..b9d5d7a097 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -117,6 +117,13 @@ static struct snd_soc_dai_driver rt5682_dai[] = { }, }; +static void rt5682_i2c_disable_regulators(void *data) +{ + struct rt5682_priv *rt5682 = data; + + regulator_bulk_disable(ARRAY_SIZE(rt5682->supplies), rt5682->supplies); +} + static int rt5682_i2c_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { @@ -157,6 +164,11 @@ static int rt5682_i2c_probe(struct i2c_client *i2c, return ret; } + ret = devm_add_action_or_reset(&i2c->dev, rt5682_i2c_disable_regulators, + rt5682); + if (ret) + return ret; + ret = regulator_bulk_enable(ARRAY_SIZE(rt5682->supplies), rt5682->supplies); if (ret) { @@ -282,10 +294,7 @@ static void rt5682_i2c_shutdown(struct i2c_client *client) static int rt5682_i2c_remove(struct i2c_client *client) { - struct rt5682_priv *rt5682 = i2c_get_clientdata(client); - rt5682_i2c_shutdown(client); - regulator_bulk_disable(ARRAY_SIZE(rt5682->supplies), rt5682->supplies); return 0; } diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c index 86c92e03ea..d885ced34f 100644 --- a/sound/soc/codecs/wcd9335.c +++ b/sound/soc/codecs/wcd9335.c @@ -4076,6 +4076,16 @@ static int wcd9335_setup_irqs(struct wcd9335_codec *wcd) return ret; } +static void wcd9335_teardown_irqs(struct wcd9335_codec *wcd) +{ + int i; + + /* disable interrupts on all slave ports */ + for (i = 0; i < WCD9335_SLIM_NUM_PORT_REG; i++) + regmap_write(wcd->if_regmap, WCD9335_SLIM_PGD_PORT_INT_EN0 + i, + 0x00); +} + static void wcd9335_cdc_sido_ccl_enable(struct wcd9335_codec *wcd, bool ccl_flag) { @@ -4844,6 +4854,7 @@ static void wcd9335_codec_init(struct snd_soc_component *component) static int wcd9335_codec_probe(struct snd_soc_component *component) { struct wcd9335_codec *wcd = dev_get_drvdata(component->dev); + int ret; int i; snd_soc_component_init_regmap(component, wcd->regmap); @@ -4861,7 +4872,15 @@ static int wcd9335_codec_probe(struct snd_soc_component *component) for (i = 0; i < NUM_CODEC_DAIS; i++) INIT_LIST_HEAD(&wcd->dai[i].slim_ch_list); - return wcd9335_setup_irqs(wcd); + ret = wcd9335_setup_irqs(wcd); + if (ret) + goto free_clsh_ctrl; + + return 0; + +free_clsh_ctrl: + wcd_clsh_ctrl_free(wcd->clsh_ctrl); + return ret; } static void wcd9335_codec_remove(struct snd_soc_component *comp) @@ -4869,7 +4888,7 @@ static void wcd9335_codec_remove(struct snd_soc_component *comp) struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev); wcd_clsh_ctrl_free(wcd->clsh_ctrl); - free_irq(regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS), wcd); + wcd9335_teardown_irqs(wcd); } static int wcd9335_codec_set_sysclk(struct snd_soc_component *comp, diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index fe15cbc7bc..a4d4cbf716 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -747,6 +747,8 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp, static void wm_adsp2_cleanup_debugfs(struct wm_adsp *dsp) { wm_adsp_debugfs_clear(dsp); + debugfs_remove_recursive(dsp->debugfs_root); + dsp->debugfs_root = NULL; } #else static inline void wm_adsp2_init_debugfs(struct wm_adsp *dsp, diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c index ea5c973e2e..d60f4dac6c 100644 --- a/sound/soc/fsl/fsl_rpmsg.c +++ b/sound/soc/fsl/fsl_rpmsg.c @@ -165,25 +165,25 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) } /* Get the optional clocks */ - rpmsg->ipg = devm_clk_get(&pdev->dev, "ipg"); + rpmsg->ipg = devm_clk_get_optional(&pdev->dev, "ipg"); if (IS_ERR(rpmsg->ipg)) - rpmsg->ipg = NULL; + return PTR_ERR(rpmsg->ipg); - rpmsg->mclk = devm_clk_get(&pdev->dev, "mclk"); + rpmsg->mclk = devm_clk_get_optional(&pdev->dev, "mclk"); if (IS_ERR(rpmsg->mclk)) - rpmsg->mclk = NULL; + return PTR_ERR(rpmsg->mclk); - rpmsg->dma = devm_clk_get(&pdev->dev, "dma"); + rpmsg->dma = devm_clk_get_optional(&pdev->dev, "dma"); if (IS_ERR(rpmsg->dma)) - rpmsg->dma = NULL; + return PTR_ERR(rpmsg->dma); - rpmsg->pll8k = devm_clk_get(&pdev->dev, "pll8k"); + rpmsg->pll8k = devm_clk_get_optional(&pdev->dev, "pll8k"); if (IS_ERR(rpmsg->pll8k)) - rpmsg->pll8k = NULL; + return PTR_ERR(rpmsg->pll8k); - rpmsg->pll11k = devm_clk_get(&pdev->dev, "pll11k"); + rpmsg->pll11k = devm_clk_get_optional(&pdev->dev, "pll11k"); if (IS_ERR(rpmsg->pll11k)) - rpmsg->pll11k = NULL; + return PTR_ERR(rpmsg->pll11k); platform_set_drvdata(pdev, rpmsg); pm_runtime_enable(&pdev->dev); diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 5db2f4865b..905c7965f6 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -127,7 +127,7 @@ static void sst_fill_alloc_params(struct snd_pcm_substream *substream, snd_pcm_uframes_t period_size; ssize_t periodbytes; ssize_t buffer_bytes = snd_pcm_lib_buffer_bytes(substream); - u32 buffer_addr = substream->runtime->dma_addr; + u32 buffer_addr = virt_to_phys(substream->runtime->dma_area); channels = substream->runtime->channels; period_size = substream->runtime->period_size; diff --git a/sound/soc/intel/boards/kbl_da7219_max98927.c b/sound/soc/intel/boards/kbl_da7219_max98927.c index a31a7a7bbf..2b43459adc 100644 --- a/sound/soc/intel/boards/kbl_da7219_max98927.c +++ b/sound/soc/intel/boards/kbl_da7219_max98927.c @@ -199,7 +199,7 @@ static int kabylake_ssp0_hw_params(struct snd_pcm_substream *substream, } if (!strcmp(codec_dai->component->name, MAX98373_DEV0_NAME)) { ret = snd_soc_dai_set_tdm_slot(codec_dai, - 0x03, 3, 8, 24); + 0x30, 3, 8, 16); if (ret < 0) { dev_err(runtime->dev, "DEV0 TDM slot err:%d\n", ret); @@ -208,10 +208,10 @@ static int kabylake_ssp0_hw_params(struct snd_pcm_substream *substream, } if (!strcmp(codec_dai->component->name, MAX98373_DEV1_NAME)) { ret = snd_soc_dai_set_tdm_slot(codec_dai, - 0x0C, 3, 8, 24); + 0xC0, 3, 8, 16); if (ret < 0) { dev_err(runtime->dev, - "DEV0 TDM slot err:%d\n", ret); + "DEV1 TDM slot err:%d\n", ret); return ret; } } @@ -311,24 +311,6 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd, * The above 2 loops are mutually exclusive based on the stream direction, * thus rtd_dpcm variable will never be overwritten */ - /* - * Topology for kblda7219m98373 & kblmax98373 supports only S24_LE, - * where as kblda7219m98927 & kblmax98927 supports S16_LE by default. - * Skipping the port wise FE and BE configuration for kblda7219m98373 & - * kblmax98373 as the topology (FE & BE) supports S24_LE only. - */ - - if (!strcmp(rtd->card->name, "kblda7219m98373") || - !strcmp(rtd->card->name, "kblmax98373")) { - /* The ADSP will convert the FE rate to 48k, stereo */ - rate->min = rate->max = 48000; - chan->min = chan->max = DUAL_CHANNEL; - - /* set SSP to 24 bit */ - snd_mask_none(fmt); - snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE); - return 0; - } /* * The ADSP will convert the FE rate to 48k, stereo, 24 bit @@ -479,31 +461,20 @@ static struct snd_pcm_hw_constraint_list constraints_channels_quad = { static int kbl_fe_startup(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; - struct snd_soc_pcm_runtime *soc_rt = asoc_substream_to_rtd(substream); /* * On this platform for PCM device we support, * 48Khz * stereo + * 16 bit audio */ runtime->hw.channels_max = DUAL_CHANNEL; snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, &constraints_channels); - /* - * Setup S24_LE (32 bit container and 24 bit valid data) for - * kblda7219m98373 & kblmax98373. For kblda7219m98927 & - * kblmax98927 keeping it as 16/16 due to topology FW dependency. - */ - if (!strcmp(soc_rt->card->name, "kblda7219m98373") || - !strcmp(soc_rt->card->name, "kblmax98373")) { - runtime->hw.formats = SNDRV_PCM_FMTBIT_S24_LE; - snd_pcm_hw_constraint_msbits(runtime, 0, 32, 24); - } else { - runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE; - snd_pcm_hw_constraint_msbits(runtime, 0, 16, 16); - } + runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE; + snd_pcm_hw_constraint_msbits(runtime, 0, 16, 16); snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &constraints_rates); @@ -536,23 +507,11 @@ static int kabylake_dmic_fixup(struct snd_soc_pcm_runtime *rtd, static int kabylake_dmic_startup(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; - struct snd_soc_pcm_runtime *soc_rt = asoc_substream_to_rtd(substream); runtime->hw.channels_min = runtime->hw.channels_max = QUAD_CHANNEL; snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, &constraints_channels_quad); - /* - * Topology for kblda7219m98373 & kblmax98373 supports only S24_LE. - * The DMIC also configured for S24_LE. Forcing the DMIC format to - * S24_LE due to the topology FW dependency. - */ - if (!strcmp(soc_rt->card->name, "kblda7219m98373") || - !strcmp(soc_rt->card->name, "kblmax98373")) { - runtime->hw.formats = SNDRV_PCM_FMTBIT_S24_LE; - snd_pcm_hw_constraint_msbits(runtime, 0, 32, 24); - } - return snd_pcm_hw_constraint_list(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &constraints_rates); } diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c index 42ef51c3fb..b591c6fd13 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c @@ -75,7 +75,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[] = { }, { .id = "DLGS7219", - .drv_name = "cml_da7219_max98357a", + .drv_name = "cml_da7219_mx98357a", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &max98390_spk_codecs, .sof_fw_filename = "sof-cml.ri", diff --git a/sound/soc/intel/common/soc-acpi-intel-kbl-match.c b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c index ba5ff468c2..741bf2f9e0 100644 --- a/sound/soc/intel/common/soc-acpi-intel-kbl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c @@ -87,7 +87,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[] = { }, { .id = "DLGS7219", - .drv_name = "kbl_da7219_max98357a", + .drv_name = "kbl_da7219_mx98357a", .fw_filename = "intel/dsp_fw_kbl.bin", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &kbl_7219_98357_codecs, diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index c0fdab39e7..09037d555e 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -113,7 +113,7 @@ static int is_skl_dsp_widget_type(struct snd_soc_dapm_widget *w, static void skl_dump_mconfig(struct skl_dev *skl, struct skl_module_cfg *mcfg) { - struct skl_module_iface *iface = &mcfg->module->formats[0]; + struct skl_module_iface *iface = &mcfg->module->formats[mcfg->fmt_idx]; dev_dbg(skl->dev, "Dumping config\n"); dev_dbg(skl->dev, "Input Format:\n"); @@ -195,8 +195,8 @@ static void skl_tplg_update_params_fixup(struct skl_module_cfg *m_cfg, struct skl_module_fmt *in_fmt, *out_fmt; /* Fixups will be applied to pin 0 only */ - in_fmt = &m_cfg->module->formats[0].inputs[0].fmt; - out_fmt = &m_cfg->module->formats[0].outputs[0].fmt; + in_fmt = &m_cfg->module->formats[m_cfg->fmt_idx].inputs[0].fmt; + out_fmt = &m_cfg->module->formats[m_cfg->fmt_idx].outputs[0].fmt; if (params->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (is_fe) { @@ -239,9 +239,9 @@ static void skl_tplg_update_buffer_size(struct skl_dev *skl, /* Since fixups is applied to pin 0 only, ibs, obs needs * change for pin 0 only */ - res = &mcfg->module->resources[0]; - in_fmt = &mcfg->module->formats[0].inputs[0].fmt; - out_fmt = &mcfg->module->formats[0].outputs[0].fmt; + res = &mcfg->module->resources[mcfg->res_idx]; + in_fmt = &mcfg->module->formats[mcfg->fmt_idx].inputs[0].fmt; + out_fmt = &mcfg->module->formats[mcfg->fmt_idx].outputs[0].fmt; if (mcfg->m_type == SKL_MODULE_TYPE_SRCINT) multiplier = 5; @@ -1463,12 +1463,6 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol, struct skl_dev *skl = get_skl_ctx(w->dapm->dev); if (ac->params) { - /* - * Widget data is expected to be stripped of T and L - */ - size -= 2 * sizeof(unsigned int); - data += 2; - if (size > ac->max) return -EINVAL; ac->size = size; @@ -1637,11 +1631,12 @@ int skl_tplg_update_pipe_params(struct device *dev, struct skl_module_cfg *mconfig, struct skl_pipe_params *params) { - struct skl_module_res *res = &mconfig->module->resources[0]; + struct skl_module_res *res; struct skl_dev *skl = get_skl_ctx(dev); struct skl_module_fmt *format = NULL; u8 cfg_idx = mconfig->pipe->cur_config_idx; + res = &mconfig->module->resources[mconfig->res_idx]; skl_tplg_fill_dma_id(mconfig, params); mconfig->fmt_idx = mconfig->mod_cfg[cfg_idx].fmt_idx; mconfig->res_idx = mconfig->mod_cfg[cfg_idx].res_idx; @@ -1650,9 +1645,9 @@ int skl_tplg_update_pipe_params(struct device *dev, return 0; if (params->stream == SNDRV_PCM_STREAM_PLAYBACK) - format = &mconfig->module->formats[0].inputs[0].fmt; + format = &mconfig->module->formats[mconfig->fmt_idx].inputs[0].fmt; else - format = &mconfig->module->formats[0].outputs[0].fmt; + format = &mconfig->module->formats[mconfig->fmt_idx].outputs[0].fmt; /* set the hw_params */ format->s_freq = params->s_freq; diff --git a/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c b/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c index c4a598cbbd..14e77df06b 100644 --- a/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c +++ b/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c @@ -1119,25 +1119,26 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) afe->regmap = syscon_node_to_regmap(dev->parent->of_node); if (IS_ERR(afe->regmap)) { dev_err(dev, "could not get regmap from parent\n"); - return PTR_ERR(afe->regmap); + ret = PTR_ERR(afe->regmap); + goto err_pm_disable; } ret = regmap_attach_dev(dev, afe->regmap, &mt8183_afe_regmap_config); if (ret) { dev_warn(dev, "regmap_attach_dev fail, ret %d\n", ret); - return ret; + goto err_pm_disable; } rstc = devm_reset_control_get(dev, "audiosys"); if (IS_ERR(rstc)) { ret = PTR_ERR(rstc); dev_err(dev, "could not get audiosys reset:%d\n", ret); - return ret; + goto err_pm_disable; } ret = reset_control_reset(rstc); if (ret) { dev_err(dev, "failed to trigger audio reset:%d\n", ret); - return ret; + goto err_pm_disable; } /* enable clock for regcache get default value from hw */ @@ -1147,7 +1148,7 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) ret = regmap_reinit_cache(afe->regmap, &mt8183_afe_regmap_config); if (ret) { dev_err(dev, "regmap_reinit_cache fail, ret %d\n", ret); - return ret; + goto err_pm_disable; } pm_runtime_put_sync(&pdev->dev); @@ -1160,8 +1161,10 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) afe->memif_size = MT8183_MEMIF_NUM; afe->memif = devm_kcalloc(dev, afe->memif_size, sizeof(*afe->memif), GFP_KERNEL); - if (!afe->memif) - return -ENOMEM; + if (!afe->memif) { + ret = -ENOMEM; + goto err_pm_disable; + } for (i = 0; i < afe->memif_size; i++) { afe->memif[i].data = &memif_data[i]; @@ -1178,22 +1181,26 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) afe->irqs_size = MT8183_IRQ_NUM; afe->irqs = devm_kcalloc(dev, afe->irqs_size, sizeof(*afe->irqs), GFP_KERNEL); - if (!afe->irqs) - return -ENOMEM; + if (!afe->irqs) { + ret = -ENOMEM; + goto err_pm_disable; + } for (i = 0; i < afe->irqs_size; i++) afe->irqs[i].irq_data = &irq_data[i]; /* request irq */ irq_id = platform_get_irq(pdev, 0); - if (irq_id < 0) - return irq_id; + if (irq_id < 0) { + ret = irq_id; + goto err_pm_disable; + } ret = devm_request_irq(dev, irq_id, mt8183_afe_irq_handler, IRQF_TRIGGER_NONE, "asys-isr", (void *)afe); if (ret) { dev_err(dev, "could not request_irq for asys-isr\n"); - return ret; + goto err_pm_disable; } /* init sub_dais */ @@ -1204,7 +1211,7 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) { dev_warn(afe->dev, "dai register i %d fail, ret %d\n", i, ret); - return ret; + goto err_pm_disable; } } @@ -1213,7 +1220,7 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) { dev_warn(afe->dev, "mtk_afe_combine_sub_dai fail, ret %d\n", ret); - return ret; + goto err_pm_disable; } afe->mtk_afe_hardware = &mt8183_afe_hardware; @@ -1229,7 +1236,7 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) NULL, 0); if (ret) { dev_warn(dev, "err_platform\n"); - return ret; + goto err_pm_disable; } ret = devm_snd_soc_register_component(afe->dev, @@ -1238,10 +1245,14 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev) afe->num_dai_drivers); if (ret) { dev_warn(dev, "err_dai_component\n"); - return ret; + goto err_pm_disable; } return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } static int mt8183_afe_pcm_dev_remove(struct platform_device *pdev) diff --git a/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c b/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c index 7a1724f5ff..31c280339c 100644 --- a/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c +++ b/sound/soc/mediatek/mt8192/mt8192-afe-pcm.c @@ -2229,12 +2229,13 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) afe->regmap = syscon_node_to_regmap(dev->parent->of_node); if (IS_ERR(afe->regmap)) { dev_err(dev, "could not get regmap from parent\n"); - return PTR_ERR(afe->regmap); + ret = PTR_ERR(afe->regmap); + goto err_pm_disable; } ret = regmap_attach_dev(dev, afe->regmap, &mt8192_afe_regmap_config); if (ret) { dev_warn(dev, "regmap_attach_dev fail, ret %d\n", ret); - return ret; + goto err_pm_disable; } /* enable clock for regcache get default value from hw */ @@ -2244,7 +2245,7 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) ret = regmap_reinit_cache(afe->regmap, &mt8192_afe_regmap_config); if (ret) { dev_err(dev, "regmap_reinit_cache fail, ret %d\n", ret); - return ret; + goto err_pm_disable; } pm_runtime_put_sync(&pdev->dev); @@ -2257,8 +2258,10 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) afe->memif_size = MT8192_MEMIF_NUM; afe->memif = devm_kcalloc(dev, afe->memif_size, sizeof(*afe->memif), GFP_KERNEL); - if (!afe->memif) - return -ENOMEM; + if (!afe->memif) { + ret = -ENOMEM; + goto err_pm_disable; + } for (i = 0; i < afe->memif_size; i++) { afe->memif[i].data = &memif_data[i]; @@ -2272,22 +2275,26 @@ static int mt8192_afe_pcm_dev_probe(struct platform_device *pdev) afe->irqs_size = MT8192_IRQ_NUM; afe->irqs = devm_kcalloc(dev, afe->irqs_size, sizeof(*afe->irqs), GFP_KERNEL); - if (!afe->irqs) - return -ENOMEM; + if (!afe->irqs) { + ret = -ENOMEM; + goto err_pm_disable; + } for (i = 0; i < afe->irqs_size; i++) afe->irqs[i].irq_data = &irq_data[i]; /* request irq */ irq_id = platform_get_irq(pdev, 0); - if (irq_id < 0) - return irq_id; + if (irq_id < 0) { + ret = irq_id; + goto err_pm_disable; + } ret = devm_request_irq(dev, irq_id, mt8192_afe_irq_handler, IRQF_TRIGGER_NONE, "asys-isr", (void *)afe); if (ret) { dev_err(dev, "could not request_irq for Afe_ISR_Handle\n"); - return ret; + goto err_pm_disable; } /* init sub_dais */ diff --git a/sound/usb/card.c b/sound/usb/card.c index a1f8c3a026..6abfc9d079 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -68,6 +68,7 @@ static int pid[SNDRV_CARDS] = { [0 ... (SNDRV_CARDS-1)] = -1 }; static int device_setup[SNDRV_CARDS]; /* device parameter for this card */ static bool ignore_ctl_error; static bool autoclock = true; +static bool lowlatency = true; static char *quirk_alias[SNDRV_CARDS]; static char *delayed_register[SNDRV_CARDS]; static bool implicit_fb[SNDRV_CARDS]; @@ -92,6 +93,8 @@ MODULE_PARM_DESC(ignore_ctl_error, "Ignore errors from USB controller for mixer interfaces."); module_param(autoclock, bool, 0444); MODULE_PARM_DESC(autoclock, "Enable auto-clock selection for UAC2 devices (default: yes)."); +module_param(lowlatency, bool, 0444); +MODULE_PARM_DESC(lowlatency, "Enable low latency playback (default: yes)."); module_param_array(quirk_alias, charp, NULL, 0444); MODULE_PARM_DESC(quirk_alias, "Quirk aliases, e.g. 0123abcd:5678beef."); module_param_array(delayed_register, charp, NULL, 0444); @@ -599,6 +602,7 @@ static int snd_usb_audio_create(struct usb_interface *intf, chip->setup = device_setup[idx]; chip->generic_implicit_fb = implicit_fb[idx]; chip->autoclock = autoclock; + chip->lowlatency = lowlatency; atomic_set(&chip->active, 1); /* avoid autopm during probing */ atomic_set(&chip->usage_count, 0); atomic_set(&chip->shutdown, 0); diff --git a/sound/usb/card.h b/sound/usb/card.h index 6c0a052a28..5b19901f30 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -94,6 +94,7 @@ struct snd_usb_endpoint { struct list_head ready_playback_urbs; /* playback URB FIFO for implicit fb */ unsigned int nurbs; /* # urbs */ + unsigned int nominal_queue_size; /* total buffer sizes in URBs */ unsigned long active_mask; /* bitmask of active urbs */ unsigned long unlink_mask; /* bitmask of unlinked urbs */ char *syncbuf; /* sync buffer for all sync URBs */ @@ -187,6 +188,7 @@ struct snd_usb_substream { } dsd_dop; bool trigger_tstamp_pending_update; /* trigger timestamp being updated from initial estimate */ + bool early_playback_start; /* early start needed for playback? */ struct media_ctl *media_ctl; }; diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 4f85677121..bf26c04cf4 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1126,6 +1126,10 @@ static int data_ep_set_params(struct snd_usb_endpoint *ep) INIT_LIST_HEAD(&u->ready_list); } + /* total buffer bytes of all URBs plus the next queue; + * referred in pcm.c + */ + ep->nominal_queue_size = maxsize * urb_packs * (ep->nurbs + 1); return 0; out_of_memory: @@ -1287,6 +1291,11 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip, * to be set up before parameter setups */ iface_first = ep->cur_audiofmt->protocol == UAC_VERSION_1; + /* Workaround for Sony WALKMAN NW-A45 DAC; + * it requires the interface setup at first like UAC1 + */ + if (chip->usb_id == USB_ID(0x054c, 0x0b8c)) + iface_first = true; if (iface_first) { err = endpoint_set_interface(chip, ep, true); if (err < 0) diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 4e5031a680..5dc9266180 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -614,6 +614,15 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream) subs->period_elapsed_pending = 0; runtime->delay = 0; + /* check whether early start is needed for playback stream */ + subs->early_playback_start = + subs->direction == SNDRV_PCM_STREAM_PLAYBACK && + (!chip->lowlatency || + (subs->data_endpoint->nominal_queue_size >= subs->buffer_bytes)); + + if (subs->early_playback_start) + ret = start_endpoints(subs); + unlock: snd_usb_unlock_shutdown(chip); return ret; @@ -1394,7 +1403,7 @@ static void prepare_playback_urb(struct snd_usb_substream *subs, subs->trigger_tstamp_pending_update = false; } - if (period_elapsed && !subs->running) { + if (period_elapsed && !subs->running && !subs->early_playback_start) { subs->period_elapsed_pending = 1; period_elapsed = 0; } @@ -1448,7 +1457,8 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea prepare_playback_urb, retire_playback_urb, subs); - if (cmd == SNDRV_PCM_TRIGGER_START) { + if (!subs->early_playback_start && + cmd == SNDRV_PCM_TRIGGER_START) { err = start_endpoints(subs); if (err < 0) { snd_usb_endpoint_set_callback(subs->data_endpoint, diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 0fae44bc82..54c7c3afc4 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1904,6 +1904,7 @@ static const struct registration_quirk registration_quirks[] = { REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */ REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */ + REG_QUIRK_ENTRY(0x0ecb, 0x1f47, 2), /* JBL Quantum 800 */ REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */ REG_QUIRK_ENTRY(0x0ecb, 0x203c, 2), /* JBL Quantum 600 */ REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */ diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 538831cbd9..8b70c9ea91 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -57,6 +57,7 @@ struct snd_usb_audio { bool generic_implicit_fb; /* from the 'implicit_fb' module param */ bool autoclock; /* from the 'autoclock' module param */ + bool lowlatency; /* from the 'lowlatency' module param */ struct usb_host_interface *ctrl_intf; /* the audio control interface */ struct media_device *media_dev; struct media_intf_devnode *ctl_intf_media_devnode; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index f45fa992e0..fd67496a94 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -111,9 +111,11 @@ static void xbc_show_list(void) char key[XBC_KEYLEN_MAX]; struct xbc_node *leaf; const char *val; + int ret; xbc_for_each_key_value(leaf, val) { - if (xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX) < 0) { + ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX); + if (ret < 0) { fprintf(stderr, "Failed to compose key %d\n", ret); break; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index cc48726740..9d709b4276 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -781,6 +781,8 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, kernel_syms_destroy(&dd); } + btf__free(btf); + return 0; } @@ -2002,8 +2004,8 @@ static char *profile_target_name(int tgt_fd) struct bpf_prog_info_linear *info_linear; struct bpf_func_info *func_info; const struct btf_type *t; + struct btf *btf = NULL; char *name = NULL; - struct btf *btf; info_linear = bpf_program__get_prog_info_linear( tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); @@ -2027,6 +2029,7 @@ static char *profile_target_name(int tgt_fd) } name = strdup(btf__name_by_offset(btf, t->name_off)); out: + btf__free(btf); free(info_linear); return name; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bf9252c738..5cdff16316 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3249,7 +3249,7 @@ union bpf_attr { * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) * Description * Select a **SO_REUSEPORT** socket from a - * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. * It checks the selected socket is matching the incoming * request in the socket buffer. * Return diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index ec14aa725b..74c3b73a5f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -4,8 +4,9 @@ RM ?= rm srctree = $(abs_srctree) +VERSION_SCRIPT := libbpf.map LIBBPF_VERSION := $(shell \ - grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \ + grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \ sort -rV | head -n1 | cut -d'_' -f2) LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) @@ -110,7 +111,6 @@ SHARED_OBJDIR := $(OUTPUT)sharedobjs/ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o -VERSION_SCRIPT := libbpf.map BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) @@ -163,10 +163,10 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) -$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT) $(QUIET_LINK)$(CC) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -lz -o $@ + -Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) @@ -181,7 +181,7 @@ $(OUTPUT)libbpf.pc: check: check_abi -check_abi: $(OUTPUT)libbpf.so +check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ echo "Warning: Num of global symbols in $(BPF_IN_SHARED)" \ "($(GLOBAL_SYM_COUNT)) does NOT match with num of" \ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 6f5e2757bb..2234d5c331 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4479,6 +4479,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b { struct bpf_create_map_attr create_attr; struct bpf_map_def *def = &map->def; + int err = 0; memset(&create_attr, 0, sizeof(create_attr)); @@ -4521,8 +4522,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map_type__is_map_in_map(def->type)) { if (map->inner_map) { - int err; - err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", @@ -4547,8 +4546,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { char *cp, errmsg[STRERR_BUFSIZE]; - int err = -errno; + err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, err); @@ -4560,8 +4559,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b map->fd = bpf_create_map_xattr(&create_attr); } - if (map->fd < 0) - return -errno; + err = map->fd < 0 ? -errno : 0; if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { if (obj->gen_loader) @@ -4570,7 +4568,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b zfree(&map->inner_map); } - return 0; + return err; } static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) @@ -7588,8 +7586,10 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, kconfig = OPTS_GET(opts, kconfig, NULL); if (kconfig) { obj->kconfig = strdup(kconfig); - if (!obj->kconfig) - return ERR_PTR(-ENOMEM); + if (!obj->kconfig) { + err = -ENOMEM; + goto out; + } } err = bpf_object__elf_init(obj); @@ -9515,7 +9515,7 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) struct bpf_prog_info_linear *info_linear; struct bpf_prog_info *info; struct btf *btf = NULL; - int err = -EINVAL; + int err; info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); err = libbpf_get_error(info_linear); @@ -9524,6 +9524,8 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) attach_prog_fd); return err; } + + err = -EINVAL; info = &info_linear->info; if (!info->btf_id) { pr_warn("The target program doesn't have BTF\n"); diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index cdecda1ddd..17a9844e4f 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -296,7 +296,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, out: free(info_linear); - free(btf); + btf__free(btf); return err ? -1 : 0; } @@ -486,7 +486,7 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) perf_env__fetch_btf(env, btf_id, btf); out: - free(btf); + btf__free(btf); close(fd); } diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 8150e03367..beca55129b 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -64,8 +64,8 @@ static char *bpf_target_prog_name(int tgt_fd) struct bpf_prog_info_linear *info_linear; struct bpf_func_info *func_info; const struct btf_type *t; + struct btf *btf = NULL; char *name = NULL; - struct btf *btf; info_linear = bpf_program__get_prog_info_linear( tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); @@ -89,6 +89,7 @@ static char *bpf_target_prog_name(int tgt_fd) } name = strdup(btf__name_by_offset(btf, t->name_off)); out: + btf__free(btf); free(info_linear); return name; }