diff options
Diffstat (limited to 'kernel')
35 files changed, 509 insertions, 214 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8dd73a64f921..b1cb1dbf7417 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -657,7 +657,7 @@ static int audit_filter_rules(struct task_struct *tsk, result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); break; case AUDIT_SADDR_FAM: - if (ctx->sockaddr) + if (ctx && ctx->sockaddr) result = audit_comparator(ctx->sockaddr->ss_family, f->op, f->val); break; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index d6731c32864e..9abcc33f02cf 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -368,6 +368,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; + u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -431,10 +432,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = st_ops->func_models[i].ret_size > 0 ? + BPF_TRAMP_F_RET_FENTRY_RET : 0; err = arch_prepare_bpf_trampoline(NULL, image, st_map->image + PAGE_SIZE, - &st_ops->func_models[i], 0, - tprogs, NULL); + &st_ops->func_models[i], + flags, tprogs, NULL); if (err < 0) goto reset_unlock; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..d6b7dfdd8066 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -827,7 +827,7 @@ int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { - if (!capable(CAP_SYS_ADMIN)) { + if (!bpf_capable()) { atomic_long_sub(pages, &bpf_jit_current); return -EPERM; } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index ca3cd9aaa6ce..7b4afb7d96db 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h index e546b18d27da..a4b040793f44 100644 --- a/kernel/bpf/disasm.h +++ b/kernel/bpf/disasm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e8eefdf8cf3e..6e75bbee39f0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -63,7 +63,8 @@ static inline int stack_map_data_size(struct bpf_map *map) static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { - u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + u64 elem_size = sizeof(struct stack_map_bucket) + + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, @@ -179,7 +180,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * with build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; @@ -204,9 +205,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } if (!work) { - mmap_read_unlock_non_owner(current->mm); + mmap_read_unlock(current->mm); } else { work->mm = current->mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 047ac4b4703b..e76b55917905 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9912,6 +9912,8 @@ static int check_btf_line(struct bpf_verifier_env *env, nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; + if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) + return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 881ce1470beb..570b0c97392a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6572,74 +6572,51 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - -DEFINE_SPINLOCK(cgroup_sk_update_lock); -static bool cgroup_sk_alloc_disabled __read_mostly; - -void cgroup_sk_alloc_disable(void) -{ - if (cgroup_sk_alloc_disabled) - return; - pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); - cgroup_sk_alloc_disabled = true; -} - -#else - -#define cgroup_sk_alloc_disabled false - -#endif - void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) { - skcd->no_refcnt = 1; - return; - } - - /* Don't associate the sock with unrelated interrupted task's cgroup. */ - if (in_interrupt()) - return; + struct cgroup *cgroup; rcu_read_lock(); + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) { + cgroup = &cgrp_dfl_root.cgrp; + cgroup_get(cgroup); + goto out; + } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->val = (unsigned long)cset->dfl_cgrp; - cgroup_bpf_get(cset->dfl_cgrp); + cgroup = cset->dfl_cgrp; break; } cpu_relax(); } - +out: + skcd->cgroup = cgroup; + cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { - if (skcd->val) { - if (skcd->no_refcnt) - return; - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); - } + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); - if (skcd->no_refcnt) - return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index df1ccf4558f8..2a9695ccb65f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -311,17 +311,19 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_mutex and + * There are two global locks guarding cpuset structures - cpuset_rwsem and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. + * comment. The cpuset code uses only cpuset_rwsem write lock. Other + * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to + * prevent change to cpuset structures. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it + * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it * is the only task able to also acquire callback_lock and be able to * modify cpusets. It can perform various checks on the cpuset structure * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_mutex. While it is performing these checks, various + * just holding cpuset_rwsem. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. * Once it is ready to make the changes, it takes callback_lock, blocking * everyone else. @@ -393,7 +395,7 @@ static inline bool is_in_v2_mode(void) * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -435,7 +437,7 @@ out_unlock: * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -447,7 +449,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) @@ -468,7 +470,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_mutex. + * are only set if the other's are set. Call holding cpuset_rwsem. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -577,7 +579,7 @@ static inline void free_cpuset(struct cpuset *cs) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_mutex held. + * cpuset_rwsem held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -700,7 +702,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_mutex held. */ +/* Must be called with cpuset_rwsem held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -726,7 +728,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_mutex held. + * Must be called with cpuset_rwsem held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1005,7 +1007,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_mutex held. Takes cpus_read_lock(). + * Call with cpuset_rwsem held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1078,7 +1080,7 @@ void rebuild_sched_domains(void) * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) @@ -1347,7 +1349,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { @@ -1704,12 +1706,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_mutex */ + static nodemask_t newmems; /* protected by cpuset_rwsem */ struct css_task_iter it; struct task_struct *task; @@ -1722,7 +1724,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_mutex, we know that no other rebind effort + * the global cpuset_rwsem, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -1768,7 +1770,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -1821,7 +1823,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_mutex held. May take callback_lock during call. + * Call with cpuset_rwsem held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -1911,7 +1913,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_mutex held, cpuset membership stays + * function is called with cpuset_rwsem held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -1931,7 +1933,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -1980,7 +1982,7 @@ out: * cs: the cpuset to update * new_prs: new partition root state * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2167,7 +2169,7 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; -/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; @@ -2219,7 +2221,7 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) } /* - * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2227,7 +2229,7 @@ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { - /* static buf protected by cpuset_mutex */ + /* static buf protected by cpuset_rwsem */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; @@ -2417,7 +2419,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy + * grabbing cpuset_rwsem anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -3672,7 +3674,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * and we take cpuset_rwsem, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/cred.c b/kernel/cred.c index f784e08c2fbd..1ae0b4948a5a 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -225,8 +225,6 @@ struct cred *cred_alloc_blank(void) #ifdef CONFIG_DEBUG_CREDENTIALS new->magic = CRED_MAGIC; #endif - new->ucounts = get_ucounts(&init_ucounts); - if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -501,7 +499,7 @@ int commit_creds(struct cred *new) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); - if (new->user != old->user) + if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); alter_cred_subscribers(old, -2); @@ -669,7 +667,7 @@ int set_cred_ucounts(struct cred *new) { struct task_struct *task = current; const struct cred *old = task->real_cred; - struct ucounts *old_ucounts = new->ucounts; + struct ucounts *new_ucounts, *old_ucounts = new->ucounts; if (new->user == old->user && new->user_ns == old->user_ns) return 0; @@ -681,9 +679,10 @@ int set_cred_ucounts(struct cred *new) if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid)) return 0; - if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid))) + if (!(new_ucounts = alloc_ucounts(new->user_ns, new->euid))) return -EAGAIN; + new->ucounts = new_ucounts; if (old_ucounts) put_ucounts(old_ucounts); diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 6c90c69e5311..7a14ca29c377 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -552,7 +552,7 @@ static void active_cacheline_remove(struct dma_debug_entry *entry) * Wrapper function for adding an entry to the hash. * This function takes care of locking itself. */ -static void add_dma_entry(struct dma_debug_entry *entry) +static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs) { struct hash_bucket *bucket; unsigned long flags; @@ -566,8 +566,9 @@ static void add_dma_entry(struct dma_debug_entry *entry) if (rc == -ENOMEM) { pr_err("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; - } else if (rc == -EEXIST) { - pr_err("cacheline tracking EEXIST, overlapping mappings aren't supported\n"); + } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { + err_printk(entry->dev, entry, + "cacheline tracking EEXIST, overlapping mappings aren't supported\n"); } } @@ -1190,7 +1191,8 @@ void debug_dma_map_single(struct device *dev, const void *addr, EXPORT_SYMBOL(debug_dma_map_single); void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, - size_t size, int direction, dma_addr_t dma_addr) + size_t size, int direction, dma_addr_t dma_addr, + unsigned long attrs) { struct dma_debug_entry *entry; @@ -1221,7 +1223,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, check_for_illegal_area(dev, addr, size); } - add_dma_entry(entry); + add_dma_entry(entry, attrs); } void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -1279,7 +1281,8 @@ void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, } void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, int mapped_ents, int direction) + int nents, int mapped_ents, int direction, + unsigned long attrs) { struct dma_debug_entry *entry; struct scatterlist *s; @@ -1288,6 +1291,12 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, if (unlikely(dma_debug_disabled())) return; + for_each_sg(sg, s, nents, i) { + check_for_stack(dev, sg_page(s), s->offset); + if (!PageHighMem(sg_page(s))) + check_for_illegal_area(dev, sg_virt(s), s->length); + } + for_each_sg(sg, s, mapped_ents, i) { entry = dma_entry_alloc(); if (!entry) @@ -1303,15 +1312,9 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, entry->sg_call_ents = nents; entry->sg_mapped_ents = mapped_ents; - check_for_stack(dev, sg_page(s), s->offset); - - if (!PageHighMem(sg_page(s))) { - check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s)); - } - check_sg_segment(dev, s); - add_dma_entry(entry); + add_dma_entry(entry, attrs); } } @@ -1367,7 +1370,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, } void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt) + dma_addr_t dma_addr, void *virt, + unsigned long attrs) { struct dma_debug_entry *entry; @@ -1397,7 +1401,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, else entry->pfn = page_to_pfn(virt_to_page(virt)); - add_dma_entry(entry); + add_dma_entry(entry, attrs); } void debug_dma_free_coherent(struct device *dev, size_t size, @@ -1428,7 +1432,8 @@ void debug_dma_free_coherent(struct device *dev, size_t size, } void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, - int direction, dma_addr_t dma_addr) + int direction, dma_addr_t dma_addr, + unsigned long attrs) { struct dma_debug_entry *entry; @@ -1448,7 +1453,7 @@ void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, entry->direction = direction; entry->map_err_type = MAP_ERR_NOT_CHECKED; - add_dma_entry(entry); + add_dma_entry(entry, attrs); } void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h index 83643b3010b2..f525197d3cae 100644 --- a/kernel/dma/debug.h +++ b/kernel/dma/debug.h @@ -11,26 +11,30 @@ #ifdef CONFIG_DMA_API_DEBUG extern void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction, dma_addr_t dma_addr); + int direction, dma_addr_t dma_addr, + unsigned long attrs); extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, int direction); extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, int mapped_ents, int direction); + int nents, int mapped_ents, int direction, + unsigned long attrs); extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, int dir); extern void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt); + dma_addr_t dma_addr, void *virt, + unsigned long attrs); extern void debug_dma_free_coherent(struct device *dev, size_t size, void *virt, dma_addr_t addr); extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, int direction, - dma_addr_t dma_addr); + dma_addr_t dma_addr, + unsigned long attrs); extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, size_t size, int direction); @@ -53,7 +57,8 @@ extern void debug_dma_sync_sg_for_device(struct device *dev, #else /* CONFIG_DMA_API_DEBUG */ static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction, dma_addr_t dma_addr) + int direction, dma_addr_t dma_addr, + unsigned long attrs) { } @@ -63,7 +68,8 @@ static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, } static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nents, int mapped_ents, int direction) + int nents, int mapped_ents, int direction, + unsigned long attrs) { } @@ -74,7 +80,8 @@ static inline void debug_dma_unmap_sg(struct device *dev, } static inline void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt) + dma_addr_t dma_addr, void *virt, + unsigned long attrs) { } @@ -85,7 +92,8 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size, static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, int direction, - dma_addr_t dma_addr) + dma_addr_t dma_addr, + unsigned long attrs) { } diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 7ee5284bff58..8349a9f2c345 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -156,7 +156,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); else addr = ops->map_page(dev, page, offset, size, dir, attrs); - debug_dma_map_page(dev, page, offset, size, dir, addr); + debug_dma_map_page(dev, page, offset, size, dir, addr, attrs); return addr; } @@ -195,7 +195,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, ents = ops->map_sg(dev, sg, nents, dir, attrs); if (ents > 0) - debug_dma_map_sg(dev, sg, nents, ents, dir); + debug_dma_map_sg(dev, sg, nents, ents, dir, attrs); else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM && ents != -EIO)) return -EIO; @@ -206,7 +206,8 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, /** * dma_map_sg_attrs - Map the given buffer for DMA * @dev: The device for which to perform the DMA operation - * @sg: The sg_table object describing the buffer + * @sg: The sg_table object describing the buffer + * @nents: Number of entries to map * @dir: DMA direction * @attrs: Optional DMA attributes for the map operation * @@ -248,12 +249,12 @@ EXPORT_SYMBOL(dma_map_sg_attrs); * Returns 0 on success or a negative error code on error. The following * error codes are supported with the given meaning: * - * -EINVAL - An invalid argument, unaligned access or other error - * in usage. Will not succeed if retried. - * -ENOMEM - Insufficient resources (like memory or IOVA space) to - * complete the mapping. Should succeed if retried later. - * -EIO - Legacy error code with an unknown meaning. eg. this is - * returned if a lower level call returned DMA_MAPPING_ERROR. + * -EINVAL An invalid argument, unaligned access or other error + * in usage. Will not succeed if retried. + * -ENOMEM Insufficient resources (like memory or IOVA space) to + * complete the mapping. Should succeed if retried later. + * -EIO Legacy error code with an unknown meaning. eg. this is + * returned if a lower level call returned DMA_MAPPING_ERROR. */ int dma_map_sgtable(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir, unsigned long attrs) @@ -304,7 +305,7 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, else if (ops->map_resource) addr = ops->map_resource(dev, phys_addr, size, dir, attrs); - debug_dma_map_resource(dev, phys_addr, size, dir, addr); + debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs); return addr; } EXPORT_SYMBOL(dma_map_resource); @@ -509,7 +510,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, else return NULL; - debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); + debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, attrs); return cpu_addr; } EXPORT_SYMBOL(dma_alloc_attrs); @@ -565,7 +566,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp); if (page) - debug_dma_map_page(dev, page, 0, size, dir, *dma_handle); + debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0); return page; } EXPORT_SYMBOL_GPL(dma_alloc_pages); @@ -643,7 +644,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, if (sgt) { sgt->nents = 1; - debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir); + debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs); } return sgt; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index bf16395b9e13..d5a61d565ad5 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) handle_signal_work(regs, ti_work); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } /* Architecture specific TIF work */ arch_exit_to_user_mode_work(regs, ti_work); diff --git a/kernel/events/core.c b/kernel/events/core.c index 744e8726c5b2..f23ca260307f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +static inline bool event_update_userpage(struct perf_event *event) +{ + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +} + +static inline void group_update_userpage(struct perf_event *group_event) +{ + struct perf_event *event; + + if (!event_update_userpage(group_event)) + return; + + for_each_sibling_event(event, group_event) + event_update_userpage(event); +} + static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; @@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { + *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } else { + ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); + group_update_userpage(event); } - - *can_add_hw = 0; - ctx->rotate_necessary = 1; - perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6324,6 +6348,8 @@ accounting: ring_buffer_attach(event, rb); + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { @@ -10193,7 +10219,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event) return; if (ifh->nr_file_filters) { - mm = get_task_mm(event->ctx->task); + mm = get_task_mm(task); if (!mm) goto restart; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 19e83e9b723c..4d8fc65cf38f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); * Allocates and initializes an irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index d456579d0952..2fede72b6af5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -94,6 +94,9 @@ static inline unsigned long __owner_flags(unsigned long owner) return owner & MUTEX_FLAGS; } +/* + * Returns: __mutex_owner(lock) on failure or NULL on success. + */ static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff) { unsigned long owner, curr = (unsigned long)current; @@ -736,6 +739,44 @@ __ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass, return __mutex_lock_common(lock, state, subclass, NULL, ip, ww_ctx, true); } +/** + * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context + * @ww: mutex to lock + * @ww_ctx: optional w/w acquire context + * + * Trylocks a mutex with the optional acquire context; no deadlock detection is + * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. + * + * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is + * specified, -EALREADY handling may happen in calls to ww_mutex_trylock. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) +{ + if (!ww_ctx) + return mutex_trylock(&ww->base); + + MUTEX_WARN_ON(ww->base.magic != &ww->base); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__mutex_trylock(&ww->base)) { + ww_mutex_set_context_fastpath(ww, ww_ctx); + mutex_acquire_nest(&ww->base.dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 4ba15088e640..88191f6e252c 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -41,6 +41,12 @@ * The risk of writer starvation is there, but the pathological use cases * which trigger it are not necessarily the typical RT workloads. * + * Fast-path orderings: + * The lock/unlock of readers can run in fast paths: lock and unlock are only + * atomic ops, and there is no inner lock to provide ACQUIRE and RELEASE + * semantics of rwbase_rt. Atomic ops should thus provide _acquire() + * and _release() (or stronger). + * * Common code shared between RT rw_semaphore and rwlock */ @@ -53,6 +59,7 @@ static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb) * set. */ for (r = atomic_read(&rwb->readers); r < 0;) { + /* Fully-ordered if cmpxchg() succeeds, provides ACQUIRE */ if (likely(atomic_try_cmpxchg(&rwb->readers, &r, r + 1))) return 1; } @@ -162,6 +169,8 @@ static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb, /* * rwb->readers can only hit 0 when a writer is waiting for the * active readers to leave the critical section. + * + * dec_and_test() is fully ordered, provides RELEASE. */ if (unlikely(atomic_dec_and_test(&rwb->readers))) __rwbase_read_unlock(rwb, state); @@ -172,7 +181,11 @@ static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias, { struct rt_mutex_base *rtm = &rwb->rtmutex; - atomic_add(READER_BIAS - bias, &rwb->readers); + /* + * _release() is needed in case that reader is in fast path, pairing + * with atomic_try_cmpxchg() in rwbase_read_trylock(), provides RELEASE + */ + (void)atomic_add_return_release(READER_BIAS - bias, &rwb->readers); raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); rwbase_rtmutex_unlock(rtm); } @@ -196,6 +209,23 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb) __rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags); } +static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb) +{ + /* Can do without CAS because we're serialized by wait_lock. */ + lockdep_assert_held(&rwb->rtmutex.wait_lock); + + /* + * _acquire is needed in case the reader is in the fast path, pairing + * with rwbase_read_unlock(), provides ACQUIRE. + */ + if (!atomic_read_acquire(&rwb->readers)) { + atomic_set(&rwb->readers, WRITER_BIAS); + return 1; + } + + return 0; +} + static int __sched rwbase_write_lock(struct rwbase_rt *rwb, unsigned int state) { @@ -210,34 +240,30 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb, atomic_sub(READER_BIAS, &rwb->readers); raw_spin_lock_irqsave(&rtm->wait_lock, flags); - /* - * set_current_state() for rw_semaphore - * current_save_and_set_rtlock_wait_state() for rwlock - */ - rwbase_set_and_save_current_state(state); + if (__rwbase_write_trylock(rwb)) + goto out_unlock; - /* Block until all readers have left the critical section. */ - for (; atomic_read(&rwb->readers);) { + rwbase_set_and_save_current_state(state); + for (;;) { /* Optimized out for rwlocks */ if (rwbase_signal_pending_state(state, current)) { - __set_current_state(TASK_RUNNING); + rwbase_restore_current_state(); __rwbase_write_unlock(rwb, 0, flags); return -EINTR; } + + if (__rwbase_write_trylock(rwb)) + break; + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); + rwbase_schedule(); + raw_spin_lock_irqsave(&rtm->wait_lock, flags); - /* - * Schedule and wait for the readers to leave the critical - * section. The last reader leaving it wakes the waiter. - */ - if (atomic_read(&rwb->readers) != 0) - rwbase_schedule(); set_current_state(state); - raw_spin_lock_irqsave(&rtm->wait_lock, flags); } - - atomic_set(&rwb->readers, WRITER_BIAS); rwbase_restore_current_state(); + +out_unlock: raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); return 0; } @@ -253,8 +279,7 @@ static inline int rwbase_write_trylock(struct rwbase_rt *rwb) atomic_sub(READER_BIAS, &rwb->readers); raw_spin_lock_irqsave(&rtm->wait_lock, flags); - if (!atomic_read(&rwb->readers)) { - atomic_set(&rwb->readers, WRITER_BIAS); + if (__rwbase_write_trylock(rwb)) { raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); return 1; } diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 3e82f449b4ff..d63ac411f367 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -16,6 +16,15 @@ static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +#define ww_acquire_init_noinject(a, b) do { \ + ww_acquire_init((a), (b)); \ + (a)->deadlock_inject_countdown = ~0U; \ + } while (0) +#else +#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b)) +#endif + struct test_mutex { struct work_struct work; struct ww_mutex mutex; @@ -36,7 +45,7 @@ static void test_mutex_work(struct work_struct *work) wait_for_completion(&mtx->go); if (mtx->flags & TEST_MTX_TRY) { - while (!ww_mutex_trylock(&mtx->mutex)) + while (!ww_mutex_trylock(&mtx->mutex, NULL)) cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); @@ -109,19 +118,38 @@ static int test_mutex(void) return 0; } -static int test_aa(void) +static int test_aa(bool trylock) { struct ww_mutex mutex; struct ww_acquire_ctx ctx; int ret; + const char *from = trylock ? "trylock" : "lock"; ww_mutex_init(&mutex, &ww_class); ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&mutex, &ctx); + if (!trylock) { + ret = ww_mutex_lock(&mutex, &ctx); + if (ret) { + pr_err("%s: initial lock failed!\n", __func__); + goto out; + } + } else { + if (!ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: initial trylock failed!\n", __func__); + goto out; + } + } - if (ww_mutex_trylock(&mutex)) { - pr_err("%s: trylocked itself!\n", __func__); + if (ww_mutex_trylock(&mutex, NULL)) { + pr_err("%s: trylocked itself without context from %s!\n", __func__, from); + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + if (ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: trylocked itself with context from %s!\n", __func__, from); ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; @@ -129,17 +157,17 @@ static int test_aa(void) ret = ww_mutex_lock(&mutex, &ctx); if (ret != -EALREADY) { - pr_err("%s: missed deadlock for recursing, ret=%d\n", - __func__, ret); + pr_err("%s: missed deadlock for recursing, ret=%d from %s\n", + __func__, ret, from); if (!ret) ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; } + ww_mutex_unlock(&mutex); ret = 0; out: - ww_mutex_unlock(&mutex); ww_acquire_fini(&ctx); return ret; } @@ -150,7 +178,7 @@ struct test_abba { struct ww_mutex b_mutex; struct completion a_ready; struct completion b_ready; - bool resolve; + bool resolve, trylock; int result; }; @@ -160,8 +188,13 @@ static void test_abba_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err; - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba->b_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!abba->trylock) + ww_mutex_lock(&abba->b_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx); complete(&abba->b_ready); wait_for_completion(&abba->a_ready); @@ -181,7 +214,7 @@ static void test_abba_work(struct work_struct *work) abba->result = err; } -static int test_abba(bool resolve) +static int test_abba(bool trylock, bool resolve) { struct test_abba abba; struct ww_acquire_ctx ctx; @@ -192,12 +225,18 @@ static int test_abba(bool resolve) INIT_WORK_ONSTACK(&abba.work, test_abba_work); init_completion(&abba.a_ready); init_completion(&abba.b_ready); + abba.trylock = trylock; abba.resolve = resolve; schedule_work(&abba.work); - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba.a_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!trylock) + ww_mutex_lock(&abba.a_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx); complete(&abba.a_ready); wait_for_completion(&abba.b_ready); @@ -249,7 +288,7 @@ static void test_cycle_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err, erra = 0; - ww_acquire_init(&ctx, &ww_class); + ww_acquire_init_noinject(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); complete(cycle->a_signal); @@ -581,7 +620,9 @@ static int stress(int nlocks, int nthreads, unsigned int flags) static int __init test_ww_mutex_init(void) { int ncpus = num_online_cpus(); - int ret; + int ret, i; + + printk(KERN_INFO "Beginning ww mutex selftests\n"); wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); if (!wq) @@ -591,17 +632,19 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = test_aa(); + ret = test_aa(false); if (ret) return ret; - ret = test_abba(false); + ret = test_aa(true); if (ret) return ret; - ret = test_abba(true); - if (ret) - return ret; + for (i = 0; i < 4; i++) { + ret = test_abba(i & 1, i & 2); + if (ret) + return ret; + } ret = test_cycle(ncpus); if (ret) @@ -619,6 +662,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; + printk(KERN_INFO "All ww mutex selftests passed\n"); return 0; } diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c index 3f1fff7d2780..0e00205cf467 100644 --- a/kernel/locking/ww_rt_mutex.c +++ b/kernel/locking/ww_rt_mutex.c @@ -9,6 +9,31 @@ #define WW_RT #include "rtmutex.c" +int ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex *rtm = &lock->base; + + if (!ww_ctx) + return rt_mutex_trylock(rtm); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__rt_mutex_trylock(&rtm->rtmutex)) { + ww_mutex_set_context_fastpath(lock, ww_ctx); + mutex_acquire_nest(&rtm->dep_map, 0, 1, ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + static int __sched __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, unsigned long ip) diff --git a/kernel/module.c b/kernel/module.c index 40ec9a030eec..5c26a76e800b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4489,8 +4489,10 @@ static void cfi_init(struct module *mod) /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; +#ifdef CONFIG_MODULE_UNLOAD if (exit) mod->exit = *exit; +#endif cfi_module_add(mod, module_addr_min); #endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 825277e1e742..a8d0a58deebc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free(__pa(new_descs), new_descs_size); + memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: - memblock_free(__pa(new_log_buf), new_log_buf_len); + memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/kernel/rseq.c b/kernel/rseq.c index 35f7bd0fced0..6d45ac3dae7f 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -282,9 +282,17 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(t->flags & PF_EXITING)) return; - ret = rseq_ip_fixup(regs); - if (unlikely(ret < 0)) - goto error; + + /* + * regs is NULL if and only if the caller is in a syscall path. Skip + * fixup and leave rseq_cs as is so that rseq_sycall() will detect and + * kill a misbehaving userspace on debug kernels. + */ + if (regs) { + ret = rseq_ip_fixup(regs); + if (unlikely(ret < 0)) + goto error; + } if (unlikely(rseq_update_cpu_id(t))) goto error; return; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1bba4128a3e6..f21714ea3db8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8795,6 +8795,7 @@ void idle_task_exit(void) finish_arch_post_lock_switch(); } + scs_task_reset(current); /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 49716228efb4..17a653b67006 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[16]; + unsigned int scaling; if (cnt > 15) cnt = 15; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; - if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling)) + if (kstrtouint(buf, 10, &scaling)) return -EINVAL; + if (scaling >= SCHED_TUNABLESCALING_END) + return -EINVAL; + + sysctl_sched_tunable_scaling = scaling; if (sched_update_scaling()) return -EINVAL; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ff69f245b939..f6a05d9b5443 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - if (!cfs_rq->load.weight) + /* Nothing to run but something to decay (on_list)? Complete the branch */ + if (!cfs_rq->load.weight) { + if (cfs_rq->on_list) + goto unthrottle_throttle; return; + } task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; diff --git a/kernel/signal.c b/kernel/signal.c index 952741f6d0f9..487bf4f5dadf 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -426,22 +426,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, */ rcu_read_lock(); ucounts = task_ucounts(t); - sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1); - switch (sigpending) { - case 1: - if (likely(get_ucounts(ucounts))) - break; - fallthrough; - case LONG_MAX: - /* - * we need to decrease the ucount in the userns tree on any - * failure to avoid counts leaking. - */ - dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1); - rcu_read_unlock(); - return NULL; - } + sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); + if (!sigpending) + return NULL; if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); @@ -450,8 +438,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, } if (unlikely(q == NULL)) { - if (dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) - put_ucounts(ucounts); + dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); } else { INIT_LIST_HEAD(&q->list); q->flags = sigqueue_flags; @@ -464,8 +451,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) { - put_ucounts(q->ucounts); + if (q->ucounts) { + dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING); q->ucounts = NULL; } kmem_cache_free(sigqueue_cachep, q); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ee736861b18f..643d412ac623 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1404,7 +1404,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, } } - *newval += now; + if (*newval) + *newval += now; } /* diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c221e4c3f625..fa91f398f28b 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1605,6 +1605,14 @@ static int blk_trace_remove_queue(struct request_queue *q) if (bt == NULL) return -EINVAL; + if (bt->trace_state == Blktrace_running) { + bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); + relay_flush(bt->rchan); + } + put_probe_ref(); synchronize_rcu(); blk_trace_free(bt); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7efbc8aaf7f6..635fbdc9d589 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6977,7 +6977,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op; int bit; - bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START); if (bit < 0) return; @@ -7052,7 +7052,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, { int bit; - bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START); if (bit < 0) return; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7896d30d90f7..bc677cd64224 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1744,16 +1744,15 @@ void latency_fsnotify(struct trace_array *tr) irq_work_queue(&tr->fsnotify_irqwork); } -/* - * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ - * defined(CONFIG_FSNOTIFY) - */ -#else +#elif defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) \ + || defined(CONFIG_OSNOISE_TRACER) #define trace_create_maxlat_file(tr, d_tracer) \ trace_create_file("tracing_max_latency", 0644, d_tracer, \ &tr->max_latency, &tracing_max_lat_fops) +#else +#define trace_create_maxlat_file(tr, d_tracer) do { } while (0) #endif #ifdef CONFIG_TRACER_MAX_TRACE @@ -9473,9 +9472,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) create_trace_options_dir(tr); -#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) trace_create_maxlat_file(tr, d_tracer); -#endif if (ftrace_create_function_files(tr, d_tracer)) MEM_FAIL(1, "Could not allocate function filter files"); diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 3044b762cbd7..c4a15aef36af 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -119,10 +119,58 @@ static bool eprobe_dyn_event_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev) { struct trace_eprobe *ep = to_trace_eprobe(ev); + const char *slash; - return strcmp(trace_probe_name(&ep->tp), event) == 0 && - (!system || strcmp(trace_probe_group_name(&ep->tp), system) == 0) && - trace_probe_match_command_args(&ep->tp, argc, argv); + /* + * We match the following: + * event only - match all eprobes with event name + * system and event only - match all system/event probes + * + * The below has the above satisfied with more arguments: + * + * attached system/event - If the arg has the system and event + * the probe is attached to, match + * probes with the attachment. + * + * If any more args are given, then it requires a full match. + */ + + /* + * If system exists, but this probe is not part of that system + * do not match. + */ + if (system && strcmp(trace_probe_group_name(&ep->tp), system) != 0) + return false; + + /* Must match the event name */ + if (strcmp(trace_probe_name(&ep->tp), event) != 0) + return false; + + /* No arguments match all */ + if (argc < 1) + return true; + + /* First argument is the system/event the probe is attached to */ + + slash = strchr(argv[0], '/'); + if (!slash) + slash = strchr(argv[0], '.'); + if (!slash) + return false; + + if (strncmp(ep->event_system, argv[0], slash - argv[0])) + return false; + if (strcmp(ep->event_name, slash + 1)) + return false; + + argc--; + argv++; + + /* If there are no other args, then match */ + if (argc < 1) + return true; + + return trace_probe_match_command_args(&ep->tp, argc, argv); } static struct dyn_event_operations eprobe_dyn_event_ops = { @@ -632,6 +680,13 @@ static int disable_eprobe(struct trace_eprobe *ep, trace_event_trigger_enable_disable(file, 0); update_cond_flag(file); + + /* Make sure nothing is using the edata or trigger */ + tracepoint_synchronize_unregister(); + + kfree(edata); + kfree(trigger); + return 0; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index a6061a69aa84..f01e442716e2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2506,7 +2506,7 @@ find_synthetic_field_var(struct hist_trigger_data *target_hist_data, * events. However, for convenience, users are allowed to directly * specify an event field in an action, which will be automatically * converted into a variable on their behalf. - + * * If a user specifies a field on an event that isn't the event the * histogram currently being defined (the target event histogram), the * only way that can be accomplished is if a new hist trigger is diff --git a/kernel/ucount.c b/kernel/ucount.c index bb51849e6375..eb03f3c68375 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -284,6 +284,55 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) return (new == 0); } +static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, + struct ucounts *last, enum ucount_type type) +{ + struct ucounts *iter, *next; + for (iter = ucounts; iter != last; iter = next) { + long dec = atomic_long_add_return(-1, &iter->ucount[type]); + WARN_ON_ONCE(dec < 0); + next = iter->ns->ucounts; + if (dec == 0) + put_ucounts(iter); + } +} + +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type) +{ + do_dec_rlimit_put_ucounts(ucounts, NULL, type); +} + +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type) +{ + /* Caller must hold a reference to ucounts */ + struct ucounts *iter; + long dec, ret = 0; + + for (iter = ucounts; iter; iter = iter->ns->ucounts) { + long max = READ_ONCE(iter->ns->ucount_max[type]); + long new = atomic_long_add_return(1, &iter->ucount[type]); + if (new < 0 || new > max) + goto unwind; + if (iter == ucounts) + ret = new; + /* + * Grab an extra ucount reference for the caller when + * the rlimit count was previously 0. + */ + if (new != 1) + continue; + if (!get_ucounts(iter)) + goto dec_unwind; + } + return ret; +dec_unwind: + dec = atomic_long_add_return(-1, &iter->ucount[type]); + WARN_ON_ONCE(dec < 0); +unwind: + do_dec_rlimit_put_ucounts(ucounts, iter, type); + return 0; +} + bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max) { struct ucounts *iter; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33a6b4a2443d..1b3eb1e9531f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4830,8 +4830,16 @@ void show_workqueue_state(void) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); show_pwq(pwq); + printk_deferred_exit(); + } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. @@ -4849,7 +4857,12 @@ void show_workqueue_state(void) raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; - + /* + * Defer printing to avoid deadlocks in console drivers that + * queue work while holding locks also taken in their write + * paths. + */ + printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%us workers=%d", @@ -4864,6 +4877,7 @@ void show_workqueue_state(void) first = false; } pr_cont("\n"); + printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, flags); /* |