diff options
Diffstat (limited to 'kernel')
39 files changed, 220 insertions, 151 deletions
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a10e2997aa6c..333b3bcfc545 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -681,7 +681,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->values[i] = AUDIT_UID_UNSET; break; } - /* fall through - if set */ + fallthrough; /* if set */ default: data->values[i] = f->val; } diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b6715964b685..8faa2ce89396 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq) iter_priv->done_stop = true; } +/* maximum visited objects before bailing out */ +#define MAX_ITER_OBJECTS 1000000 + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; - int err = 0; + int err = 0, num_objs = 0; void *p; mutex_lock(&seq->lock); @@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, while (1) { loff_t pos = seq->index; + num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { @@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, if (seq->count >= size) break; + if (num_objs >= MAX_ITER_OBJECTS) { + if (offs == 0) { + err = -EAGAIN; + seq->op->stop(seq, p); + goto done; + } + break; + } + err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 83ff127ef7ae..e21de4f1754c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1794,7 +1794,7 @@ static bool cg_sockopt_is_valid_access(int off, int size, return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; case offsetof(struct bpf_sockopt, optname): - /* fallthrough */ + fallthrough; case offsetof(struct bpf_sockopt, level): if (size != size_default) return false; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index f1c46529929b..6386b7bb98f2 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -279,7 +279,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, break; default: bpf_warn_invalid_xdp_action(act); - /* fallthrough */ + fallthrough; case XDP_DROP: xdp_return_frame(xdpf); stats->drop++; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4fd830a62be2..cfed0ac44d38 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr, phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } @@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr, phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 86299a292214..1bf960aa615c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2029,7 +2029,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; - /* fallthrough */ + fallthrough; default: return 0; } diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 232df29793e9..99af4cea1102 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, rcu_read_lock(); retry: - pid = idr_get_next(&ns->idr, tid); + pid = find_ge_pid(*tid, ns); if (pid) { + *tid = pid_nr_ns(pid, ns); task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ++*tid; @@ -178,10 +179,11 @@ again: f = fcheck_files(curr_files, curr_fd); if (!f) continue; + if (!get_file_rcu(f)) + continue; /* set info->fd */ info->fd = curr_fd; - get_file(f); rcu_read_unlock(); return f; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ef938f17b944..47e74f09fa37 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5236,7 +5236,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, off_reg == dst_reg ? dst : src); return -EACCES; } - /* fall-through */ + fallthrough; default: break; } @@ -10988,7 +10988,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) default: if (!prog_extension) return -EINVAL; - /* fallthrough */ + fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_TRACE_FENTRY: diff --git a/kernel/capability.c b/kernel/capability.c index 1444f3954d75..7c59b096c98a 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -93,7 +93,7 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); - /* fall through - v3 is otherwise equivalent to v2. */ + fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; diff --git a/kernel/compat.c b/kernel/compat.c index b8d2800bb4b7..05adfd6fa8bf 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -255,11 +255,11 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) return -EFAULT; switch (_NSIG_WORDS) { case 4: set->sig[3] = v.sig[6] | (((long)v.sig[7]) << 32 ); - /* fall through */ + fallthrough; case 3: set->sig[2] = v.sig[4] | (((long)v.sig[5]) << 32 ); - /* fall through */ + fallthrough; case 2: set->sig[1] = v.sig[2] | (((long)v.sig[3]) << 32 ); - /* fall through */ + fallthrough; case 1: set->sig[0] = v.sig[0] | (((long)v.sig[1]) << 32 ); } #else diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index a790026e42d0..cc3c43dfec44 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1046,14 +1046,14 @@ int gdb_serial_stub(struct kgdb_state *ks) return DBG_PASS_EVENT; } #endif - /* Fall through */ + fallthrough; case 'C': /* Exception passing */ tmp = gdb_cmd_exception_pass(ks); if (tmp > 0) goto default_handle; if (tmp == 0) break; - /* Fall through - on tmp < 0 */ + fallthrough; /* on tmp < 0 */ case 'c': /* Continue packet */ case 's': /* Single step packet */ if (kgdb_contthread && kgdb_contthread != current) { @@ -1062,7 +1062,7 @@ int gdb_serial_stub(struct kgdb_state *ks) break; } dbg_activate_sw_breakpoints(); - /* Fall through - to default processing */ + fallthrough; /* to default processing */ default: default_handle: error = kgdb_arch_handle_exception(ks->ex_vector, diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 750497b0003a..f877a0a0d7cf 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -173,11 +173,11 @@ int kdb_get_kbd_char(void) case KT_LATIN: if (isprint(keychar)) break; /* printable characters */ - /* fall through */ + fallthrough; case KT_SPEC: if (keychar == K_ENTER) break; - /* fall through */ + fallthrough; default: return -1; /* ignore unprintables */ } diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 004c5b6c87f8..6226502ce049 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_getphysword: bad width %ld\n", (long) size); @@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_getword: bad width %ld\n", (long) size); @@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) diag = kdb_putarea(addr, w8); break; } - /* fall through */ + fallthrough; default: diag = KDB_BADWIDTH; kdb_printf("kdb_putword: bad width %ld\n", (long) size); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 5732b2b3ef17..847a9d1fa634 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -1,5 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only +config NO_DMA + bool + config HAS_DMA bool depends on !NO_DMA diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index bb0041e99659..db6ef07aec3b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev) return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, u64 *phys_limit) { u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); @@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, return 0; } -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <= min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); @@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, size, &page, gfp); - if (!ret) + u64 phys_mask; + + gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); + page = dma_alloc_from_pool(dev, size, &ret, gfp, + dma_coherent_ok); + if (!page) return NULL; goto done; } diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 6bc74a2d5127..1281c0f0442b 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -3,7 +3,9 @@ * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2020 Google LLC */ +#include <linux/cma.h> #include <linux/debugfs.h> +#include <linux/dma-contiguous.h> #include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> #include <linux/init.h> @@ -55,11 +57,34 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size) pool_size_kernel += size; } +static bool cma_in_zone(gfp_t gfp) +{ + unsigned long size; + phys_addr_t end; + struct cma *cma; + + cma = dev_get_cma_area(NULL); + if (!cma) + return false; + + size = cma_get_size(cma); + if (!size) + return false; + + /* CMA can't cross zone boundaries, see cma_activate_area() */ + end = cma_get_base(cma) + size - 1; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return end <= DMA_BIT_MASK(zone_dma_bits); + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return end <= DMA_BIT_MASK(32); + return true; +} + static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, gfp_t gfp) { unsigned int order; - struct page *page; + struct page *page = NULL; void *addr; int ret = -ENOMEM; @@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, do { pool_size = 1 << (PAGE_SHIFT + order); - page = alloc_pages(gfp, order); + if (cma_in_zone(gfp)) + page = dma_alloc_from_contiguous(NULL, 1 << order, + order, false); + if (!page) + page = alloc_pages(gfp, order); } while (!page && order-- > 0); if (!page) goto out; @@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void) } postcore_initcall(dma_atomic_pool_init); -static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev) +static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { - u64 phys_mask; - gfp_t gfp; - - gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); - if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA) + if (prev == NULL) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return atomic_pool_dma32; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return atomic_pool_dma; + return atomic_pool_kernel; + } + if (prev == atomic_pool_kernel) + return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; + if (prev == atomic_pool_dma32) return atomic_pool_dma; - if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32) - return atomic_pool_dma32; - return atomic_pool_kernel; + return NULL; } -static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool) +static struct page *__dma_alloc_from_pool(struct device *dev, size_t size, + struct gen_pool *pool, void **cpu_addr, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { - if (bad_pool == atomic_pool_kernel) - return atomic_pool_dma32 ? : atomic_pool_dma; + unsigned long addr; + phys_addr_t phys; - if (bad_pool == atomic_pool_dma32) - return atomic_pool_dma; + addr = gen_pool_alloc(pool, size); + if (!addr) + return NULL; - return NULL; -} + phys = gen_pool_virt_to_phys(pool, addr); + if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) { + gen_pool_free(pool, addr, size); + return NULL; + } -static inline struct gen_pool *dma_guess_pool(struct device *dev, - struct gen_pool *bad_pool) -{ - if (bad_pool) - return dma_get_safer_pool(bad_pool); + if (gen_pool_avail(pool) < atomic_pool_size) + schedule_work(&atomic_pool_work); - return dma_guess_pool_from_device(dev); + *cpu_addr = (void *)addr; + memset(*cpu_addr, 0, size); + return pfn_to_page(__phys_to_pfn(phys)); } -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags) +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t gfp, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { struct gen_pool *pool = NULL; - unsigned long val = 0; - void *ptr = NULL; - phys_addr_t phys; - - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) { - WARN(1, "Failed to get suitable pool for %s\n", - dev_name(dev)); - break; - } - - val = gen_pool_alloc(pool, size); - if (!val) - continue; - - phys = gen_pool_virt_to_phys(pool, val); - if (dma_coherent_ok(dev, phys, size)) - break; - - gen_pool_free(pool, val, size); - val = 0; - } - - - if (val) { - *ret_page = pfn_to_page(__phys_to_pfn(phys)); - ptr = (void *)val; - memset(ptr, 0, size); + struct page *page; - if (gen_pool_avail(pool) < atomic_pool_size) - schedule_work(&atomic_pool_work); + while ((pool = dma_guess_pool(pool, gfp))) { + page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, + phys_addr_ok); + if (page) + return page; } - return ptr; + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + return NULL; } bool dma_free_from_pool(struct device *dev, void *start, size_t size) { struct gen_pool *pool = NULL; - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) - return false; - - if (gen_pool_has_addr(pool, (unsigned long)start, size)) { - gen_pool_free(pool, (unsigned long)start, size); - return true; - } + while ((pool = dma_guess_pool(pool, 0))) { + if (!gen_pool_has_addr(pool, (unsigned long)start, size)) + continue; + gen_pool_free(pool, (unsigned long)start, size); + return true; } + + return false; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 9852e0d62d95..fcae019158ca 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -65,7 +65,8 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, syscall_enter_audit(regs, syscall); - return ret ? : syscall; + /* The above might have changed the syscall number */ + return ret ? : syscall_get_nr(current, regs); } noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) diff --git a/kernel/events/core.c b/kernel/events/core.c index 5bfe8e3c6e44..7ed5248f0445 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10034,7 +10034,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, case IF_SRC_KERNELADDR: case IF_SRC_KERNEL: kernel = 1; - /* fall through */ + fallthrough; case IF_SRC_FILEADDR: case IF_SRC_FILE: diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 649fd53dc9ad..0e18aaf23a7b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a8e14c80b405..762a928e18f9 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -173,7 +173,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags __irq_wake_thread(desc, action); - /* Fall through - to add to randomness */ + fallthrough; /* to add to randomness */ case IRQ_HANDLED: *flags |= action->flags; break; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 52ac5391dcc6..5df903fccb60 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -271,7 +271,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); - /* fall through */ + fallthrough; case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); @@ -868,7 +868,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags) case IRQ_SET_MASK_OK_DONE: irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); irqd_set(&desc->irq_data, flags); - /* fall through */ + fallthrough; case IRQ_SET_MASK_OK_NOCOPY: flags = irqd_get_trigger_type(&desc->irq_data); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 95cb74f73292..4fb15fa96734 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -684,12 +684,12 @@ bool kallsyms_show_value(const struct cred *cred) case 0: if (kallsyms_for_perf()) return true; - /* fallthrough */ + fallthrough; case 1: if (security_capable(cred, &init_user_ns, CAP_SYSLOG, CAP_OPT_NOAUDIT) == 0) return true; - /* fallthrough */ + fallthrough; default: return false; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 2fad21d345b0..54b74fabf40c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3756,7 +3756,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip) skip_checks: /* we'll do an OFF -> ON transition: */ - this_cpu_write(hardirqs_enabled, 1); + __this_cpu_write(hardirqs_enabled, 1); trace->hardirq_enable_ip = ip; trace->hardirq_enable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_on_events); @@ -3795,7 +3795,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip) /* * We have done an ON -> OFF transition: */ - this_cpu_write(hardirqs_enabled, 0); + __this_cpu_write(hardirqs_enabled, 0); trace->hardirq_disable_ip = ip; trace->hardirq_disable_event = ++trace->irq_events; debug_atomic_inc(hardirqs_off_events); @@ -4977,6 +4977,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, { unsigned long flags; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); + if (unlikely(current->lockdep_recursion)) { /* XXX allow trylock from NMI ?!? */ if (lockdep_nmi() && !trylock) { @@ -5001,7 +5003,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, check_flags(flags); current->lockdep_recursion++; - trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, irqs_disabled_flags(flags), nest_lock, ip, 0, 0); lockdep_recursion_finish(); @@ -5013,13 +5014,15 @@ void lock_release(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_release(lock, ip); + if (unlikely(current->lockdep_recursion)) return; raw_local_irq_save(flags); check_flags(flags); + current->lockdep_recursion++; - trace_lock_release(lock, ip); if (__lock_release(lock, ip)) check_chain_key(current); lockdep_recursion_finish(); @@ -5205,8 +5208,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip) hlock->holdtime_stamp = now; } - trace_lock_acquired(lock, ip); - stats = get_lock_stats(hlock_class(hlock)); if (waittime) { if (hlock->read) @@ -5225,6 +5226,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_acquired(lock, ip); + if (unlikely(!lock_stat || !debug_locks)) return; @@ -5234,7 +5237,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion++; - trace_lock_contended(lock, ip); __lock_contended(lock, ip); lockdep_recursion_finish(); raw_local_irq_restore(flags); @@ -5245,6 +5247,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; + trace_lock_contended(lock, ip); + if (unlikely(!lock_stat || !debug_locks)) return; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index f33769f97aca..e7aa57fb2fdc 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -659,7 +659,7 @@ static void power_down(void) break; case HIBERNATION_PLATFORM: hibernation_platform_enter(); - /* Fall through */ + fallthrough; case HIBERNATION_SHUTDOWN: if (pm_power_off) kernel_power_off(); diff --git a/kernel/power/qos.c b/kernel/power/qos.c index db0bed2cae26..ec7e1e85923e 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -119,7 +119,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, * and add, then see if the aggregate has changed. */ plist_del(node, &c->list); - /* fall through */ + fallthrough; case PM_QOS_ADD_REQ: plist_node_init(node, new_value); plist_add(node, &c->list); @@ -188,7 +188,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf, break; case PM_QOS_UPDATE_REQ: pm_qos_flags_remove_req(pqf, req); - /* fall through */ + fallthrough; case PM_QOS_ADD_REQ: req->flags = val; INIT_LIST_HEAD(&req->node); diff --git a/kernel/relay.c b/kernel/relay.c index 72fe443ea78f..fb4e0c530c08 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -197,6 +197,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8471a0f7eb32..2d95dc3f4644 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2320,7 +2320,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) state = possible; break; } - /* Fall-through */ + fallthrough; case possible: do_set_cpus_allowed(p, cpu_possible_mask); state = fail; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 6bf34986f45c..f324dc36fc43 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -54,17 +54,18 @@ __setup("hlt", cpu_idle_nopoll_setup); static noinline int __cpuidle cpu_idle_poll(void) { + trace_cpu_idle(0, smp_processor_id()); + stop_critical_timings(); rcu_idle_enter(); - trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); - stop_critical_timings(); while (!tif_need_resched() && - (cpu_idle_force_poll || tick_check_broadcast_expired())) + (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); - start_critical_timings(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + start_critical_timings(); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); return 1; } @@ -90,9 +91,14 @@ void __cpuidle default_idle_call(void) if (current_clr_polling_and_test()) { local_irq_enable(); } else { + + trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); + rcu_idle_enter(); arch_cpu_idle(); + rcu_idle_exit(); start_critical_timings(); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } } @@ -158,7 +164,6 @@ static void cpuidle_idle_call(void) if (cpuidle_not_available(drv, dev)) { tick_nohz_idle_stop_tick(); - rcu_idle_enter(); default_idle_call(); goto exit_idle; @@ -178,21 +183,17 @@ static void cpuidle_idle_call(void) u64 max_latency_ns; if (idle_should_enter_s2idle()) { - rcu_idle_enter(); entered_state = call_cpuidle_s2idle(drv, dev); if (entered_state > 0) goto exit_idle; - rcu_idle_exit(); - max_latency_ns = U64_MAX; } else { max_latency_ns = dev->forced_idle_latency_limit_ns; } tick_nohz_idle_stop_tick(); - rcu_idle_enter(); next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); @@ -209,8 +210,6 @@ static void cpuidle_idle_call(void) else tick_nohz_idle_retain_tick(); - rcu_idle_enter(); - entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome @@ -226,8 +225,6 @@ exit_idle: */ if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); - - rcu_idle_exit(); } /* diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 007b0a6b0152..1bd7e3af904f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1219,13 +1219,13 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what, case sa_rootdomain: if (!atomic_read(&d->rd->refcount)) free_rootdomain(&d->rd->rcu); - /* Fall through */ + fallthrough; case sa_sd: free_percpu(d->sd); - /* Fall through */ + fallthrough; case sa_sd_storage: __sdt_free(cpu_map); - /* Fall through */ + fallthrough; case sa_none: break; } diff --git a/kernel/signal.c b/kernel/signal.c index 6f16f7c5d375..a38b3edc6851 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -851,7 +851,7 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info, */ if (!sid || sid == task_session(current)) break; - /* fall through */ + fallthrough; default: return -EPERM; } @@ -2541,7 +2541,21 @@ bool get_signal(struct ksignal *ksig) relock: spin_lock_irq(&sighand->siglock); - current->jobctl &= ~JOBCTL_TASK_WORK; + /* + * Make sure we can safely read ->jobctl() in task_work add. As Oleg + * states: + * + * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we + * roughly have + * + * task_work_add: get_signal: + * STORE(task->task_works, new_work); STORE(task->jobctl); + * mb(); mb(); + * LOAD(task->jobctl); LOAD(task->task_works); + * + * and we can rely on STORE-MB-LOAD [ in task_work_add]. + */ + smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK); if (unlikely(current->task_works)) { spin_unlock_irq(&sighand->siglock); task_work_run(); diff --git a/kernel/sys.c b/kernel/sys.c index ca11af9d815d..ab6c409b1159 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1753,7 +1753,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) if (who == RUSAGE_CHILDREN) break; - /* fall through */ + fallthrough; case RUSAGE_SELF: thread_group_cputime_adjusted(p, &tgutime, &tgstime); diff --git a/kernel/task_work.c b/kernel/task_work.c index 5c0848ca1287..613b2d634af8 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -42,7 +42,13 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify) set_notify_resume(task); break; case TWA_SIGNAL: - if (lock_task_sighand(task, &flags)) { + /* + * Only grab the sighand lock if we don't already have some + * task_work pending. This pairs with the smp_store_mb() + * in get_signal(), see comment there. + */ + if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && + lock_task_sighand(task, &flags)) { task->jobctl |= JOBCTL_TASK_WORK; signal_wake_up(task, 0); unlock_task_sighand(task, &flags); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index c4038511d5c9..95b6a708b040 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -377,7 +377,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); - /* fall through */ + fallthrough; default: return false; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 07709ac30439..bf540f5a4115 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -439,12 +439,12 @@ static struct pid *good_sigevent(sigevent_t * event) rtn = pid_task(pid, PIDTYPE_PID); if (!rtn || !same_thread_group(rtn, current)) return NULL; - /* FALLTHRU */ + fallthrough; case SIGEV_SIGNAL: case SIGEV_THREAD: if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) return NULL; - /* FALLTHRU */ + fallthrough; case SIGEV_NONE: return pid; default: diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index e51778c312f1..36d7464c8962 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -381,7 +381,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) switch (mode) { case TICK_BROADCAST_FORCE: tick_broadcast_forced = 1; - /* fall through */ + fallthrough; case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index a16764b0116e..a50364df1054 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -666,7 +666,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) case ODEBUG_STATE_ACTIVE: WARN_ON(1); - /* fall through */ + fallthrough; default: return false; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7ba62d68885a..4b3a42fc3b24 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -745,7 +745,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) #endif case BLKTRACESTART: start = 1; - /* fall through */ + fallthrough; case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index bf44f6bbd0c3..78a678eeb140 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -499,7 +499,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, ptr++; break; } - /* fall through */ + fallthrough; default: parse_error(pe, FILT_ERR_TOO_MANY_PREDS, next - str); @@ -1273,7 +1273,7 @@ static int parse_pred(const char *str, void *data, switch (op) { case OP_NE: pred->not = 1; - /* Fall through */ + fallthrough; case OP_GLOB: case OP_EQ: break; diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index f74020f6bd9d..0ef8f65bd2d7 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu) struct watch *watch = container_of(rcu, struct watch, rcu); put_watch_queue(rcu_access_pointer(watch->queue)); + atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); } @@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) watch->cred = get_current_cred(); rcu_assign_pointer(watch->watch_list, wlist); + if (atomic_inc_return(&watch->cred->user->nr_watches) > + task_rlimit(current, RLIMIT_NOFILE)) { + atomic_dec(&watch->cred->user->nr_watches); + put_cred(watch->cred); + return -EAGAIN; + } + spin_lock_bh(&wqueue->lock); kref_get(&wqueue->usage); kref_get(&watch->usage); |