diff options
Diffstat (limited to 'kernel')
73 files changed, 2307 insertions, 1436 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 186c49582f45..56f4ee97f328 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -67,6 +67,7 @@ obj-y += up.o endif obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULE_DECOMPRESS) += module_decompress.o obj-$(CONFIG_MODULE_SIG) += module_signing.o obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 33bb8ae4a804..e16dafeb2450 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5686,7 +5686,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - if (check_ctx_reg(env, reg, regno)) + if (check_ptr_off_reg(env, reg, regno)) return -EINVAL; } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { const struct btf_type *reg_ref_t; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 80da1db47c68..5a8d9f7467bf 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -648,12 +648,22 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); - if (opt < 0) + if (opt < 0) { /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ - return opt == -ENOPARAM ? 0 : opt; + if (opt == -ENOPARAM) { + opt = vfs_parse_fs_param_source(fc, param); + if (opt != -ENOPARAM) + return opt; + + return 0; + } + + if (opt < 0) + return opt; + } switch (opt) { case OPT_MODE: diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 49e567209c6b..22c8ae94e4c1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -472,13 +472,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; - long res; + long res = -EINVAL; if (!try_get_task_stack(task)) return -EFAULT; regs = task_pt_regs(task); - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (regs) + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task); return res; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bfb45381fb3f..a39eedecc93a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,6 +570,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env, if (type & MEM_RDONLY) strncpy(prefix, "rdonly_", 16); + if (type & MEM_ALLOC) + strncpy(prefix, "alloc_", 16); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); @@ -616,7 +618,7 @@ static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) { - env->scratched_stack_slots |= 1UL << spi; + env->scratched_stack_slots |= 1ULL << spi; } static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) @@ -637,14 +639,14 @@ static bool verifier_state_scratched(const struct bpf_verifier_env *env) static void mark_verifier_state_clean(struct bpf_verifier_env *env) { env->scratched_regs = 0U; - env->scratched_stack_slots = 0UL; + env->scratched_stack_slots = 0ULL; } /* Used for printing the entire verifier state. */ static void mark_verifier_state_scratched(struct bpf_verifier_env *env) { env->scratched_regs = ~0U; - env->scratched_stack_slots = ~0UL; + env->scratched_stack_slots = ~0ULL; } /* The reg state of a pointer or a bounded scalar was saved when @@ -3969,16 +3971,17 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +static int __check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + bool fixed_off_ok) { - /* Access to ctx or passing it to a helper is only allowed in - * its original, unmodified form. + /* Access to this pointer-typed register or passing it to a helper + * is only allowed in its original, unmodified form. */ - if (reg->off) { - verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", - regno, reg->off); + if (!fixed_off_ok && reg->off) { + verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } @@ -3986,13 +3989,20 @@ int check_ctx_reg(struct bpf_verifier_env *env, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); + verbose(env, "variable %s access var_off=%s disallowed\n", + reg_type_str(env, reg->type), tn_buf); return -EACCES; } return 0; } +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) +{ + return __check_ptr_off_reg(env, reg, regno, false); +} + static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, @@ -4437,7 +4447,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - err = check_ctx_reg(env, reg, regno); + err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; @@ -5127,6 +5137,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, + PTR_TO_MEM | MEM_ALLOC, PTR_TO_BUF, }, }; @@ -5144,7 +5155,7 @@ static const struct bpf_reg_types int_ptr_types = { static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; -static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } }; +static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5244,12 +5255,6 @@ found: kernel_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } - - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { - verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", - regno); - return -EACCES; - } } return 0; @@ -5304,10 +5309,33 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, if (err) return err; - if (type == PTR_TO_CTX) { - err = check_ctx_reg(env, reg, regno); + switch ((u32)type) { + case SCALAR_VALUE: + /* Pointer types where reg offset is explicitly allowed: */ + case PTR_TO_PACKET: + case PTR_TO_PACKET_META: + case PTR_TO_MAP_KEY: + case PTR_TO_MAP_VALUE: + case PTR_TO_MEM: + case PTR_TO_MEM | MEM_RDONLY: + case PTR_TO_MEM | MEM_ALLOC: + case PTR_TO_BUF: + case PTR_TO_BUF | MEM_RDONLY: + case PTR_TO_STACK: + /* Some of the argument types nevertheless require a + * zero register offset. + */ + if (arg_type == ARG_PTR_TO_ALLOC_MEM) + goto force_off_check; + break; + /* All the rest must be rejected: */ + default: +force_off_check: + err = __check_ptr_off_reg(env, reg, regno, + type == PTR_TO_BTF_ID); if (err < 0) return err; + break; } skip_type_check: @@ -9507,9 +9535,13 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } - if (insn->src_reg == BPF_PSEUDO_BTF_ID) { - mark_reg_known_zero(env, regs, insn->dst_reg); + /* All special src_reg cases are listed below. From this point onwards + * we either succeed and assign a corresponding dst_reg->type after + * zeroing the offset, or fail and reject the program. + */ + mark_reg_known_zero(env, regs, insn->dst_reg); + if (insn->src_reg == BPF_PSEUDO_BTF_ID) { dst_reg->type = aux->btf_var.reg_type; switch (base_type(dst_reg->type)) { case PTR_TO_MEM: @@ -9547,7 +9579,6 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) } map = env->used_maps[aux->map_index]; - mark_reg_known_zero(env, regs, insn->dst_reg); dst_reg->map_ptr = map; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || @@ -9651,7 +9682,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b31e1465868a..9d05c3ca2d5e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { @@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&ctx->psi.trigger, new); - + smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; @@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; - psi_trigger_replace(&ctx->psi.trigger, NULL); + psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config new file mode 100644 index 000000000000..e9ffb0cc1eec --- /dev/null +++ b/kernel/configs/debug.config @@ -0,0 +1,105 @@ +# The config is based on running daily CI for enterprise Linux distros to +# seek regressions on linux-next builds on different bare-metal and virtual +# platforms. It can be used for example, +# +# $ make ARCH=arm64 defconfig debug.config +# +# Keep alphabetically sorted inside each section. +# +# printk and dmesg options +# +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DYNAMIC_DEBUG=y +CONFIG_PRINTK_CALLER=y +CONFIG_PRINTK_TIME=y +CONFIG_SYMBOLIC_ERRNAME=y +# +# Compile-time checks and compiler options +# +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_FRAME_WARN=2048 +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +# +# Generic Kernel Debugging Instruments +# +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_UBSAN_DIV_ZERO is not set +# CONFIG_UBSAN_TRAP is not set +# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_FS_ALLOW_ALL=y +CONFIG_DEBUG_IRQFLAGS=y +CONFIG_UBSAN=y +CONFIG_UBSAN_BOOL=y +CONFIG_UBSAN_BOUNDS=y +CONFIG_UBSAN_ENUM=y +CONFIG_UBSAN_SHIFT=y +CONFIG_UBSAN_UNREACHABLE=y +# +# Memory Debugging +# +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF is not set +# CONFIG_DEBUG_RODATA_TEST is not set +# CONFIG_DEBUG_WX is not set +# CONFIG_KFENCE is not set +# CONFIG_PAGE_POISONING is not set +# CONFIG_SLUB_STATS is not set +CONFIG_PAGE_EXTENSION=y +CONFIG_PAGE_OWNER=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_VIRTUAL=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_PGFLAGS=y +CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_VM_VMACACHE=y +CONFIG_GENERIC_PTDUMP=y +CONFIG_KASAN=y +CONFIG_KASAN_GENERIC=y +CONFIG_KASAN_INLINE=y +CONFIG_KASAN_VMALLOC=y +CONFIG_PTDUMP_DEBUGFS=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_SLUB_DEBUG_ON=y +# +# Debug Oops, Lockups and Hangs +# +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PANIC_TIMEOUT=0 +CONFIG_SOFTLOCKUP_DETECTOR=y +# +# Lock Debugging (spinlocks, mutexes, etc...) +# +# CONFIG_PROVE_RAW_LOCK_NESTING is not set +CONFIG_PROVE_LOCKING=y +# +# Debug kernel data structures +# +CONFIG_BUG_ON_DATA_CORRUPTION=y +# +# RCU Debugging +# +CONFIG_PROVE_RCU=y +CONFIG_PROVE_RCU_LIST=y +# +# Tracers +# +CONFIG_BRANCH_PROFILE_NONE=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FTRACE=y +CONFIG_FUNCTION_TRACER=y diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 51530d5b15a8..c5e8cea9e05f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -100,19 +100,10 @@ void __delayacct_blkio_start(void) */ void __delayacct_blkio_end(struct task_struct *p) { - struct task_delay_info *delays = p->delays; - u64 *total; - u32 *count; - - if (p->delays->flags & DELAYACCT_PF_SWAPIN) { - total = &delays->swapin_delay; - count = &delays->swapin_count; - } else { - total = &delays->blkio_delay; - count = &delays->blkio_count; - } - - delayacct_end(&delays->lock, &delays->blkio_start, total, count); + delayacct_end(&p->delays->lock, + &p->delays->blkio_start, + &p->delays->blkio_delay, + &p->delays->blkio_count); } int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -164,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; + tmp = d->compact_delay_total + tsk->delays->compact_delay; + d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; + d->compact_count += tsk->delays->compact_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -179,8 +173,7 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) unsigned long flags; raw_spin_lock_irqsave(&tsk->delays->lock, flags); - ret = nsec_to_clock_t(tsk->delays->blkio_delay + - tsk->delays->swapin_delay); + ret = nsec_to_clock_t(tsk->delays->blkio_delay); raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } @@ -210,3 +203,29 @@ void __delayacct_thrashing_end(void) ¤t->delays->thrashing_delay, ¤t->delays->thrashing_count); } + +void __delayacct_swapin_start(void) +{ + current->delays->swapin_start = local_clock(); +} + +void __delayacct_swapin_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->swapin_start, + ¤t->delays->swapin_delay, + ¤t->delays->swapin_count); +} + +void __delayacct_compact_start(void) +{ + current->delays->compact_start = local_clock(); +} + +void __delayacct_compact_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->compact_start, + ¤t->delays->compact_delay, + ¤t->delays->compact_count); +} diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 5f84e6cdb78e..4d40dcce7604 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -203,7 +203,7 @@ static int __init dma_atomic_pool_init(void) GFP_KERNEL); if (!atomic_pool_kernel) ret = -ENOMEM; - if (IS_ENABLED(CONFIG_ZONE_DMA)) { + if (has_managed_dma()) { atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA); if (!atomic_pool_dma) @@ -226,7 +226,7 @@ static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) 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)) + if (atomic_pool_dma && (gfp & GFP_DMA)) return atomic_pool_dma; return atomic_pool_kernel; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8e840fbbed7c..f1e7ea160b43 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -50,6 +50,7 @@ #include <asm/io.h> #include <asm/dma.h> +#include <linux/io.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/iommu-helper.h> @@ -72,6 +73,8 @@ enum swiotlb_force swiotlb_force; struct io_tlb_mem io_tlb_default_mem; +phys_addr_t swiotlb_unencrypted_base; + /* * Max segment that we can provide which (if pages are contingous) will * not be bounced (unless SWIOTLB_FORCE is set). @@ -156,6 +159,34 @@ static inline unsigned long nr_slots(u64 val) } /* + * Remap swioltb memory in the unencrypted physical address space + * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP + * Isolation VMs). + */ +#ifdef CONFIG_HAS_IOMEM +static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) +{ + void *vaddr = NULL; + + if (swiotlb_unencrypted_base) { + phys_addr_t paddr = mem->start + swiotlb_unencrypted_base; + + vaddr = memremap(paddr, bytes, MEMREMAP_WB); + if (!vaddr) + pr_err("Failed to map the unencrypted memory %pa size %lx.\n", + &paddr, bytes); + } + + return vaddr; +} +#else +static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) +{ + return NULL; +} +#endif + +/* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to * call SWIOTLB when the operations are possible. It needs to be called @@ -172,7 +203,12 @@ void __init swiotlb_update_mem_attributes(void) vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); + + mem->vaddr = swiotlb_mem_remap(mem, bytes); + if (!mem->vaddr) + mem->vaddr = vaddr; + + memset(mem->vaddr, 0, bytes); } static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, @@ -196,7 +232,17 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; } + + /* + * If swiotlb_unencrypted_base is set, the bounce buffer memory will + * be remapped and cleared in swiotlb_update_mem_attributes. + */ + if (swiotlb_unencrypted_base) + return; + memset(vaddr, 0, bytes); + mem->vaddr = vaddr; + return; } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) @@ -371,7 +417,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); - unsigned char *vaddr = phys_to_virt(tlb_addr); + unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; unsigned int tlb_offset, orig_addr_offset; if (orig_addr == INVALID_PHYS_ADDR) diff --git a/kernel/exit.c b/kernel/exit.c index f702a6a63686..b00a25bb4ab9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -116,7 +116,7 @@ static void __exit_signal(struct task_struct *tsk) * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) - wake_up_process(sig->group_exit_task); + wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); @@ -697,7 +697,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) - wake_up_process(tsk->signal->group_exit_task); + wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { @@ -735,37 +735,22 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; - /* - * We can get here from a kernel oops, sometimes with preemption off. - * Start by checking for critical errors. - * Then fix up important state like USER_DS and preemption. - * Then do everything else. - */ - WARN_ON(blk_needs_flush_plug(tsk)); - if (unlikely(in_interrupt())) - panic("Aiee, killing interrupt handler!"); - if (unlikely(!tsk->pid)) - panic("Attempted to kill the idle task!"); - /* - * If do_exit is called because this processes oopsed, it's possible + * If do_dead is called because this processes oopsed, it's possible * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before * continuing. Amongst other possible reasons, this is to prevent * mm_release()->clear_child_tid() from writing to a user-controlled * kernel address. + * + * On uptodate architectures force_uaccess_begin is a noop. On + * architectures that still have set_fs/get_fs in addition to handling + * oopses handles kernel threads that run as set_fs(KERNEL_DS) by + * default. */ force_uaccess_begin(); - if (unlikely(in_atomic())) { - pr_info("note: %s[%d] exited with preempt_count %d\n", - current->comm, task_pid_nr(current), - preempt_count()); - preempt_count_set(PREEMPT_ENABLED); - } - - profile_task_exit(tsk); kcov_task_exit(tsk); coredump_task_exit(tsk); @@ -773,17 +758,6 @@ void __noreturn do_exit(long code) validate_creds_for_do_exit(tsk); - /* - * We're taking recursive faults here in do_exit. Safest is to just - * leave this task alone and wait for reboot. - */ - if (unlikely(tsk->flags & PF_EXITING)) { - pr_alert("Fixing recursive fault but reboot is needed!\n"); - futex_exit_recursive(tsk); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule(); - } - io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ @@ -882,16 +856,46 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } -EXPORT_SYMBOL_GPL(do_exit); -void complete_and_exit(struct completion *comp, long code) +void __noreturn make_task_dead(int signr) { - if (comp) - complete(comp); + /* + * Take the task off the cpu after something catastrophic has + * happened. + * + * We can get here from a kernel oops, sometimes with preemption off. + * Start by checking for critical errors. + * Then fix up important state like USER_DS and preemption. + * Then do everything else. + */ + struct task_struct *tsk = current; - do_exit(code); + if (unlikely(in_interrupt())) + panic("Aiee, killing interrupt handler!"); + if (unlikely(!tsk->pid)) + panic("Attempted to kill the idle task!"); + + if (unlikely(in_atomic())) { + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } + + /* + * We're taking recursive faults here in make_task_dead. Safest is to just + * leave this task alone and wait for reboot. + */ + if (unlikely(tsk->flags & PF_EXITING)) { + pr_alert("Fixing recursive fault but reboot is needed!\n"); + futex_exit_recursive(tsk); + tsk->exit_state = EXIT_DEAD; + refcount_inc(&tsk->rcu_users); + do_task_dead(); + } + + do_exit(signr); } -EXPORT_SYMBOL(complete_and_exit); SYSCALL_DEFINE1(exit, int, error_code) { @@ -907,17 +911,19 @@ do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; - BUG_ON(exit_code & 0x80); /* core dumps don't get here */ - - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else if (!thread_group_empty(current)) { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; @@ -1012,7 +1018,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { - status = p->exit_code; + status = (p->signal->flags & SIGNAL_GROUP_EXIT) + ? p->signal->group_exit_code : p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); diff --git a/kernel/fork.c b/kernel/fork.c index 3161d7980155..d75a528f7b21 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> @@ -365,12 +366,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; + dup_vma_anon_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { + free_vma_anon_name(vma); kmem_cache_free(vm_area_cachep, vma); } @@ -754,9 +757,7 @@ void __put_task_struct(struct task_struct *tsk) delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); - - if (!profile_handoff_task(tsk)) - free_task(tsk); + free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); @@ -950,7 +951,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - tsk->pf_io_worker = NULL; + tsk->worker_private = NULL; account_kernel_stack(tsk, 1); @@ -2006,12 +2007,6 @@ static __latent_entropy struct task_struct *copy_process( siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } - /* - * This _must_ happen before we call free_task(), i.e. before we jump - * to any of the bad_fork_* labels. This is to avoid freeing - * p->set_child_tid which is (ab)used as a kthread's data pointer for - * kernel threads (PF_KTHREAD). - */ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? @@ -2092,12 +2087,16 @@ static __latent_entropy struct task_struct *copy_process( p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); + if (p->flags & PF_KTHREAD) { + if (!set_kthread_struct(p)) + goto bad_fork_cleanup_delayacct; + } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; - goto bad_fork_cleanup_threadgroup_lock; + goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS @@ -2434,8 +2433,8 @@ bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); -bad_fork_cleanup_threadgroup_lock: #endif +bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 926c2bb752bc..51dd822a8060 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1031,7 +1031,7 @@ static void futex_cleanup(struct task_struct *tsk) * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * - * This is called from the recursive fault handling path in do_exit(). + * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 053447183ac5..04f4ebdc3cf5 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,7 +4,6 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS - depends on !CC_IS_CLANG || CLANG_VERSION >= 110000 depends on !ARCH_WANTS_NO_INSTR || CC_HAS_NO_PROFILE_FN_ATTR select CONSTRUCTORS default n diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 9888e2bc8c76..52501e5f7655 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -63,7 +63,9 @@ static struct task_struct *watchdog_task; * Should we dump all CPUs backtraces in a hung task event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ /* @@ -222,11 +224,13 @@ static long hung_timeout_jiffies(unsigned long last_checked, MAX_SCHEDULE_TIMEOUT; } +#ifdef CONFIG_SYSCTL /* * Process updating of timeout sysctl */ -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) { int ret; @@ -241,6 +245,76 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, return ret; } +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ +static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); +static struct ctl_table hung_task_sysctls[] = { +#ifdef CONFIG_SMP + { + .procname = "hung_task_all_cpu_backtrace", + .data = &sysctl_hung_task_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ + { + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "hung_task_check_count", + .data = &sysctl_hung_task_check_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "hung_task_timeout_secs", + .data = &sysctl_hung_task_timeout_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_NEG_ONE, + }, + {} +}; + +static void __init hung_task_sysctl_init(void) +{ + register_sysctl_init("kernel", hung_task_sysctls); +} +#else +#define hung_task_sysctl_init() do { } while (0) +#endif /* CONFIG_SYSCTL */ + + static atomic_t reset_hung_task = ATOMIC_INIT(0); void reset_hung_task_detector(void) @@ -310,6 +384,7 @@ static int __init hung_task_init(void) pm_notifier(hungtask_pm_notify, 0); watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + hung_task_sysctl_init(); return 0; } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index ee595ec09778..623b8136e9af 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -137,7 +137,7 @@ static inline int irq_select_affinity_usr(unsigned int irq) static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); + unsigned int irq = (int)(long)pde_data(file_inode(file)); cpumask_var_t new_value; int err; @@ -190,12 +190,12 @@ static ssize_t irq_affinity_list_proc_write(struct file *file, static int irq_affinity_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_proc_show, pde_data(inode)); } static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_list_proc_show, pde_data(inode)); } static const struct proc_ops irq_affinity_proc_ops = { @@ -265,7 +265,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, PDE_DATA(inode)); + return single_open(file, default_affinity_show, pde_data(inode)); } static const struct proc_ops default_affinity_proc_ops = { diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3011bc33a5ba..951c93216fc4 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -243,6 +243,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, ret = fn(data, namebuf, NULL, kallsyms_sym_address(i)); if (ret != 0) return ret; + cond_resched(); } return 0; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 5a5d192a89ac..68480f731192 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -81,7 +81,7 @@ int kexec_should_crash(struct task_struct *p) if (crash_kexec_post_notifiers) return 0; /* - * There are 4 panic() calls in do_exit() path, each of which + * There are 4 panic() calls in make_task_dead() path, each of which * corresponds to each of these 4 conditions. */ if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 21eccc961bba..94cab8c9ce56 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -48,6 +48,9 @@ #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) +#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL) +#define kprobe_sysctls_init() do { } while (0) +#endif static int kprobes_initialized; /* kprobe_table can be accessed by @@ -938,10 +941,10 @@ static void unoptimize_all_kprobes(void) } static DEFINE_MUTEX(kprobe_sysctl_mutex); -int sysctl_kprobes_optimization; -int proc_kprobes_optimization_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, - loff_t *ppos) +static int sysctl_kprobes_optimization; +static int proc_kprobes_optimization_handler(struct ctl_table *table, + int write, void *buffer, + size_t *length, loff_t *ppos) { int ret; @@ -957,6 +960,24 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table kprobe_sysctls[] = { + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static void __init kprobe_sysctls_init(void) +{ + register_sysctl_init("debug", kprobe_sysctls); +} #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. */ @@ -2584,6 +2605,7 @@ static int __init init_kprobes(void) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); + kprobe_sysctls_init(); return err; } early_initcall(init_kprobes); diff --git a/kernel/kthread.c b/kernel/kthread.c index 7113003fab63..38c6dd822da8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -52,6 +52,7 @@ struct kthread_create_info struct kthread { unsigned long flags; unsigned int cpu; + int result; int (*threadfn)(void *); void *data; mm_segment_t oldfs; @@ -60,6 +61,8 @@ struct kthread { #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif + /* To store the full name if task comm is truncated. */ + char *full_name; }; enum KTHREAD_BITS { @@ -71,7 +74,7 @@ enum KTHREAD_BITS { static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); - return (__force void *)k->set_child_tid; + return k->worker_private; } /* @@ -79,7 +82,7 @@ static inline struct kthread *to_kthread(struct task_struct *k) * * Per construction; when: * - * (p->flags & PF_KTHREAD) && p->set_child_tid + * (p->flags & PF_KTHREAD) && p->worker_private * * the task is both a kthread and struct kthread is persistent. However * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and @@ -87,26 +90,41 @@ static inline struct kthread *to_kthread(struct task_struct *k) */ static inline struct kthread *__to_kthread(struct task_struct *p) { - void *kthread = (__force void *)p->set_child_tid; + void *kthread = p->worker_private; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; } -void set_kthread_struct(struct task_struct *p) +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - struct kthread *kthread; + struct kthread *kthread = to_kthread(tsk); - if (__to_kthread(p)) + if (!kthread || !kthread->full_name) { + __get_task_comm(buf, buf_size, tsk); return; + } + + strscpy_pad(buf, kthread->full_name, buf_size); +} + +bool set_kthread_struct(struct task_struct *p) +{ + struct kthread *kthread; + + if (WARN_ON_ONCE(to_kthread(p))) + return false; kthread = kzalloc(sizeof(*kthread), GFP_KERNEL); - /* - * We abuse ->set_child_tid to avoid the new member and because it - * can't be wrongly copied by copy_process(). We also rely on fact - * that the caller can't exec, so PF_KTHREAD can't be cleared. - */ - p->set_child_tid = (__force void __user *)kthread; + if (!kthread) + return false; + + init_completion(&kthread->exited); + init_completion(&kthread->parked); + p->vfork_done = &kthread->exited; + + p->worker_private = kthread; + return true; } void free_kthread_struct(struct task_struct *k) @@ -114,13 +132,17 @@ void free_kthread_struct(struct task_struct *k) struct kthread *kthread; /* - * Can be NULL if this kthread was created by kernel_thread() - * or if kmalloc() in kthread() failed. + * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); + if (!kthread) + return; + #ifdef CONFIG_BLK_CGROUP - WARN_ON_ONCE(kthread && kthread->blkcg_css); + WARN_ON_ONCE(kthread->blkcg_css); #endif + k->worker_private = NULL; + kfree(kthread->full_name); kfree(kthread); } @@ -268,6 +290,44 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +/** + * kthread_exit - Cause the current kthread return @result to kthread_stop(). + * @result: The integer value to return to kthread_stop(). + * + * While kthread_exit can be called directly, it exists so that + * functions which do some additional work in non-modular code such as + * module_put_and_kthread_exit can be implemented. + * + * Does not return. + */ +void __noreturn kthread_exit(long result) +{ + struct kthread *kthread = to_kthread(current); + kthread->result = result; + do_exit(0); +} + +/** + * kthread_complete_and_exit - Exit the current kthread. + * @comp: Completion to complete + * @code: The integer value to return to kthread_stop(). + * + * If present complete @comp and the reuturn code to kthread_stop(). + * + * A kernel thread whose module may be removed after the completion of + * @comp can use this function exit safely. + * + * Does not return. + */ +void __noreturn kthread_complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + kthread_exit(code); +} +EXPORT_SYMBOL(kthread_complete_and_exit); + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; @@ -279,27 +339,17 @@ static int kthread(void *_create) struct kthread *self; int ret; - set_kthread_struct(current); self = to_kthread(current); /* If user was SIGKILLed, I release the structure. */ done = xchg(&create->done, NULL); if (!done) { kfree(create); - do_exit(-EINTR); - } - - if (!self) { - create->result = ERR_PTR(-ENOMEM); - complete(done); - do_exit(-ENOMEM); + kthread_exit(-EINTR); } self->threadfn = threadfn; self->data = data; - init_completion(&self->exited); - init_completion(&self->parked); - current->vfork_done = &self->exited; /* * The new thread inherited kthreadd's priority and CPU mask. Reset @@ -326,7 +376,7 @@ static int kthread(void *_create) __kthread_parkme(self); ret = threadfn(data); } - do_exit(ret); + kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ @@ -406,12 +456,22 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { char name[TASK_COMM_LEN]; + va_list aq; + int len; /* * task is already visible to other tasks, so updating * COMM must be protected. */ - vsnprintf(name, sizeof(name), namefmt, args); + va_copy(aq, args); + len = vsnprintf(name, sizeof(name), namefmt, aq); + va_end(aq); + if (len >= TASK_COMM_LEN) { + struct kthread *kthread = to_kthread(task); + + /* leave it truncated when out of memory. */ + kthread->full_name = kvasprintf(GFP_KERNEL, namefmt, args); + } set_task_comm(task, name); } kfree(create); @@ -523,6 +583,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), to_kthread(p)->cpu = cpu; return p; } +EXPORT_SYMBOL(kthread_create_on_cpu); void kthread_set_per_cpu(struct task_struct *k, int cpu) { @@ -627,7 +688,7 @@ EXPORT_SYMBOL_GPL(kthread_park); * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * - * If threadfn() may call do_exit() itself, the caller must ensure + * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() @@ -646,7 +707,7 @@ int kthread_stop(struct task_struct *k) kthread_unpark(k); wake_up_process(k); wait_for_completion(&kthread->exited); - ret = k->exit_code; + ret = kthread->result; put_task_struct(k); trace_sched_kthread_stop_ret(ret); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 335d988bd811..585494ec464f 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -862,14 +862,11 @@ static void klp_init_object_early(struct klp_patch *patch, list_add_tail(&obj->node, &patch->obj_list); } -static int klp_init_patch_early(struct klp_patch *patch) +static void klp_init_patch_early(struct klp_patch *patch) { struct klp_object *obj; struct klp_func *func; - if (!patch->objs) - return -EINVAL; - INIT_LIST_HEAD(&patch->list); INIT_LIST_HEAD(&patch->obj_list); kobject_init(&patch->kobj, &klp_ktype_patch); @@ -879,20 +876,12 @@ static int klp_init_patch_early(struct klp_patch *patch) init_completion(&patch->finish); klp_for_each_object_static(patch, obj) { - if (!obj->funcs) - return -EINVAL; - klp_init_object_early(patch, obj); klp_for_each_func_static(obj, func) { klp_init_func_early(obj, func); } } - - if (!try_module_get(patch->mod)) - return -ENODEV; - - return 0; } static int klp_init_patch(struct klp_patch *patch) @@ -1024,10 +1013,17 @@ err: int klp_enable_patch(struct klp_patch *patch) { int ret; + struct klp_object *obj; - if (!patch || !patch->mod) + if (!patch || !patch->mod || !patch->objs) return -EINVAL; + klp_for_each_object_static(patch, obj) { + if (!obj->funcs) + return -EINVAL; + } + + if (!is_livepatch_module(patch->mod)) { pr_err("module %s is not marked as a livepatch module\n", patch->mod->name); @@ -1051,12 +1047,13 @@ int klp_enable_patch(struct klp_patch *patch) return -EINVAL; } - ret = klp_init_patch_early(patch); - if (ret) { + if (!try_module_get(patch->mod)) { mutex_unlock(&klp_mutex); - return ret; + return -ENODEV; } + klp_init_patch_early(patch); + ret = klp_init_patch(patch); if (ret) goto err; diff --git a/kernel/livepatch/shadow.c b/kernel/livepatch/shadow.c index e5c9fb295ba9..c2e724d97ddf 100644 --- a/kernel/livepatch/shadow.c +++ b/kernel/livepatch/shadow.c @@ -272,12 +272,12 @@ void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor) EXPORT_SYMBOL_GPL(klp_shadow_free); /** - * klp_shadow_free_all() - detach and free all <*, id> shadow variables + * klp_shadow_free_all() - detach and free all <_, id> shadow variables * @id: data identifier * @dtor: custom callback that can be used to unregister the variable * and/or free data that the shadow variable points to (optional) * - * This function releases the memory for all <*, id> shadow variable + * This function releases the memory for all <_, id> shadow variable * instances, callers should stop referencing them accordingly. */ void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) @@ -288,7 +288,7 @@ void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) spin_lock_irqsave(&klp_shadow_lock, flags); - /* Delete all <*, id> from hash */ + /* Delete all <_, id> from hash */ hash_for_each(klp_shadow_hash, i, shadow, node) { if (klp_shadow_match(shadow, shadow->obj, id)) klp_shadow_free_struct(shadow, dtor); diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index b562f9289372..7f49baaa4979 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -300,6 +300,16 @@ void __lockfunc _raw_write_lock(rwlock_t *lock) __raw_write_lock(lock); } EXPORT_SYMBOL(_raw_write_lock); + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +#define __raw_write_lock_nested(lock, subclass) __raw_write_lock(((void)(subclass), (lock))) +#endif + +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + __raw_write_lock_nested(lock, subclass); +} +EXPORT_SYMBOL(_raw_write_lock_nested); #endif #ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index 9e396a09fe0f..48a19ed8486d 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -239,6 +239,18 @@ void __sched rt_write_lock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_write_lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rtlock_might_resched(); + rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_); + rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock_nested); +#endif + void __sched rt_read_unlock(rwlock_t *rwlock) { rwlock_release(&rwlock->dep_map, _RET_IP_); diff --git a/kernel/module-internal.h b/kernel/module-internal.h index 33783abc377b..8c381c99062f 100644 --- a/kernel/module-internal.h +++ b/kernel/module-internal.h @@ -23,9 +23,28 @@ struct load_info { #ifdef CONFIG_KALLSYMS unsigned long mod_kallsyms_init_off; #endif +#ifdef CONFIG_MODULE_DECOMPRESS + struct page **pages; + unsigned int max_pages; + unsigned int used_pages; +#endif struct { unsigned int sym, str, mod, vers, info, pcpu; } index; }; extern int mod_verify_sig(const void *mod, struct load_info *info); + +#ifdef CONFIG_MODULE_DECOMPRESS +int module_decompress(struct load_info *info, const void *buf, size_t size); +void module_decompress_cleanup(struct load_info *info); +#else +static inline int module_decompress(struct load_info *info, + const void *buf, size_t size) +{ + return -EOPNOTSUPP; +} +static inline void module_decompress_cleanup(struct load_info *info) +{ +} +#endif diff --git a/kernel/module.c b/kernel/module.c index 84a9141a5e15..24dab046e16c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -337,12 +337,12 @@ static inline void add_taint_module(struct module *mod, unsigned flag, * A thread that wants to hold a reference to a module only while it * is running can call this to safely exit. nfsd and lockd use this. */ -void __noreturn __module_put_and_exit(struct module *mod, long code) +void __noreturn __module_put_and_kthread_exit(struct module *mod, long code) { module_put(mod); - do_exit(code); + kthread_exit(code); } -EXPORT_SYMBOL(__module_put_and_exit); +EXPORT_SYMBOL(__module_put_and_kthread_exit); /* Find a module section: 0 means not found. */ static unsigned int find_sec(const struct load_info *info, const char *name) @@ -958,7 +958,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, } } - /* Stop the machine so refcounts can't move and disable module. */ ret = try_stop_module(mod, flags, &forced); if (ret != 0) goto out; @@ -2884,12 +2883,13 @@ static int module_sig_check(struct load_info *info, int flags) const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; const char *reason; const void *mod = info->hdr; - + bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS | + MODULE_INIT_IGNORE_VERMAGIC); /* - * Require flags == 0, as a module with version information - * removed is no longer the module that was signed + * Do not allow mangled modules as a module with version information + * removed is no longer the module that was signed. */ - if (flags == 0 && + if (!mangled_module && info->len > markerlen && memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { /* We truncate the module to discard the signature */ @@ -3174,9 +3174,12 @@ out: return err; } -static void free_copy(struct load_info *info) +static void free_copy(struct load_info *info, int flags) { - vfree(info->hdr); + if (flags & MODULE_INIT_COMPRESSED_FILE) + module_decompress_cleanup(info); + else + vfree(info->hdr); } static int rewrite_section_headers(struct load_info *info, int flags) @@ -4125,7 +4128,7 @@ static int load_module(struct load_info *info, const char __user *uargs, } /* Get rid of temporary copy. */ - free_copy(info); + free_copy(info, flags); /* Done! */ trace_module_load(mod); @@ -4174,7 +4177,7 @@ static int load_module(struct load_info *info, const char __user *uargs, module_deallocate(mod, info); free_copy: - free_copy(info); + free_copy(info, flags); return err; } @@ -4201,7 +4204,8 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; - void *hdr = NULL; + void *buf = NULL; + int len; int err; err = may_init_module(); @@ -4211,15 +4215,24 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC)) + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) return -EINVAL; - err = kernel_read_file_from_fd(fd, 0, &hdr, INT_MAX, NULL, + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); - if (err < 0) - return err; - info.hdr = hdr; - info.len = err; + if (len < 0) + return len; + + if (flags & MODULE_INIT_COMPRESSED_FILE) { + err = module_decompress(&info, buf, len); + vfree(buf); /* compressed data is no longer needed */ + if (err) + return err; + } else { + info.hdr = buf; + info.len = len; + } return load_module(&info, uargs, flags); } @@ -4499,6 +4512,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, mod, kallsyms_symbol_value(sym)); if (ret != 0) goto out; + + cond_resched(); } } out: diff --git a/kernel/module_decompress.c b/kernel/module_decompress.c new file mode 100644 index 000000000000..b01c69c2ff99 --- /dev/null +++ b/kernel/module_decompress.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2021 Google LLC. + */ + +#include <linux/init.h> +#include <linux/highmem.h> +#include <linux/kobject.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/sysfs.h> +#include <linux/vmalloc.h> + +#include "module-internal.h" + +static int module_extend_max_pages(struct load_info *info, unsigned int extent) +{ + struct page **new_pages; + + new_pages = kvmalloc_array(info->max_pages + extent, + sizeof(info->pages), GFP_KERNEL); + if (!new_pages) + return -ENOMEM; + + memcpy(new_pages, info->pages, info->max_pages * sizeof(info->pages)); + kvfree(info->pages); + info->pages = new_pages; + info->max_pages += extent; + + return 0; +} + +static struct page *module_get_next_page(struct load_info *info) +{ + struct page *page; + int error; + + if (info->max_pages == info->used_pages) { + error = module_extend_max_pages(info, info->used_pages); + if (error) + return ERR_PTR(error); + } + + page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + if (!page) + return ERR_PTR(-ENOMEM); + + info->pages[info->used_pages++] = page; + return page; +} + +#ifdef CONFIG_MODULE_COMPRESS_GZIP +#include <linux/zlib.h> +#define MODULE_COMPRESSION gzip +#define MODULE_DECOMPRESS_FN module_gzip_decompress + +/* + * Calculate length of the header which consists of signature, header + * flags, time stamp and operating system ID (10 bytes total), plus + * an optional filename. + */ +static size_t module_gzip_header_len(const u8 *buf, size_t size) +{ + const u8 signature[] = { 0x1f, 0x8b, 0x08 }; + size_t len = 10; + + if (size < len || memcmp(buf, signature, sizeof(signature))) + return 0; + + if (buf[3] & 0x08) { + do { + /* + * If we can't find the end of the file name we must + * be dealing with a corrupted file. + */ + if (len == size) + return 0; + } while (buf[len++] != '\0'); + } + + return len; +} + +static ssize_t module_gzip_decompress(struct load_info *info, + const void *buf, size_t size) +{ + struct z_stream_s s = { 0 }; + size_t new_size = 0; + size_t gzip_hdr_len; + ssize_t retval; + int rc; + + gzip_hdr_len = module_gzip_header_len(buf, size); + if (!gzip_hdr_len) { + pr_err("not a gzip compressed module\n"); + return -EINVAL; + } + + s.next_in = buf + gzip_hdr_len; + s.avail_in = size - gzip_hdr_len; + + s.workspace = kmalloc(zlib_inflate_workspacesize(), GFP_KERNEL); + if (!s.workspace) + return -ENOMEM; + + rc = zlib_inflateInit2(&s, -MAX_WBITS); + if (rc != Z_OK) { + pr_err("failed to initialize decompressor: %d\n", rc); + retval = -EINVAL; + goto out; + } + + do { + struct page *page = module_get_next_page(info); + if (!page) { + retval = -ENOMEM; + goto out_inflate_end; + } + + s.next_out = kmap(page); + s.avail_out = PAGE_SIZE; + rc = zlib_inflate(&s, 0); + kunmap(page); + + new_size += PAGE_SIZE - s.avail_out; + } while (rc == Z_OK); + + if (rc != Z_STREAM_END) { + pr_err("decompression failed with status %d\n", rc); + retval = -EINVAL; + goto out_inflate_end; + } + + retval = new_size; + +out_inflate_end: + zlib_inflateEnd(&s); +out: + kfree(s.workspace); + return retval; +} +#elif CONFIG_MODULE_COMPRESS_XZ +#include <linux/xz.h> +#define MODULE_COMPRESSION xz +#define MODULE_DECOMPRESS_FN module_xz_decompress + +static ssize_t module_xz_decompress(struct load_info *info, + const void *buf, size_t size) +{ + static const u8 signature[] = { 0xfd, '7', 'z', 'X', 'Z', 0 }; + struct xz_dec *xz_dec; + struct xz_buf xz_buf; + enum xz_ret xz_ret; + size_t new_size = 0; + ssize_t retval; + + if (size < sizeof(signature) || + memcmp(buf, signature, sizeof(signature))) { + pr_err("not an xz compressed module\n"); + return -EINVAL; + } + + xz_dec = xz_dec_init(XZ_DYNALLOC, (u32)-1); + if (!xz_dec) + return -ENOMEM; + + xz_buf.in_size = size; + xz_buf.in = buf; + xz_buf.in_pos = 0; + + do { + struct page *page = module_get_next_page(info); + if (!page) { + retval = -ENOMEM; + goto out; + } + + xz_buf.out = kmap(page); + xz_buf.out_pos = 0; + xz_buf.out_size = PAGE_SIZE; + xz_ret = xz_dec_run(xz_dec, &xz_buf); + kunmap(page); + + new_size += xz_buf.out_pos; + } while (xz_buf.out_pos == PAGE_SIZE && xz_ret == XZ_OK); + + if (xz_ret != XZ_STREAM_END) { + pr_err("decompression failed with status %d\n", xz_ret); + retval = -EINVAL; + goto out; + } + + retval = new_size; + + out: + xz_dec_end(xz_dec); + return retval; +} +#else +#error "Unexpected configuration for CONFIG_MODULE_DECOMPRESS" +#endif + +int module_decompress(struct load_info *info, const void *buf, size_t size) +{ + unsigned int n_pages; + ssize_t data_size; + int error; + + /* + * Start with number of pages twice as big as needed for + * compressed data. + */ + n_pages = DIV_ROUND_UP(size, PAGE_SIZE) * 2; + error = module_extend_max_pages(info, n_pages); + + data_size = MODULE_DECOMPRESS_FN(info, buf, size); + if (data_size < 0) { + error = data_size; + goto err; + } + + info->hdr = vmap(info->pages, info->used_pages, VM_MAP, PAGE_KERNEL); + if (!info->hdr) { + error = -ENOMEM; + goto err; + } + + info->len = data_size; + return 0; + +err: + module_decompress_cleanup(info); + return error; +} + +void module_decompress_cleanup(struct load_info *info) +{ + int i; + + if (info->hdr) + vunmap(info->hdr); + + for (i = 0; i < info->used_pages; i++) + __free_page(info->pages[i]); + + kvfree(info->pages); + + info->pages = NULL; + info->max_pages = info->used_pages = 0; +} + +static ssize_t compression_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", __stringify(MODULE_COMPRESSION)); +} +static struct kobj_attribute module_compression_attr = __ATTR_RO(compression); + +static int __init module_decompress_sysfs_init(void) +{ + int error; + + error = sysfs_create_file(&module_kset->kobj, + &module_compression_attr.attr); + if (error) + pr_warn("Failed to create 'compression' attribute"); + + return 0; +} +late_initcall(module_decompress_sysfs_init); diff --git a/kernel/panic.c b/kernel/panic.c index cefd7d82366f..55b50e052ec3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -32,6 +32,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <trace/events/error_report.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 @@ -533,26 +534,9 @@ void oops_enter(void) trigger_all_cpu_backtrace(); } -/* - * 64-bit random ID for oopses: - */ -static u64 oops_id; - -static int init_oops_id(void) -{ - if (!oops_id) - get_random_bytes(&oops_id, sizeof(oops_id)); - else - oops_id++; - - return 0; -} -late_initcall(init_oops_id); - static void print_oops_end_marker(void) { - init_oops_id(); - pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id); + pr_warn("---[ end trace %016llx ]---\n", 0ULL); } /* @@ -609,6 +593,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, print_irqtrace_events(current); print_oops_end_marker(); + trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f7a986078213..330d49937692 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -978,8 +978,7 @@ static void memory_bm_recycle(struct memory_bitmap *bm) * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ -void __init __register_nosave_region(unsigned long start_pfn, - unsigned long end_pfn, int use_kmalloc) +void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; @@ -995,18 +994,12 @@ void __init __register_nosave_region(unsigned long start_pfn, goto Report; } } - if (use_kmalloc) { - /* During init, this shouldn't fail */ - region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); - BUG_ON(!region); - } else { - /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), - SMP_CACHE_BYTES); - if (!region) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct nosave_region)); - } + /* This allocation cannot fail */ + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); + if (!region) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 105df4dfc783..52571dcad768 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -39,23 +39,20 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) { struct rb_node *node; struct wakelock *wl; - char *str = buf; - char *end = buf + PAGE_SIZE; + int len = 0; mutex_lock(&wakelocks_lock); for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); if (wl->ws->active == show_active) - str += scnprintf(str, end - str, "%s ", wl->name); + len += sysfs_emit_at(buf, len, "%s ", wl->name); } - if (str > buf) - str--; - str += scnprintf(str, end - str, "\n"); + len += sysfs_emit_at(buf, len, "\n"); mutex_unlock(&wakelocks_lock); - return (str - buf); + return len; } #if CONFIG_PM_WAKELOCKS_LIMIT > 0 diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index d118739874c0..f5b388e810b9 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -2,5 +2,8 @@ obj-y = printk.o obj-$(CONFIG_PRINTK) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o -obj-$(CONFIG_PRINTK) += printk_ringbuffer.o obj-$(CONFIG_PRINTK_INDEX) += index.o + +obj-$(CONFIG_PRINTK) += printk_support.o +printk_support-y := printk_ringbuffer.o +printk_support-$(CONFIG_SYSCTL) += sysctl.o diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 9f3ed2fdb721..d947ca6c84f9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -4,6 +4,14 @@ */ #include <linux/percpu.h> +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) +void __init printk_sysctl_init(void); +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +#else +#define printk_sysctl_init() do { } while (0) +#endif + #ifdef CONFIG_PRINTK /* Flags for a single printk record. */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 155229f0cf0f..82abfaf3c2aa 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -171,7 +171,7 @@ static int __init control_devkmsg(char *str) __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; - +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -210,6 +210,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, return 0; } +#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; @@ -3211,6 +3212,7 @@ static int __init printk_late_init(void) ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); + printk_sysctl_init(); return 0; } late_initcall(printk_late_init); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c new file mode 100644 index 000000000000..653ae04aab7f --- /dev/null +++ b/kernel/printk/sysctl.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sysctl.c: General linux system control interface + */ + +#include <linux/sysctl.h> +#include <linux/printk.h> +#include <linux/capability.h> +#include <linux/ratelimit.h> +#include "internal.h" + +static const int ten_thousand = 10000; + +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} + +static struct ctl_table printk_sysctls[] = { + { + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_ratelimit", + .data = &printk_ratelimit_state.interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "printk_ratelimit_burst", + .data = &printk_ratelimit_state.burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_delay", + .data = &printk_delay_msec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&ten_thousand, + }, + { + .procname = "printk_devkmsg", + .data = devkmsg_log_str, + .maxlen = DEVKMSG_STR_MAX_SIZE, + .mode = 0644, + .proc_handler = devkmsg_sysctl_set_loglvl, + }, + { + .procname = "dmesg_restrict", + .data = &dmesg_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "kptr_restrict", + .data = &kptr_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + {} +}; + +void __init printk_sysctl_init(void) +{ + register_sysctl_init("kernel", printk_sysctls); +} diff --git a/kernel/profile.c b/kernel/profile.c index eb9c7f0f5ac5..37640a0bd8a3 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -133,79 +133,6 @@ int __ref profile_init(void) return -ENOMEM; } -/* Profile event notifications */ - -static BLOCKING_NOTIFIER_HEAD(task_exit_notifier); -static ATOMIC_NOTIFIER_HEAD(task_free_notifier); -static BLOCKING_NOTIFIER_HEAD(munmap_notifier); - -void profile_task_exit(struct task_struct *task) -{ - blocking_notifier_call_chain(&task_exit_notifier, 0, task); -} - -int profile_handoff_task(struct task_struct *task) -{ - int ret; - ret = atomic_notifier_call_chain(&task_free_notifier, 0, task); - return (ret == NOTIFY_OK) ? 1 : 0; -} - -void profile_munmap(unsigned long addr) -{ - blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr); -} - -int task_handoff_register(struct notifier_block *n) -{ - return atomic_notifier_chain_register(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_register); - -int task_handoff_unregister(struct notifier_block *n) -{ - return atomic_notifier_chain_unregister(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_unregister); - -int profile_event_register(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_register( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_register( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_register); - -int profile_event_unregister(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_unregister( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_unregister( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_unregister); - #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f8589bf8d7dc..eea265082e97 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -419,8 +419,6 @@ static int ptrace_attach(struct task_struct *task, long request, if (task->ptrace) goto unlock_tasklist; - if (seize) - flags |= PT_SEIZED; task->ptrace = flags; ptrace_link(task, current); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 33ea446101b3..422f7e4cc08d 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -2031,9 +2031,8 @@ static int rcutorture_booster_init(unsigned int cpu) mutex_lock(&boost_mutex); rcu_torture_disable_rt_throttle(); VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); - boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, - cpu_to_node(cpu), - "rcu_torture_boost"); + boost_tasks[cpu] = kthread_run_on_cpu(rcu_torture_boost, NULL, + cpu, "rcu_torture_boost_%u"); if (IS_ERR(boost_tasks[cpu])) { retval = PTR_ERR(boost_tasks[cpu]); VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed"); @@ -2042,8 +2041,6 @@ static int rcutorture_booster_init(unsigned int cpu) mutex_unlock(&boost_mutex); return retval; } - kthread_bind(boost_tasks[cpu], cpu); - wake_up_process(boost_tasks[cpu]); mutex_unlock(&boost_mutex); return 0; } diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 84f1d91604cc..d64f0b1d8cd3 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -123,7 +123,7 @@ static struct rcu_tasks rt_name = \ .call_func = call, \ .rtpcpu = &rt_name ## __percpu, \ .name = n, \ - .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS), \ + .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS) + 1, \ .percpu_enqueue_lim = 1, \ .percpu_dequeue_lim = 1, \ .barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex), \ @@ -216,6 +216,7 @@ static void cblist_init_generic(struct rcu_tasks *rtp) int cpu; unsigned long flags; int lim; + int shift; raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rcu_task_enqueue_lim < 0) { @@ -229,7 +230,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (lim > nr_cpu_ids) lim = nr_cpu_ids; - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids / lim)); + shift = ilog2(nr_cpu_ids / lim); + if (((nr_cpu_ids - 1) >> shift) >= lim) + shift++; + WRITE_ONCE(rtp->percpu_enqueue_shift, shift); WRITE_ONCE(rtp->percpu_dequeue_lim, lim); smp_store_release(&rtp->percpu_enqueue_lim, lim); for_each_possible_cpu(cpu) { @@ -298,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, if (unlikely(needadjust)) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim != nr_cpu_ids) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1); WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids); smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids); pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name); @@ -413,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim > 1) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name); diff --git a/kernel/resource.c b/kernel/resource.c index 5ad3eba619ba..9c08d6e9eef2 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -99,7 +99,7 @@ enum { MAX_IORES_LEVEL = 5 }; static void *r_start(struct seq_file *m, loff_t *pos) __acquires(resource_lock) { - struct resource *p = PDE_DATA(file_inode(m->file)); + struct resource *p = pde_data(file_inode(m->file)); loff_t l = 0; read_lock(&resource_lock); for (p = p->child; p && l < *pos; p = r_next(m, p, &l)) @@ -115,7 +115,7 @@ static void r_stop(struct seq_file *m, void *v) static int r_show(struct seq_file *m, void *v) { - struct resource *root = PDE_DATA(file_inode(m->file)); + struct resource *root = pde_data(file_inode(m->file)); struct resource *r = v, *p; unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 83872f95a1ea..848eaa0efe0e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5822,8 +5822,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } if (schedstat_enabled() && rq->core->core_forceidle_count) { - if (cookie) - rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_start = rq_clock(rq->core); rq->core->core_forceidle_occupation = occ; } @@ -8219,9 +8218,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; spin_lock(lock); @@ -8239,9 +8236,7 @@ int __cond_resched_rwlock_read(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { read_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; read_lock(lock); @@ -8259,9 +8254,7 @@ int __cond_resched_rwlock_write(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { write_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; write_lock(lock); @@ -8642,14 +8635,6 @@ void __init init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); - /* - * The idle task doesn't need the kthread struct to function, but it - * is dressed up as a per-CPU kthread and thus needs to play the part - * if we want to avoid special-casing it in code that deals with per-CPU - * kthreads. - */ - set_kthread_struct(idle); - raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_rq_lock(rq); @@ -9469,6 +9454,14 @@ void __init sched_init(void) enter_lazy_tlb(&init_mm, current); /* + * The idle task doesn't need the kthread struct to function, but it + * is dressed up as a per-CPU kthread and thus needs to play the part + * if we want to avoid special-casing it in code that deals with per-CPU + * kthreads. + */ + WARN_ON(!set_kthread_struct(current)); + + /* * Make us the idle thread. Technically, schedule() should not be * called from this thread, however somewhere below it might be, * but because we are the idle thread, we just pick up running again diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 1fb45672ec85..c8746a9a7ada 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -277,7 +277,7 @@ void __sched_core_account_forceidle(struct rq *rq) rq_i = cpu_rq(i); p = rq_i->core_pick ?: rq_i->curr; - if (!p->core_cookie) + if (p == rq_i->idle) continue; __schedstat_add(p->stats.core_forceidle_sum, delta); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 095b0aa378df..5146163bfabb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3028,9 +3028,11 @@ enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u32 divider = get_pelt_divider(&se->avg); sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } #else static inline void @@ -3381,7 +3383,6 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; } - /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3449,15 +3450,14 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3466,23 +3466,30 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq */ divider = get_pelt_divider(&cfs_rq->avg); + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; - se->avg.util_sum = se->avg.util_avg * divider; + new_sum = se->avg.util_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.util_sum; + se->avg.util_sum = new_sum; /* Update parent cfs_rq utilization */ - add_positive(&cfs_rq->avg.util_avg, delta); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + add_positive(&cfs_rq->avg.util_avg, delta_avg); + add_positive(&cfs_rq->avg.util_sum, delta_sum); + + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3493,19 +3500,25 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* Set new sched_entity's runnable */ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg; - se->avg.runnable_sum = se->avg.runnable_avg * divider; + new_sum = se->avg.runnable_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.runnable_sum; + se->avg.runnable_sum = new_sum; /* Update parent cfs_rq runnable */ - add_positive(&cfs_rq->avg.runnable_avg, delta); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + add_positive(&cfs_rq->avg.runnable_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; + s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3532,7 +3545,7 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq * assuming all tasks are equally runnable. */ if (scale_load_down(gcfs_rq->load.weight)) { - load_sum = div_s64(gcfs_rq->avg.load_sum, + load_sum = div_u64(gcfs_rq->avg.load_sum, scale_load_down(gcfs_rq->load.weight)); } @@ -3549,19 +3562,22 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); - load_sum = (s64)se_weight(se) * runnable_sum; - load_avg = div_s64(load_sum, divider); - - se->avg.load_sum = runnable_sum; + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); - delta = load_avg - se->avg.load_avg; - if (!delta) + delta_avg = load_avg - se->avg.load_avg; + if (!delta_avg) return; - se->avg.load_avg = load_avg; + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - add_positive(&cfs_rq->avg.load_avg, delta); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3652,7 +3668,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum * * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. * - * Returns true if the load decayed or we removed load. + * Return: true if the load decayed or we removed load. * * Since both these conditions indicate a changed cfs_rq->avg.load we should * call update_tg_load_avg() when this function returns true. @@ -3677,15 +3693,32 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sa->load_sum = sa->load_avg * divider; + sub_positive(&sa->load_sum, r * divider); + /* See sa->util_sum below */ + sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER); r = removed_util; sub_positive(&sa->util_avg, r); - sa->util_sum = sa->util_avg * divider; + sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sa->runnable_sum = sa->runnable_avg * divider; + sub_positive(&sa->runnable_sum, r * divider); + /* See sa->util_sum above */ + sa->runnable_sum = max_t(u32, sa->runnable_sum, + sa->runnable_avg * PELT_MIN_DIVIDER); /* * removed_runnable is the unweighted version of removed_load so we @@ -3772,17 +3805,18 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - /* - * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. - * See ___update_load_avg() for details. - */ - u32 divider = get_pelt_divider(&cfs_rq->avg); - dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); + sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -8539,6 +8573,8 @@ group_type group_classify(unsigned int imbalance_pct, * * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings * of @dst_cpu are idle and @sg has lower priority. + * + * Return: true if @dst_cpu can pull tasks, false otherwise. */ static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, @@ -8614,6 +8650,7 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. + * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. * @sg_status: Holds flag indicating the status of the sched_group @@ -9421,12 +9458,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. + * @env: The load balancing environment. * * Also calculates the amount of runnable load which should be moved * to restore balance. * - * @env: The load balancing environment. - * * Return: - The busiest group if imbalance exists. */ static struct sched_group *find_busiest_group(struct lb_env *env) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index b5add64d9698..3d2825408e3a 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -147,11 +147,11 @@ #endif #ifdef CONFIG_RSEQ -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \ +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ) #else -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 #endif #define MEMBARRIER_CMD_BITMASK \ @@ -159,7 +159,8 @@ | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ - | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) static void ipi_mb(void *info) { diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index e06071bf3472..c336f5f481bc 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif +#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) + static inline u32 get_pelt_divider(struct sched_avg *avg) { - return LOAD_AVG_MAX - 1024 + avg->period_contrib; + return PELT_MIN_DIVIDER + avg->period_contrib; } static inline void cfs_se_util_change(struct sched_avg *avg) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..e14358178849 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1082,44 +1082,6 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -static int psi_io_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_IO); -} - -static int psi_memory_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_MEM); -} - -static int psi_cpu_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_CPU); -} - -static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) -{ - if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return single_open(file, psi_show, NULL); -} - -static int psi_io_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_io_show); -} - -static int psi_memory_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_memory_show); -} - -static int psi_cpu_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_cpu_show); -} - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res) { @@ -1162,7 +1124,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1152,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1200,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1219,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,27 +1228,57 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } +#ifdef CONFIG_PROC_FS +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) +{ + if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + return single_open(file, psi_show, NULL); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_io_show); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_memory_show); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_cpu_show); +} + static ssize_t psi_write(struct file *file, const char __user *user_buf, size_t nbytes, enum psi_res res) { @@ -1316,14 +1299,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1351,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } @@ -1400,3 +1393,5 @@ static int __init psi_proc_init(void) return 0; } module_init(psi_proc_init); + +#endif /* CONFIG_PROC_FS */ diff --git a/kernel/signal.c b/kernel/signal.c index dfcee3888b00..38602738866e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -626,7 +626,8 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, * * All callers have to hold the siglock. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info) +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type) { bool resched_timer = false; int signr; @@ -634,8 +635,10 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ + *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { + *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS @@ -903,8 +906,8 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) struct task_struct *t; sigset_t flush; - if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { - if (!(signal->flags & SIGNAL_GROUP_EXIT)) + if (signal->flags & SIGNAL_GROUP_EXIT) { + if (signal->core_state) return sig == SIGKILL; /* * The process is in the middle of dying, nothing to do. @@ -1029,7 +1032,7 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type) * then start taking the whole group down immediately. */ if (sig_fatal(p, sig) && - !(signal->flags & SIGNAL_GROUP_EXIT) && + (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || !p->ptrace)) { /* @@ -1820,6 +1823,7 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) * force_sig_seccomp - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland * @reason: filter-supplied reason code to send to userland (via si_errno) + * @force_coredump: true to trigger a coredump * * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. */ @@ -2383,7 +2387,8 @@ static bool do_signal_stop(int signr) WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || - unlikely(signal_group_exit(sig))) + unlikely(sig->flags & SIGNAL_GROUP_EXIT) || + unlikely(sig->group_exec_task)) return false; /* * There is no group stop already in progress. We must @@ -2544,7 +2549,7 @@ static void do_freezer_trap(void) freezable_schedule(); } -static int ptrace_signal(int signr, kernel_siginfo_t *info) +static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type) { /* * We do not check sig_kernel_stop(signr) but set this marker @@ -2584,8 +2589,9 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info) } /* If the (new) signal is now blocked, requeue it. */ - if (sigismember(¤t->blocked, signr)) { - send_signal(signr, info, current, PIDTYPE_PID); + if (sigismember(¤t->blocked, signr) || + fatal_signal_pending(current)) { + send_signal(signr, info, current, type); signr = 0; } @@ -2684,18 +2690,20 @@ relock: goto relock; } - /* Has this task already been marked for death? */ - if (signal_group_exit(signal)) { - ksig->info.si_signo = signr = SIGKILL; - sigdelset(¤t->pending.signal, SIGKILL); - trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, - &sighand->action[SIGKILL - 1]); - recalc_sigpending(); - goto fatal; - } - for (;;) { struct k_sigaction *ka; + enum pid_type type; + + /* Has this task already been marked for death? */ + if ((signal->flags & SIGNAL_GROUP_EXIT) || + signal->group_exec_task) { + ksig->info.si_signo = signr = SIGKILL; + sigdelset(¤t->pending.signal, SIGKILL); + trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, + &sighand->action[SIGKILL - 1]); + recalc_sigpending(); + goto fatal; + } if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && do_signal_stop(0)) @@ -2728,16 +2736,18 @@ relock: * so that the instruction pointer in the signal stack * frame points to the faulting instruction. */ + type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + signr = dequeue_signal(current, ¤t->blocked, + &ksig->info, &type); if (!signr) break; /* will return 0 */ if (unlikely(current->ptrace) && (signr != SIGKILL) && !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { - signr = ptrace_signal(signr, &ksig->info); + signr = ptrace_signal(signr, &ksig->info, type); if (!signr) continue; } @@ -2863,13 +2873,13 @@ out: } /** - * signal_delivered - + * signal_delivered - called after signal delivery to update blocked signals * @ksig: kernel signal struct * @stepping: nonzero if debugger single-step or block-step in use * * This function should be called when a signal has successfully been * delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask - * is always blocked, and the signal itself is blocked unless %SA_NODEFER + * is always blocked), and the signal itself is blocked unless %SA_NODEFER * is set in @ksig->ka.sa.sa_flags. Tracing is notified. */ static void signal_delivered(struct ksignal *ksig, int stepping) @@ -2942,7 +2952,7 @@ void exit_signals(struct task_struct *tsk) */ cgroup_threadgroup_change_begin(tsk); - if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { + if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; @@ -3562,6 +3572,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; sigset_t mask = *which; + enum pid_type type; int sig, ret = 0; if (ts) { @@ -3578,7 +3589,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested @@ -3597,7 +3608,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ce161a8e8d97..66b8af394e58 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -16,11 +16,13 @@ #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include <linux/jump_label.h> #include <linux/sysctl.h> +#include <linux/init.h> static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +#ifdef CONFIG_SYSCTL +static int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; int state = !static_branch_unlikely(&stack_erasing_bypass); @@ -42,6 +44,26 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, state ? "enabled" : "disabled"); return ret; } +static struct ctl_table stackleak_sysctls[] = { + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init stackleak_sysctls_init(void) +{ + register_sysctl_init("kernel", stackleak_sysctls); + return 0; +} +late_initcall(stackleak_sysctls_init); +#endif /* CONFIG_SYSCTL */ #define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) #else diff --git a/kernel/sys.c b/kernel/sys.c index 8fdac0d90504..ecc4cf019242 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -220,7 +220,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) niceval = MAX_NICE; rcu_read_lock(); - read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) @@ -235,9 +234,11 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) pgrp = find_vpid(who); else pgrp = task_pgrp(current); + read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); @@ -249,16 +250,15 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) if (!user) goto out_unlock; /* No processes for this user */ } - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); - } while_each_thread(g, p); + } if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: - read_unlock(&tasklist_lock); rcu_read_unlock(); out: return error; @@ -283,7 +283,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) return -EINVAL; rcu_read_lock(); - read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) @@ -301,11 +300,13 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); + read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); @@ -317,19 +318,18 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) if (!user) goto out_unlock; /* No processes for this user */ } - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } - } while_each_thread(g, p); + } if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: - read_unlock(&tasklist_lock); rcu_read_unlock(); return retval; @@ -2261,6 +2261,66 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) +#ifdef CONFIG_ANON_VMA_NAME + +#define ANON_VMA_NAME_MAX_LEN 80 +#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" + +static inline bool is_valid_name_char(char ch) +{ + /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ + return ch > 0x1f && ch < 0x7f && + !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); +} + +static int prctl_set_vma(unsigned long opt, unsigned long addr, + unsigned long size, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + const char __user *uname; + char *name, *pch; + int error; + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + uname = (const char __user *)arg; + if (uname) { + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + for (pch = name; *pch != '\0'; pch++) { + if (!is_valid_name_char(*pch)) { + kfree(name); + return -EINVAL; + } + } + } else { + /* Reset the name */ + name = NULL; + } + + mmap_write_lock(mm); + error = madvise_set_anon_name(mm, addr, size, name); + mmap_write_unlock(mm); + kfree(name); + break; + default: + error = -EINVAL; + } + + return error; +} + +#else /* CONFIG_ANON_VMA_NAME */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long size, unsigned long arg) +{ + return -EINVAL; +} +#endif /* CONFIG_ANON_VMA_NAME */ + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2530,6 +2590,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d7ed1dffa426..5ae443b2882e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -20,7 +20,6 @@ */ #include <linux/module.h> -#include <linux/aio.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> @@ -50,7 +49,6 @@ #include <linux/times.h> #include <linux/limits.h> #include <linux/dcache.h> -#include <linux/dnotify.h> #include <linux/syscalls.h> #include <linux/vmstat.h> #include <linux/nfs_fs.h> @@ -58,19 +56,15 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/perf_event.h> -#include <linux/kprobes.h> -#include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/kmod.h> #include <linux/capability.h> #include <linux/binfmts.h> #include <linux/sched/sysctl.h> -#include <linux/sched/coredump.h> #include <linux/kexec.h> #include <linux/bpf.h> #include <linux/mount.h> #include <linux/userfaultfd_k.h> -#include <linux/coredump.h> #include <linux/latencytop.h> #include <linux/pid.h> #include <linux/delayacct.h> @@ -97,64 +91,21 @@ #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) #include <linux/lockdep.h> #endif -#ifdef CONFIG_CHR_DEV_SG -#include <scsi/sg.h> -#endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -#include <linux/stackleak.h> -#endif -#ifdef CONFIG_LOCKUP_DETECTOR -#include <linux/nmi.h> -#endif #if defined(CONFIG_SYSCTL) /* Constants used for minimum and maximum */ -#ifdef CONFIG_LOCKUP_DETECTOR -static int sixty = 60; -#endif - -static int __maybe_unused neg_one = -1; -static int __maybe_unused two = 2; -static int __maybe_unused four = 4; -static unsigned long zero_ul; -static unsigned long one_ul = 1; -static unsigned long long_max = LONG_MAX; -static int one_hundred = 100; -static int two_hundred = 200; -static int one_thousand = 1000; -#ifdef CONFIG_PRINTK -static int ten_thousand = 10000; -#endif + #ifdef CONFIG_PERF_EVENTS -static int six_hundred_forty_kb = 640 * 1024; +static const int six_hundred_forty_kb = 640 * 1024; #endif /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ -static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; - -/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ -static int maxolduid = 65535; -static int minolduid; +static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -static int ngroups_max = NGROUPS_MAX; +static const int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -/* - * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs - * and hung_task_check_interval_secs - */ -#ifdef CONFIG_DETECT_HUNG_TASK -static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); -#endif - -#ifdef CONFIG_INOTIFY_USER -#include <linux/inotify.h> -#endif -#ifdef CONFIG_FANOTIFY -#include <linux/fanotify.h> -#endif - #ifdef CONFIG_PROC_SYSCTL /** @@ -191,8 +142,8 @@ int sysctl_legacy_va_layout; #endif #ifdef CONFIG_COMPACTION -static int min_extfrag_threshold; -static int max_extfrag_threshold = 1000; +/* min_extfrag_threshold is SYSCTL_ZERO */; +static const int max_extfrag_threshold = 1000; #endif #endif /* CONFIG_SYSCTL */ @@ -803,12 +754,12 @@ static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); } -static int do_proc_douintvec(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) { return __do_proc_douintvec(table->data, table, write, buffer, lenp, ppos, conv, data); @@ -937,17 +888,6 @@ static int proc_taint(struct ctl_table *table, int write, return err; } -#ifdef CONFIG_PRINTK -static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - if (write && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); -} -#endif - /** * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure * @min: pointer to minimum allowable value @@ -1143,67 +1083,6 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); -static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, - unsigned int *valp, - int write, void *data) -{ - if (write) { - unsigned int val; - - val = round_pipe_size(*lvalp); - if (val == 0) - return -EINVAL; - - *valp = val; - } else { - unsigned int val = *valp; - *lvalp = (unsigned long) val; - } - - return 0; -} - -static int proc_dopipe_max_size(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, NULL); -} - -static void validate_coredump_safety(void) -{ -#ifdef CONFIG_COREDUMP - if (suid_dumpable == SUID_DUMP_ROOT && - core_pattern[0] != '/' && core_pattern[0] != '|') { - printk(KERN_WARNING -"Unsafe core_pattern used with fs.suid_dumpable=2.\n" -"Pipe handler or fully qualified core dump path required.\n" -"Set kernel.core_pattern before fs.suid_dumpable.\n" - ); - } -#endif -} - -static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!error) - validate_coredump_safety(); - return error; -} - -#ifdef CONFIG_COREDUMP -static int proc_dostring_coredump(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int error = proc_dostring(table, write, buffer, lenp, ppos); - if (!error) - validate_coredump_safety(); - return error; -} -#endif - #ifdef CONFIG_MAGIC_SYSRQ static int sysrq_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -1266,10 +1145,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, err = proc_get_long(&p, &left, &val, &neg, proc_wspace_sep, sizeof(proc_wspace_sep), NULL); - if (err) + if (err || neg) { + err = -EINVAL; break; - if (neg) - continue; + } + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) { err = -EINVAL; @@ -1927,29 +1807,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, -#ifdef CONFIG_COREDUMP - { - .procname = "core_uses_pid", - .data = &core_uses_pid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "core_pattern", - .data = core_pattern, - .maxlen = CORENAME_MAX_SIZE, - .mode = 0644, - .proc_handler = proc_dostring_coredump, - }, - { - .procname = "core_pipe_limit", - .data = &core_pipe_limit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", @@ -1963,7 +1820,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, .extra2 = SYSCTL_ONE, }, #endif @@ -2130,15 +1987,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dostring, }, #endif -#ifdef CONFIG_CHR_DEV_SG - { - .procname = "sg-big-buff", - .data = &sg_big_buff, - .maxlen = sizeof (int), - .mode = 0444, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_BSD_PROCESS_ACCT { .procname = "acct", @@ -2174,30 +2022,18 @@ static struct ctl_table kern_table[] = { .proc_handler = sysctl_max_threads, }, { - .procname = "random", - .mode = 0555, - .child = random_table, - }, - { .procname = "usermodehelper", .mode = 0555, .child = usermodehelper_table, }, -#ifdef CONFIG_FW_LOADER_USER_HELPER - { - .procname = "firmware_config", - .mode = 0555, - .child = firmware_config_table, - }, -#endif { .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, }, { .procname = "overflowgid", @@ -2205,8 +2041,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, }, #ifdef CONFIG_S390 { @@ -2251,66 +2087,9 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, -#if defined CONFIG_PRINTK - { - .procname = "printk", - .data = &console_loglevel, - .maxlen = 4*sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "printk_ratelimit", - .data = &printk_ratelimit_state.interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "printk_ratelimit_burst", - .data = &printk_ratelimit_state.burst, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "printk_delay", - .data = &printk_delay_msec, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &ten_thousand, - }, - { - .procname = "printk_devkmsg", - .data = devkmsg_log_str, - .maxlen = DEVKMSG_STR_MAX_SIZE, - .mode = 0644, - .proc_handler = devkmsg_sysctl_set_loglvl, - }, - { - .procname = "dmesg_restrict", - .data = &dmesg_restrict, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "kptr_restrict", - .data = &kptr_restrict, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, -#endif { .procname = "ngroups_max", - .data = &ngroups_max, + .data = (void *)&ngroups_max, .maxlen = sizeof (int), .mode = 0444, .proc_handler = proc_dointvec, @@ -2322,96 +2101,6 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, -#if defined(CONFIG_LOCKUP_DETECTOR) - { - .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "watchdog_thresh", - .data = &watchdog_thresh, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_watchdog_thresh, - .extra1 = SYSCTL_ZERO, - .extra2 = &sixty, - }, - { - .procname = "nmi_watchdog", - .data = &nmi_watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = NMI_WATCHDOG_SYSCTL_PERM, - .proc_handler = proc_nmi_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "watchdog_cpumask", - .data = &watchdog_cpumask_bits, - .maxlen = NR_CPUS, - .mode = 0644, - .proc_handler = proc_watchdog_cpumask, - }, -#ifdef CONFIG_SOFTLOCKUP_DETECTOR - { - .procname = "soft_watchdog", - .data = &soft_watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_soft_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "softlockup_panic", - .data = &softlockup_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#ifdef CONFIG_SMP - { - .procname = "softlockup_all_cpu_backtrace", - .data = &sysctl_softlockup_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ -#endif -#ifdef CONFIG_HARDLOCKUP_DETECTOR - { - .procname = "hardlockup_panic", - .data = &hardlockup_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#ifdef CONFIG_SMP - { - .procname = "hardlockup_all_cpu_backtrace", - .data = &sysctl_hardlockup_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ -#endif -#endif - #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { .procname = "unknown_nmi_panic", @@ -2514,60 +2203,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_DETECT_HUNG_TASK -#ifdef CONFIG_SMP - { - .procname = "hung_task_all_cpu_backtrace", - .data = &sysctl_hung_task_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ - { - .procname = "hung_task_panic", - .data = &sysctl_hung_task_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "hung_task_check_count", - .data = &sysctl_hung_task_check_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "hung_task_timeout_secs", - .data = &sysctl_hung_task_timeout_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_check_interval_secs", - .data = &sysctl_hung_task_check_interval_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_warnings", - .data = &sysctl_hung_task_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, - }, -#endif #ifdef CONFIG_RT_MUTEXES { .procname = "max_lock_depth", @@ -2627,7 +2262,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_cpu_time_max_percent_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "perf_event_max_stack", @@ -2636,7 +2271,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &six_hundred_forty_kb, + .extra2 = (void *)&six_hundred_forty_kb, }, { .procname = "perf_event_max_contexts_per_stack", @@ -2645,7 +2280,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_thousand, + .extra2 = SYSCTL_ONE_THOUSAND, }, #endif { @@ -2676,7 +2311,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", @@ -2708,17 +2343,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_INT_MAX, }, #endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE - { - .procname = "stack_erasing", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = stack_erasing_sysctl, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif { } }; @@ -2730,7 +2354,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = overcommit_policy_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "panic_on_oom", @@ -2739,7 +2363,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "oom_kill_allocating_task", @@ -2784,7 +2408,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", @@ -2792,7 +2416,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, - .extra1 = &one_ul, + .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", @@ -2801,7 +2425,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", @@ -2809,7 +2433,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, - .extra1 = &dirty_bytes_min, + .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", @@ -2841,7 +2465,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two_hundred, + .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_HUGETLB_PAGE { @@ -2898,7 +2522,7 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = drop_caches_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &four, + .extra2 = SYSCTL_FOUR, }, #ifdef CONFIG_COMPACTION { @@ -2915,7 +2539,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", @@ -2923,8 +2547,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &min_extfrag_threshold, - .extra2 = &max_extfrag_threshold, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&max_extfrag_threshold, }, { .procname = "compact_unevictable_allowed", @@ -2960,7 +2584,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &one_thousand, + .extra2 = SYSCTL_THREE_THOUSAND, }, { .procname = "percpu_pagelist_high_fraction", @@ -3039,7 +2663,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "min_slab_ratio", @@ -3048,7 +2672,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, #endif #ifdef CONFIG_SMP @@ -3182,221 +2806,6 @@ static struct ctl_table vm_table[] = { { } }; -static struct ctl_table fs_table[] = { - { - .procname = "inode-nr", - .data = &inodes_stat, - .maxlen = 2*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, - { - .procname = "inode-state", - .data = &inodes_stat, - .maxlen = 7*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, - { - .procname = "file-nr", - .data = &files_stat, - .maxlen = sizeof(files_stat), - .mode = 0444, - .proc_handler = proc_nr_files, - }, - { - .procname = "file-max", - .data = &files_stat.max_files, - .maxlen = sizeof(files_stat.max_files), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero_ul, - .extra2 = &long_max, - }, - { - .procname = "nr_open", - .data = &sysctl_nr_open, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &sysctl_nr_open_min, - .extra2 = &sysctl_nr_open_max, - }, - { - .procname = "dentry-state", - .data = &dentry_stat, - .maxlen = 6*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_dentry, - }, - { - .procname = "overflowuid", - .data = &fs_overflowuid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, - }, - { - .procname = "overflowgid", - .data = &fs_overflowgid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, - }, -#ifdef CONFIG_FILE_LOCKING - { - .procname = "leases-enable", - .data = &leases_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_DNOTIFY - { - .procname = "dir-notify-enable", - .data = &dir_notify_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_MMU -#ifdef CONFIG_FILE_LOCKING - { - .procname = "lease-break-time", - .data = &lease_break_time, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_AIO - { - .procname = "aio-nr", - .data = &aio_nr, - .maxlen = sizeof(aio_nr), - .mode = 0444, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "aio-max-nr", - .data = &aio_max_nr, - .maxlen = sizeof(aio_max_nr), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, -#endif /* CONFIG_AIO */ -#ifdef CONFIG_INOTIFY_USER - { - .procname = "inotify", - .mode = 0555, - .child = inotify_table, - }, -#endif -#ifdef CONFIG_FANOTIFY - { - .procname = "fanotify", - .mode = 0555, - .child = fanotify_table, - }, -#endif -#ifdef CONFIG_EPOLL - { - .procname = "epoll", - .mode = 0555, - .child = epoll_table, - }, -#endif -#endif - { - .procname = "protected_symlinks", - .data = &sysctl_protected_symlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_hardlinks", - .data = &sysctl_protected_hardlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_fifos", - .data = &sysctl_protected_fifos, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, - { - .procname = "protected_regular", - .data = &sysctl_protected_regular, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, - { - .procname = "suid_dumpable", - .data = &suid_dumpable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_coredump, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, -#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) - { - .procname = "binfmt_misc", - .mode = 0555, - .child = sysctl_mount_point, - }, -#endif - { - .procname = "pipe-max-size", - .data = &pipe_max_size, - .maxlen = sizeof(pipe_max_size), - .mode = 0644, - .proc_handler = proc_dopipe_max_size, - }, - { - .procname = "pipe-user-pages-hard", - .data = &pipe_user_pages_hard, - .maxlen = sizeof(pipe_user_pages_hard), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "pipe-user-pages-soft", - .data = &pipe_user_pages_soft, - .maxlen = sizeof(pipe_user_pages_soft), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "mount-max", - .data = &sysctl_mount_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, - { } -}; - static struct ctl_table debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { @@ -3407,17 +2816,6 @@ static struct ctl_table debug_table[] = { .proc_handler = proc_dointvec }, #endif -#if defined(CONFIG_OPTPROBES) - { - .procname = "kprobes-optimization", - .data = &sysctl_kprobes_optimization, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_kprobes_optimization_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif { } }; @@ -3425,41 +2823,18 @@ static struct ctl_table dev_table[] = { { } }; -static struct ctl_table sysctl_base_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kern_table, - }, - { - .procname = "vm", - .mode = 0555, - .child = vm_table, - }, - { - .procname = "fs", - .mode = 0555, - .child = fs_table, - }, - { - .procname = "debug", - .mode = 0555, - .child = debug_table, - }, - { - .procname = "dev", - .mode = 0555, - .child = dev_table, - }, - { } -}; +DECLARE_SYSCTL_BASE(kernel, kern_table); +DECLARE_SYSCTL_BASE(vm, vm_table); +DECLARE_SYSCTL_BASE(debug, debug_table); +DECLARE_SYSCTL_BASE(dev, dev_table); -int __init sysctl_init(void) +int __init sysctl_init_bases(void) { - struct ctl_table_header *hdr; + register_sysctl_base(kernel); + register_sysctl_base(vm); + register_sysctl_base(debug); + register_sysctl_base(dev); - hdr = register_sysctl_table(sysctl_base_table); - kmemleak_not_leak(hdr); return 0; } #endif /* CONFIG_SYSCTL */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index b7e52a642948..1cf73807b450 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -285,7 +285,7 @@ static void clocksource_verify_choose_cpus(void) return; /* Make sure to select at least one CPU other than the current CPU. */ - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (cpu == smp_processor_id()) cpu = cpumask_next(cpu, cpu_online_mask); if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) @@ -307,7 +307,7 @@ static void clocksource_verify_choose_cpus(void) cpu = prandom_u32() % nr_cpu_ids; cpu = cpumask_next(cpu - 1, cpu_online_mask); if (cpu >= nr_cpu_ids) - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (!WARN_ON_ONCE(cpu >= nr_cpu_ids)) cpumask_set_cpu(cpu, &cpus_chosen); } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 420ff4bc67fd..a5eb5e7fd624 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -70,6 +70,19 @@ config HAVE_C_RECORDMCOUNT help C version of recordmcount available? +config HAVE_BUILDTIME_MCOUNT_SORT + bool + help + An architecture selects this if it sorts the mcount_loc section + at build time. + +config BUILDTIME_MCOUNT_SORT + bool + default y + depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE + help + Sort the mcount_loc section at build time. + config TRACER_MAX_TRACE bool @@ -915,6 +928,20 @@ config EVENT_TRACE_TEST_SYSCALLS TBD - enable a way to actually call the syscalls as we test their events +config FTRACE_SORT_STARTUP_TEST + bool "Verify compile time sorting of ftrace functions" + depends on DYNAMIC_FTRACE + depends on BUILDTIME_MCOUNT_SORT + help + Sorting of the mcount_loc sections that is used to find the + where the ftrace knows where to patch functions for tracing + and other callbacks is done at compile time. But if the sort + is not done correctly, it will cause non-deterministic failures. + When this is set, the sorted sections will be verified that they + are in deed sorted and will warn if they are not. + + If unsure, say N + config RING_BUFFER_STARTUP_TEST bool "Ring buffer startup self test" depends on RING_BUFFER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index be5f6b32a012..f9feb197b2da 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6394,6 +6394,27 @@ static int ftrace_cmp_ips(const void *a, const void *b) return 0; } +#ifdef CONFIG_FTRACE_SORT_STARTUP_TEST +static void test_is_sorted(unsigned long *start, unsigned long count) +{ + int i; + + for (i = 1; i < count; i++) { + if (WARN(start[i - 1] > start[i], + "[%d] %pS at %lx is not sorted with %pS at %lx\n", i, + (void *)start[i - 1], start[i - 1], + (void *)start[i], start[i])) + break; + } + if (i == count) + pr_info("ftrace section at %px sorted properly\n", start); +} +#else +static void test_is_sorted(unsigned long *start, unsigned long count) +{ +} +#endif + static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) @@ -6412,8 +6433,17 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; - sort(start, count, sizeof(*start), - ftrace_cmp_ips, NULL); + /* + * Sorting mcount in vmlinux at build time depend on + * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in + * modules can not be sorted at build time. + */ + if (!IS_ENABLED(CONFIG_BUILDTIME_MCOUNT_SORT) || mod) { + sort(start, count, sizeof(*start), + ftrace_cmp_ips, NULL); + } else { + test_is_sorted(start, count); + } start_pg = ftrace_allocate_pages(count); if (!start_pg) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2699e9e562b1..05dfc7a12d3d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5898,16 +5898,13 @@ static __init int test_ringbuffer(void) rb_data[cpu].buffer = buffer; rb_data[cpu].cpu = cpu; rb_data[cpu].cnt = cpu; - rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], - "rbtester/%d", cpu); + rb_threads[cpu] = kthread_run_on_cpu(rb_test, &rb_data[cpu], + cpu, "rbtester/%u"); if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); ret = PTR_ERR(rb_threads[cpu]); goto out_free; } - - kthread_bind(rb_threads[cpu], cpu); - wake_up_process(rb_threads[cpu]); } /* Now create the rb hammer! */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 78ea542ce3bc..c860f582b078 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -980,6 +980,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev ring_buffer_write(buffer, event->array[0], &event->array[1]); /* Release the temp buffer */ this_cpu_dec(trace_buffered_event_cnt); + /* ring_buffer_unlock_commit() enables preemption */ + preempt_enable_notrace(); } else ring_buffer_unlock_commit(buffer, event); } @@ -2601,6 +2603,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) trace_flags |= TRACE_FLAG_HARDIRQ; if (in_serving_softirq()) trace_flags |= TRACE_FLAG_SOFTIRQ; + if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) + trace_flags |= TRACE_FLAG_BH_OFF; if (tif_need_resched()) trace_flags |= TRACE_FLAG_NEED_RESCHED; @@ -2745,8 +2749,8 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, *current_rb = tr->array_buffer.buffer; if (!tr->no_filter_buffering_ref && - (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) && - (entry = this_cpu_read(trace_buffered_event))) { + (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) { + preempt_disable_notrace(); /* * Filtering is on, so try to use the per cpu buffer first. * This buffer will simulate a ring_buffer_event, @@ -2764,33 +2768,38 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, * is still quicker than no copy on match, but having * to discard out of the ring buffer on a failed match. */ - int max_len = PAGE_SIZE - struct_size(entry, array, 1); + if ((entry = __this_cpu_read(trace_buffered_event))) { + int max_len = PAGE_SIZE - struct_size(entry, array, 1); - val = this_cpu_inc_return(trace_buffered_event_cnt); + val = this_cpu_inc_return(trace_buffered_event_cnt); - /* - * Preemption is disabled, but interrupts and NMIs - * can still come in now. If that happens after - * the above increment, then it will have to go - * back to the old method of allocating the event - * on the ring buffer, and if the filter fails, it - * will have to call ring_buffer_discard_commit() - * to remove it. - * - * Need to also check the unlikely case that the - * length is bigger than the temp buffer size. - * If that happens, then the reserve is pretty much - * guaranteed to fail, as the ring buffer currently - * only allows events less than a page. But that may - * change in the future, so let the ring buffer reserve - * handle the failure in that case. - */ - if (val == 1 && likely(len <= max_len)) { - trace_event_setup(entry, type, trace_ctx); - entry->array[0] = len; - return entry; + /* + * Preemption is disabled, but interrupts and NMIs + * can still come in now. If that happens after + * the above increment, then it will have to go + * back to the old method of allocating the event + * on the ring buffer, and if the filter fails, it + * will have to call ring_buffer_discard_commit() + * to remove it. + * + * Need to also check the unlikely case that the + * length is bigger than the temp buffer size. + * If that happens, then the reserve is pretty much + * guaranteed to fail, as the ring buffer currently + * only allows events less than a page. But that may + * change in the future, so let the ring buffer reserve + * handle the failure in that case. + */ + if (val == 1 && likely(len <= max_len)) { + trace_event_setup(entry, type, trace_ctx); + entry->array[0] = len; + /* Return with preemption disabled */ + return entry; + } + this_cpu_dec(trace_buffered_event_cnt); } - this_cpu_dec(trace_buffered_event_cnt); + /* __trace_buffer_lock_reserve() disables preemption */ + preempt_enable_notrace(); } entry = __trace_buffer_lock_reserve(*current_rb, type, len, @@ -4183,7 +4192,7 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" + "# / _-----=> irqs-off/BH-disabled\n" "# | / _----=> need-resched \n" "# || / _---=> hardirq/softirq \n" "# ||| / _--=> preempt-depth \n" @@ -4224,7 +4233,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); @@ -4834,6 +4843,12 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp) return 0; } +static int tracing_mark_open(struct inode *inode, struct file *filp) +{ + stream_open(inode, filp); + return tracing_open_generic_tr(inode, filp); +} + static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; @@ -5635,7 +5650,7 @@ static const char readme_msg[] = "\t - a numeric literal: e.g. ms_per_sec=1000,\n" "\t - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n" "\n" - "\t hist trigger aritmethic expressions support addition(+), subtraction(-),\n" + "\t hist trigger arithmetic expressions support addition(+), subtraction(-),\n" "\t multiplication(*) and division(/) operators. An operand can be either a\n" "\t variable reference, field or numeric literal.\n" "\n" @@ -6718,10 +6733,9 @@ waitagain: cnt = PAGE_SIZE - 1; /* reset all but tr, trace, and overruns */ - memset_startat(iter, 0, seq); + trace_iterator_reset(iter); cpumask_clear(iter->started); trace_seq_init(&iter->seq); - iter->pos = -1; trace_event_read_lock(); trace_access_lock(iter->cpu_file); @@ -7110,9 +7124,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tt) event_triggers_post_call(tr->trace_marker_file, tt); - if (written > 0) - *fpos += written; - return written; } @@ -7171,9 +7182,6 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, __buffer_unlock_commit(buffer, event); - if (written > 0) - *fpos += written; - return written; } @@ -7573,16 +7581,14 @@ static const struct file_operations tracing_free_buffer_fops = { }; static const struct file_operations tracing_mark_fops = { - .open = tracing_open_generic_tr, + .open = tracing_mark_open, .write = tracing_mark_write, - .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_mark_raw_fops = { - .open = tracing_open_generic_tr, + .open = tracing_mark_open, .write = tracing_mark_raw_write, - .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; @@ -7734,7 +7740,8 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) err = ERR_PTR(-ENOMEM); - tr->n_err_log_entries++; + else + tr->n_err_log_entries++; return err; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 38715aa6cfdf..d038ddbf1bea 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -83,6 +83,9 @@ enum trace_type { #undef __dynamic_array #define __dynamic_array(type, item) type item[]; +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item) type item[]; + #undef F_STRUCT #define F_STRUCT(args...) args @@ -1334,10 +1337,12 @@ __trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { if (this_cpu_read(trace_buffered_event) == event) { - /* Simply release the temp buffer */ + /* Simply release the temp buffer and enable preemption */ this_cpu_dec(trace_buffered_event_cnt); + preempt_enable_notrace(); return; } + /* ring_buffer_discard_commit() enables preemption */ ring_buffer_discard_commit(buffer, event); } @@ -1465,6 +1470,7 @@ struct filter_pred { static inline bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING || field->filter_type == FILTER_STATIC_STRING || field->filter_type == FILTER_PTR_STRING || field->filter_type == FILTER_COMM; @@ -1572,15 +1578,13 @@ extern int event_enable_trigger_print(struct seq_file *m, struct event_trigger_data *data); extern void event_enable_trigger_free(struct event_trigger_ops *ops, struct event_trigger_data *data); -extern int event_enable_trigger_func(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param); +extern int event_enable_trigger_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param); extern int event_enable_register_trigger(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); extern void event_enable_unregister_trigger(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *test, struct trace_event_file *file); extern void trigger_data_free(struct event_trigger_data *data); @@ -1606,6 +1610,30 @@ get_named_trigger_data(struct event_trigger_data *data); extern int register_event_command(struct event_command *cmd); extern int unregister_event_command(struct event_command *cmd); extern int register_trigger_hist_enable_disable_cmds(void); +extern bool event_trigger_check_remove(const char *glob); +extern bool event_trigger_empty_param(const char *param); +extern int event_trigger_separate_filter(char *param_and_filter, char **param, + char **filter, bool param_required); +extern struct event_trigger_data * +event_trigger_alloc(struct event_command *cmd_ops, + char *cmd, + char *param, + void *private_data); +extern int event_trigger_parse_num(char *trigger, + struct event_trigger_data *trigger_data); +extern int event_trigger_set_filter(struct event_command *cmd_ops, + struct trace_event_file *file, + char *param, + struct event_trigger_data *trigger_data); +extern void event_trigger_reset_filter(struct event_command *cmd_ops, + struct event_trigger_data *trigger_data); +extern int event_trigger_register(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, + char *cmd, + char *trigger, + struct event_trigger_data *trigger_data, + int *n_registered); /** * struct event_trigger_ops - callbacks for trace event triggers @@ -1613,10 +1641,20 @@ extern int register_trigger_hist_enable_disable_cmds(void); * The methods in this structure provide per-event trigger hooks for * various trigger operations. * + * The @init and @free methods are used during trigger setup and + * teardown, typically called from an event_command's @parse() + * function implementation. + * + * The @print method is used to print the trigger spec. + * + * The @trigger method is the function that actually implements the + * trigger and is called in the context of the triggering event + * whenever that event occurs. + * * All the methods below, except for @init() and @free(), must be * implemented. * - * @func: The trigger 'probe' function called when the triggering + * @trigger: The trigger 'probe' function called when the triggering * event occurs. The data passed into this callback is the data * that was supplied to the event_command @reg() function that * registered the trigger (see struct event_command) along with @@ -1645,9 +1683,10 @@ extern int register_trigger_hist_enable_disable_cmds(void); * (see trace_event_triggers.c). */ struct event_trigger_ops { - void (*func)(struct event_trigger_data *data, - struct trace_buffer *buffer, void *rec, - struct ring_buffer_event *rbe); + void (*trigger)(struct event_trigger_data *data, + struct trace_buffer *buffer, + void *rec, + struct ring_buffer_event *rbe); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); void (*free)(struct event_trigger_ops *ops, @@ -1696,7 +1735,7 @@ struct event_trigger_ops { * All the methods below, except for @set_filter() and @unreg_all(), * must be implemented. * - * @func: The callback function responsible for parsing and + * @parse: The callback function responsible for parsing and * registering the trigger written to the 'trigger' file by the * user. It allocates the trigger instance and registers it with * the appropriate trace event. It makes use of the other @@ -1731,21 +1770,24 @@ struct event_trigger_ops { * * @get_trigger_ops: The callback function invoked to retrieve the * event_trigger_ops implementation associated with the command. + * This callback function allows a single event_command to + * support multiple trigger implementations via different sets of + * event_trigger_ops, depending on the value of the @param + * string. */ struct event_command { struct list_head list; char *name; enum event_trigger_type trigger_type; int flags; - int (*func)(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *params); + int (*parse)(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, + char *param_and_filter); int (*reg)(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); void (*unreg)(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file); void (*unreg_all)(struct trace_event_file *file); @@ -1926,14 +1968,7 @@ extern struct trace_iterator *tracepoint_print_iter; */ static __always_inline void trace_iterator_reset(struct trace_iterator *iter) { - const size_t offset = offsetof(struct trace_iterator, seq); - - /* - * Keep gcc from complaining about overwriting more than just one - * member in the structure. - */ - memset((char *)iter + offset, 0, sizeof(struct trace_iterator) - offset); - + memset_startat(iter, 0, seq); iter->pos = -1; } diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 928867f527e7..191db32dec46 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -489,18 +489,12 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) if (trace_trigger_soft_disabled(edata->file)) return; - fbuffer.trace_ctx = tracing_gen_ctx(); - fbuffer.trace_file = edata->file; - dsize = get_eprobe_size(&edata->ep->tp, rec); - fbuffer.regs = NULL; - - fbuffer.event = - trace_event_buffer_lock_reserve(&fbuffer.buffer, edata->file, - call->event.type, - sizeof(*entry) + edata->ep->tp.size + dsize, - fbuffer.trace_ctx); - if (!fbuffer.event) + + entry = trace_event_buffer_reserve(&fbuffer, edata->file, + sizeof(*entry) + edata->ep->tp.size + dsize); + + if (!entry) return; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); @@ -549,29 +543,29 @@ static void eprobe_trigger_func(struct event_trigger_data *data, } static struct event_trigger_ops eprobe_trigger_ops = { - .func = eprobe_trigger_func, + .trigger = eprobe_trigger_func, .print = eprobe_trigger_print, .init = eprobe_trigger_init, .free = eprobe_trigger_free, }; -static int eprobe_trigger_cmd_func(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param) +static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param) { return -1; } -static int eprobe_trigger_reg_func(char *glob, struct event_trigger_ops *ops, - struct event_trigger_data *data, - struct trace_event_file *file) +static int eprobe_trigger_reg_func(char *glob, + struct event_trigger_data *data, + struct trace_event_file *file) { return -1; } -static void eprobe_trigger_unreg_func(char *glob, struct event_trigger_ops *ops, - struct event_trigger_data *data, - struct trace_event_file *file) +static void eprobe_trigger_unreg_func(char *glob, + struct event_trigger_data *data, + struct trace_event_file *file) { } @@ -586,7 +580,7 @@ static struct event_command event_trigger_cmd = { .name = "eprobe", .trigger_type = ETT_EVENT_EPROBE, .flags = EVENT_CMD_FL_NEEDS_REC, - .func = eprobe_trigger_cmd_func, + .parse = eprobe_trigger_cmd_parse, .reg = eprobe_trigger_reg_func, .unreg = eprobe_trigger_unreg_func, .unreg_all = NULL, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 92be9cb1d7d4..3147614c1812 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3461,10 +3461,8 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events, tr, &ftrace_tr_enable_fops); - if (!entry) { - pr_warn("Could not create tracefs 'enable' entry\n"); + if (!entry) return -ENOMEM; - } /* There are not as crucial, just warn if they are not created */ @@ -3480,17 +3478,13 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n"); /* ring buffer internal formats */ - entry = trace_create_file("header_page", TRACE_MODE_READ, d_events, + trace_create_file("header_page", TRACE_MODE_READ, d_events, ring_buffer_print_page_header, &ftrace_show_header_fops); - if (!entry) - pr_warn("Could not create tracefs 'header_page' entry\n"); - entry = trace_create_file("header_event", TRACE_MODE_READ, d_events, + trace_create_file("header_event", TRACE_MODE_READ, d_events, ring_buffer_print_entry_header, &ftrace_show_header_fops); - if (!entry) - pr_warn("Could not create tracefs 'header_event' entry\n"); tr->event_dir = d_events; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9124038b140..b458a9afa2c0 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -5,6 +5,7 @@ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> */ +#include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/mutex.h> @@ -654,6 +655,52 @@ DEFINE_EQUALITY_PRED(32); DEFINE_EQUALITY_PRED(16); DEFINE_EQUALITY_PRED(8); +/* user space strings temp buffer */ +#define USTRING_BUF_SIZE 1024 + +struct ustring_buffer { + char buffer[USTRING_BUF_SIZE]; +}; + +static __percpu struct ustring_buffer *ustring_per_cpu; + +static __always_inline char *test_string(char *str) +{ + struct ustring_buffer *ubuf; + char *kstr; + + if (!ustring_per_cpu) + return NULL; + + ubuf = this_cpu_ptr(ustring_per_cpu); + kstr = ubuf->buffer; + + /* For safety, do not trust the string pointer */ + if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE)) + return NULL; + return kstr; +} + +static __always_inline char *test_ustring(char *str) +{ + struct ustring_buffer *ubuf; + char __user *ustr; + char *kstr; + + if (!ustring_per_cpu) + return NULL; + + ubuf = this_cpu_ptr(ustring_per_cpu); + kstr = ubuf->buffer; + + /* user space address? */ + ustr = (char __user *)str; + if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE)) + return NULL; + + return kstr; +} + /* Filter predicate for fixed sized arrays of characters */ static int filter_pred_string(struct filter_pred *pred, void *event) { @@ -667,19 +714,43 @@ static int filter_pred_string(struct filter_pred *pred, void *event) return match; } -/* Filter predicate for char * pointers */ -static int filter_pred_pchar(struct filter_pred *pred, void *event) +static __always_inline int filter_pchar(struct filter_pred *pred, char *str) { - char **addr = (char **)(event + pred->offset); int cmp, match; - int len = strlen(*addr) + 1; /* including tailing '\0' */ + int len; - cmp = pred->regex.match(*addr, &pred->regex, len); + len = strlen(str) + 1; /* including tailing '\0' */ + cmp = pred->regex.match(str, &pred->regex, len); match = cmp ^ pred->not; return match; } +/* Filter predicate for char * pointers */ +static int filter_pred_pchar(struct filter_pred *pred, void *event) +{ + char **addr = (char **)(event + pred->offset); + char *str; + + str = test_string(*addr); + if (!str) + return 0; + + return filter_pchar(pred, str); +} + +/* Filter predicate for char * pointers in user space*/ +static int filter_pred_pchar_user(struct filter_pred *pred, void *event) +{ + char **addr = (char **)(event + pred->offset); + char *str; + + str = test_ustring(*addr); + if (!str) + return 0; + + return filter_pchar(pred, str); +} /* * Filter predicate for dynamic sized arrays of characters. @@ -706,6 +777,29 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event) return match; } +/* + * Filter predicate for relative dynamic sized arrays of characters. + * These are implemented through a list of strings at the end + * of the entry as same as dynamic string. + * The difference is that the relative one records the location offset + * from the field itself, not the event entry. + */ +static int filter_pred_strrelloc(struct filter_pred *pred, void *event) +{ + u32 *item = (u32 *)(event + pred->offset); + u32 str_item = *item; + int str_loc = str_item & 0xffff; + int str_len = str_item >> 16; + char *addr = (char *)(&item[1]) + str_loc; + int cmp, match; + + cmp = pred->regex.match(addr, &pred->regex, str_len); + + match = cmp ^ pred->not; + + return match; +} + /* Filter predicate for CPUs. */ static int filter_pred_cpu(struct filter_pred *pred, void *event) { @@ -756,7 +850,7 @@ static int filter_pred_none(struct filter_pred *pred, void *event) * * Note: * - @str might not be NULL-terminated if it's of type DYN_STRING - * or STATIC_STRING, unless @len is zero. + * RDYN_STRING, or STATIC_STRING, unless @len is zero. */ static int regex_match_full(char *str, struct regex *r, int len) @@ -1083,6 +1177,9 @@ int filter_assign_type(const char *type) if (strstr(type, "__data_loc") && strstr(type, "char")) return FILTER_DYN_STRING; + if (strstr(type, "__rel_loc") && strstr(type, "char")) + return FILTER_RDYN_STRING; + if (strchr(type, '[') && strstr(type, "char")) return FILTER_STATIC_STRING; @@ -1158,6 +1255,7 @@ static int parse_pred(const char *str, void *data, struct filter_pred *pred = NULL; char num_buf[24]; /* Big enough to hold an address */ char *field_name; + bool ustring = false; char q; u64 val; int len; @@ -1192,6 +1290,12 @@ static int parse_pred(const char *str, void *data, return -EINVAL; } + /* See if the field is a user space string */ + if ((len = str_has_prefix(str + i, ".ustring"))) { + ustring = true; + i += len; + } + while (isspace(str[i])) i++; @@ -1318,10 +1422,24 @@ static int parse_pred(const char *str, void *data, pred->fn = filter_pred_string; pred->regex.field_len = field->size; - } else if (field->filter_type == FILTER_DYN_STRING) + } else if (field->filter_type == FILTER_DYN_STRING) { pred->fn = filter_pred_strloc; - else - pred->fn = filter_pred_pchar; + } else if (field->filter_type == FILTER_RDYN_STRING) + pred->fn = filter_pred_strrelloc; + else { + + if (!ustring_per_cpu) { + /* Once allocated, keep it around for good */ + ustring_per_cpu = alloc_percpu(struct ustring_buffer); + if (!ustring_per_cpu) + goto err_mem; + } + + if (ustring) + pred->fn = filter_pred_pchar_user; + else + pred->fn = filter_pred_pchar; + } /* go past the last quote */ i++; @@ -1387,6 +1505,9 @@ static int parse_pred(const char *str, void *data, err_free: kfree(pred); return -EINVAL; +err_mem: + kfree(pred); + return -ENOMEM; } enum { diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 319f9c8ca7e7..ada87bfb5bb8 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -217,6 +217,20 @@ static u64 hist_field_dynstring(struct hist_field *hist_field, return (u64)(unsigned long)addr; } +static u64 hist_field_reldynstring(struct hist_field *hist_field, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, + struct ring_buffer_event *rbe, + void *event) +{ + u32 *item = event + hist_field->field->offset; + u32 str_item = *item; + int str_loc = str_item & 0xffff; + char *addr = (char *)&item[1] + str_loc; + + return (u64)(unsigned long)addr; +} + static u64 hist_field_pstring(struct hist_field *hist_field, struct tracing_map_elt *elt, struct trace_buffer *buffer, @@ -1956,8 +1970,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (field->filter_type == FILTER_STATIC_STRING) { hist_field->fn = hist_field_string; hist_field->size = field->size; - } else if (field->filter_type == FILTER_DYN_STRING) + } else if (field->filter_type == FILTER_DYN_STRING) { hist_field->fn = hist_field_dynstring; + } else if (field->filter_type == FILTER_RDYN_STRING) + hist_field->fn = hist_field_reldynstring; else hist_field->fn = hist_field_pstring; } else { @@ -2487,6 +2503,8 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data, (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS); expr->fn = hist_field_unary_minus; expr->operands[0] = operand1; + expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = FIELD_OP_UNARY_MINUS; expr->name = expr_str(expr, 0); expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -2703,6 +2721,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, /* The operand sizes should be the same, so just pick one */ expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = field_op; expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -2745,9 +2764,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, } static struct event_command trigger_hist_cmd; -static int event_hist_trigger_func(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param); +static int event_hist_trigger_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param); static bool compatible_keys(struct hist_trigger_data *target_hist_data, struct hist_trigger_data *hist_data, @@ -2950,8 +2969,8 @@ create_field_var_hist(struct hist_trigger_data *target_hist_data, var_hist->hist_data = hist_data; /* Create the new histogram with our variable */ - ret = event_hist_trigger_func(&trigger_hist_cmd, file, - "", "hist", cmd); + ret = event_hist_trigger_parse(&trigger_hist_cmd, file, + "", "hist", cmd); if (ret) { kfree(cmd); kfree(var_hist->cmd); @@ -3919,6 +3938,7 @@ static int trace_action_create(struct hist_trigger_data *hist_data, var_ref_idx = find_var_ref_idx(hist_data, var_ref); if (WARN_ON(var_ref_idx < 0)) { + kfree(p); ret = var_ref_idx; goto err; } @@ -4961,7 +4981,8 @@ static inline void add_to_key(char *compound_key, void *key, struct ftrace_event_field *field; field = key_field->field; - if (field->filter_type == FILTER_DYN_STRING) + if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) size = *(u32 *)(rec + field->offset) >> 16; else if (field->filter_type == FILTER_STATIC_STRING) size = field->size; @@ -5712,8 +5733,8 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data) for (i = 0; i < hist_data->n_field_var_hists; i++) { file = hist_data->field_var_hists[i]->hist_data->event_file; cmd = hist_data->field_var_hists[i]->cmd; - ret = event_hist_trigger_func(&trigger_hist_cmd, file, - "!hist", "hist", cmd); + ret = event_hist_trigger_parse(&trigger_hist_cmd, file, + "!hist", "hist", cmd); WARN_ON_ONCE(ret < 0); } } @@ -5742,7 +5763,7 @@ static void event_hist_trigger_free(struct event_trigger_ops *ops, } static struct event_trigger_ops event_hist_trigger_ops = { - .func = event_hist_trigger, + .trigger = event_hist_trigger, .print = event_hist_trigger_print, .init = event_hist_trigger_init, .free = event_hist_trigger_free, @@ -5776,7 +5797,7 @@ static void event_hist_trigger_named_free(struct event_trigger_ops *ops, } static struct event_trigger_ops event_hist_trigger_named_ops = { - .func = event_hist_trigger, + .trigger = event_hist_trigger, .print = event_hist_trigger_print, .init = event_hist_trigger_named_init, .free = event_hist_trigger_named_free, @@ -5893,7 +5914,7 @@ static bool hist_trigger_match(struct event_trigger_data *data, return true; } -static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, +static int hist_register_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { @@ -6045,7 +6066,7 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, return false; } -static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, +static void hist_unregister_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { @@ -6129,9 +6150,9 @@ static void hist_unreg_all(struct trace_event_file *file) } } -static int event_hist_trigger_func(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param) +static int event_hist_trigger_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param) { unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT; struct event_trigger_data *trigger_data; @@ -6146,7 +6167,9 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, lockdep_assert_held(&event_mutex); - if (glob && strlen(glob)) { + WARN_ON(!glob); + + if (strlen(glob)) { hist_err_clear(); last_cmd_set(file, param); } @@ -6179,7 +6202,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, continue; } break; - } while (p); + } while (1); if (!p) param = NULL; @@ -6245,7 +6268,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, goto out_free; } - cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + cmd_ops->unreg(glob+1, trigger_data, file); se_name = trace_event_name(file->event_call); se = find_synth_event(se_name); if (se) @@ -6254,7 +6277,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, goto out_free; } - ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); + ret = cmd_ops->reg(glob, trigger_data, file); /* * The above returns on success the # of triggers registered, * but if it didn't register any it returns zero. Consider no @@ -6297,7 +6320,7 @@ enable: return ret; out_unreg: - cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + cmd_ops->unreg(glob+1, trigger_data, file); out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); @@ -6314,7 +6337,7 @@ static struct event_command trigger_hist_cmd = { .name = "hist", .trigger_type = ETT_EVENT_HIST, .flags = EVENT_CMD_FL_NEEDS_REC, - .func = event_hist_trigger_func, + .parse = event_hist_trigger_parse, .reg = hist_register_trigger, .unreg = hist_unregister_trigger, .unreg_all = hist_unreg_all, @@ -6366,28 +6389,28 @@ hist_enable_count_trigger(struct event_trigger_data *data, } static struct event_trigger_ops hist_enable_trigger_ops = { - .func = hist_enable_trigger, + .trigger = hist_enable_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops hist_enable_count_trigger_ops = { - .func = hist_enable_count_trigger, + .trigger = hist_enable_count_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops hist_disable_trigger_ops = { - .func = hist_enable_trigger, + .trigger = hist_enable_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops hist_disable_count_trigger_ops = { - .func = hist_enable_count_trigger, + .trigger = hist_enable_count_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, @@ -6429,7 +6452,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file) static struct event_command trigger_hist_enable_cmd = { .name = ENABLE_HIST_STR, .trigger_type = ETT_HIST_ENABLE, - .func = event_enable_trigger_func, + .parse = event_enable_trigger_parse, .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .unreg_all = hist_enable_unreg_all, @@ -6440,7 +6463,7 @@ static struct event_command trigger_hist_enable_cmd = { static struct event_command trigger_hist_disable_cmd = { .name = DISABLE_HIST_STR, .trigger_type = ETT_HIST_ENABLE, - .func = event_enable_trigger_func, + .parse = event_enable_trigger_parse, .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .unreg_all = hist_enable_unreg_all, diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index c188045c5f97..d6b4935a78c0 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -168,10 +168,14 @@ static void *trace_alloc_entry(struct trace_event_call *call, int *size) continue; if (field->filter_type == FILTER_STATIC_STRING) continue; - if (field->filter_type == FILTER_DYN_STRING) { + if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) { u32 *str_item; int str_loc = entry_size & 0xffff; + if (field->filter_type == FILTER_RDYN_STRING) + str_loc -= field->offset + field->size; + str_item = (u32 *)(entry + field->offset); *str_item = str_loc; /* string length is 0. */ } else { @@ -214,7 +218,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) if (field->filter_type == FILTER_STATIC_STRING) { strlcpy(entry + field->offset, addr, field->size); - } else if (field->filter_type == FILTER_DYN_STRING) { + } else if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) { int str_len = strlen(addr) + 1; int str_loc = entry_size & 0xffff; u32 *str_item; @@ -229,6 +234,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) strlcpy(entry + (entry_size - str_len), addr, str_len); str_item = (u32 *)(entry + field->offset); + if (field->filter_type == FILTER_RDYN_STRING) + str_loc -= field->offset + field->size; *str_item = (str_len << 16) | str_loc; } else { char **paddr; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index ca9c13b2ecf4..154db74dadbc 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1979,7 +1979,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_next_val); /** * synth_event_add_val - Add a named field's value to an open synth trace * @field_name: The name of the synthetic event field value to set - * @val: The value to set the next field to + * @val: The value to set the named field to * @trace_state: A pointer to object tracking the piecewise trace state * * Set the value of the named field in an event that's been opened by @@ -2054,6 +2054,13 @@ static int create_synth_event(const char *raw_command) last_cmd_set(raw_command); + name = raw_command; + + /* Don't try to process if not our system */ + if (name[0] != 's' || name[1] != ':') + return -ECANCELED; + name += 2; + p = strpbrk(raw_command, " \t"); if (!p) { synth_err(SYNTH_ERR_INVALID_CMD, 0); @@ -2062,12 +2069,6 @@ static int create_synth_event(const char *raw_command) fields = skip_spaces(p); - name = raw_command; - - if (name[0] != 's' || name[1] != ':') - return -ECANCELED; - name += 2; - /* This interface accepts group name prefix */ if (strchr(name, '/')) { len = str_has_prefix(name, SYNTH_SYSTEM "/"); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 3d5c07239a2a..d00fee705f9c 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -68,7 +68,7 @@ event_triggers_call(struct trace_event_file *file, if (data->paused) continue; if (!rec) { - data->ops->func(data, buffer, rec, event); + data->ops->trigger(data, buffer, rec, event); continue; } filter = rcu_dereference_sched(data->filter); @@ -78,7 +78,7 @@ event_triggers_call(struct trace_event_file *file, tt |= data->cmd_ops->trigger_type; continue; } - data->ops->func(data, buffer, rec, event); + data->ops->trigger(data, buffer, rec, event); } return tt; } @@ -106,7 +106,7 @@ event_triggers_post_call(struct trace_event_file *file, if (data->paused) continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data, NULL, NULL, NULL); + data->ops->trigger(data, NULL, NULL, NULL); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -245,7 +245,7 @@ int trigger_process_regex(struct trace_event_file *file, char *buff) mutex_lock(&trigger_cmd_mutex); list_for_each_entry(p, &trigger_commands, list) { if (strcmp(p->name, command) == 0) { - ret = p->func(p, file, buff, command, next); + ret = p->parse(p, file, buff, command, next); goto out_unlock; } } @@ -540,7 +540,6 @@ void update_cond_flag(struct trace_event_file *file) /** * register_trigger - Generic event_command @reg implementation * @glob: The raw string used to register the trigger - * @ops: The trigger ops associated with the trigger * @data: Trigger-specific data to associate with the trigger * @file: The trace_event_file associated with the event * @@ -551,7 +550,7 @@ void update_cond_flag(struct trace_event_file *file) * * Return: 0 on success, errno otherwise */ -static int register_trigger(char *glob, struct event_trigger_ops *ops, +static int register_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { @@ -589,7 +588,6 @@ out: /** * unregister_trigger - Generic event_command @unreg implementation * @glob: The raw string used to register the trigger - * @ops: The trigger ops associated with the trigger * @test: Trigger-specific data used to find the trigger to remove * @file: The trace_event_file associated with the event * @@ -598,7 +596,7 @@ out: * Usually used directly as the @unreg method in event command * implementations. */ -static void unregister_trigger(char *glob, struct event_trigger_ops *ops, +static void unregister_trigger(char *glob, struct event_trigger_data *test, struct trace_event_file *file) { @@ -621,8 +619,350 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, data->ops->free(data->ops, data); } +/* + * Event trigger parsing helper functions. + * + * These functions help make it easier to write an event trigger + * parsing function i.e. the struct event_command.parse() callback + * function responsible for parsing and registering a trigger command + * written to the 'trigger' file. + * + * A trigger command (or just 'trigger' for short) takes the form: + * [trigger] [if filter] + * + * The struct event_command.parse() callback (and other struct + * event_command functions) refer to several components of a trigger + * command. Those same components are referenced by the event trigger + * parsing helper functions defined below. These components are: + * + * cmd - the trigger command name + * glob - the trigger command name optionally prefaced with '!' + * param_and_filter - text following cmd and ':' + * param - text following cmd and ':' and stripped of filter + * filter - the optional filter text following (and including) 'if' + * + * To illustrate the use of these componenents, here are some concrete + * examples. For the following triggers: + * + * echo 'traceon:5 if pid == 0' > trigger + * - 'traceon' is both cmd and glob + * - '5 if pid == 0' is the param_and_filter + * - '5' is the param + * - 'if pid == 0' is the filter + * + * echo 'enable_event:sys:event:n' > trigger + * - 'enable_event' is both cmd and glob + * - 'sys:event:n' is the param_and_filter + * - 'sys:event:n' is the param + * - there is no filter + * + * echo 'hist:keys=pid if prio > 50' > trigger + * - 'hist' is both cmd and glob + * - 'keys=pid if prio > 50' is the param_and_filter + * - 'keys=pid' is the param + * - 'if prio > 50' is the filter + * + * echo '!enable_event:sys:event:n' > trigger + * - 'enable_event' the cmd + * - '!enable_event' is the glob + * - 'sys:event:n' is the param_and_filter + * - 'sys:event:n' is the param + * - there is no filter + * + * echo 'traceoff' > trigger + * - 'traceoff' is both cmd and glob + * - there is no param_and_filter + * - there is no param + * - there is no filter + * + * There are a few different categories of event trigger covered by + * these helpers: + * + * - triggers that don't require a parameter e.g. traceon + * - triggers that do require a parameter e.g. enable_event and hist + * - triggers that though they may not require a param may support an + * optional 'n' param (n = number of times the trigger should fire) + * e.g.: traceon:5 or enable_event:sys:event:n + * - triggers that do not support an 'n' param e.g. hist + * + * These functions can be used or ignored as necessary - it all + * depends on the complexity of the trigger, and the granularity of + * the functions supported reflects the fact that some implementations + * may need to customize certain aspects of their implementations and + * won't need certain functions. For instance, the hist trigger + * implementation doesn't use event_trigger_separate_filter() because + * it has special requirements for handling the filter. + */ + +/** + * event_trigger_check_remove - check whether an event trigger specifies remove + * @glob: The trigger command string, with optional remove(!) operator + * + * The event trigger callback implementations pass in 'glob' as a + * parameter. This is the command name either with or without a + * remove(!) operator. This function simply parses the glob and + * determines whether the command corresponds to a trigger removal or + * a trigger addition. + * + * Return: true if this is a remove command, false otherwise + */ +bool event_trigger_check_remove(const char *glob) +{ + return (glob && glob[0] == '!') ? true : false; +} + +/** + * event_trigger_empty_param - check whether the param is empty + * @param: The trigger param string + * + * The event trigger callback implementations pass in 'param' as a + * parameter. This corresponds to the string following the command + * name minus the command name. This function can be called by a + * callback implementation for any command that requires a param; a + * callback that doesn't require a param can ignore it. + * + * Return: true if this is an empty param, false otherwise + */ +bool event_trigger_empty_param(const char *param) +{ + return !param; +} + +/** + * event_trigger_separate_filter - separate an event trigger from a filter + * @param: The param string containing trigger and possibly filter + * @trigger: outparam, will be filled with a pointer to the trigger + * @filter: outparam, will be filled with a pointer to the filter + * @param_required: Specifies whether or not the param string is required + * + * Given a param string of the form '[trigger] [if filter]', this + * function separates the filter from the trigger and returns the + * trigger in *trigger and the filter in *filter. Either the *trigger + * or the *filter may be set to NULL by this function - if not set to + * NULL, they will contain strings corresponding to the trigger and + * filter. + * + * There are two cases that need to be handled with respect to the + * passed-in param: either the param is required, or it is not + * required. If @param_required is set, and there's no param, it will + * return -EINVAL. If @param_required is not set and there's a param + * that starts with a number, that corresponds to the case of a + * trigger with :n (n = number of times the trigger should fire) and + * the parsing continues normally; otherwise the function just returns + * and assumes param just contains a filter and there's nothing else + * to do. + * + * Return: 0 on success, errno otherwise + */ +int event_trigger_separate_filter(char *param_and_filter, char **param, + char **filter, bool param_required) +{ + int ret = 0; + + *param = *filter = NULL; + + if (!param_and_filter) { + if (param_required) + ret = -EINVAL; + goto out; + } + + /* + * Here we check for an optional param. The only legal + * optional param is :n, and if that's the case, continue + * below. Otherwise we assume what's left is a filter and + * return it as the filter string for the caller to deal with. + */ + if (!param_required && param_and_filter && !isdigit(param_and_filter[0])) { + *filter = param_and_filter; + goto out; + } + + /* + * Separate the param from the filter (param [if filter]). + * Here we have either an optional :n param or a required + * param and an optional filter. + */ + *param = strsep(¶m_and_filter, " \t"); + + /* + * Here we have a filter, though it may be empty. + */ + if (param_and_filter) { + *filter = skip_spaces(param_and_filter); + if (!**filter) + *filter = NULL; + } +out: + return ret; +} + +/** + * event_trigger_alloc - allocate and init event_trigger_data for a trigger + * @cmd_ops: The event_command operations for the trigger + * @cmd: The cmd string + * @param: The param string + * @private_data: User data to associate with the event trigger + * + * Allocate an event_trigger_data instance and initialize it. The + * @cmd_ops are used along with the @cmd and @param to get the + * trigger_ops to assign to the event_trigger_data. @private_data can + * also be passed in and associated with the event_trigger_data. + * + * Use event_trigger_free() to free an event_trigger_data object. + * + * Return: The trigger_data object success, NULL otherwise + */ +struct event_trigger_data *event_trigger_alloc(struct event_command *cmd_ops, + char *cmd, + char *param, + void *private_data) +{ + struct event_trigger_data *trigger_data; + struct event_trigger_ops *trigger_ops; + + trigger_ops = cmd_ops->get_trigger_ops(cmd, param); + + trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); + if (!trigger_data) + return NULL; + + trigger_data->count = -1; + trigger_data->ops = trigger_ops; + trigger_data->cmd_ops = cmd_ops; + trigger_data->private_data = private_data; + + INIT_LIST_HEAD(&trigger_data->list); + INIT_LIST_HEAD(&trigger_data->named_list); + RCU_INIT_POINTER(trigger_data->filter, NULL); + + return trigger_data; +} + +/** + * event_trigger_parse_num - parse and return the number param for a trigger + * @param: The param string + * @trigger_data: The trigger_data for the trigger + * + * Parse the :n (n = number of times the trigger should fire) param + * and set the count variable in the trigger_data to the parsed count. + * + * Return: 0 on success, errno otherwise + */ +int event_trigger_parse_num(char *param, + struct event_trigger_data *trigger_data) +{ + char *number; + int ret = 0; + + if (param) { + number = strsep(¶m, ":"); + + if (!strlen(number)) + return -EINVAL; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &trigger_data->count); + } + + return ret; +} + +/** + * event_trigger_set_filter - set an event trigger's filter + * @cmd_ops: The event_command operations for the trigger + * @file: The event file for the trigger's event + * @param: The string containing the filter + * @trigger_data: The trigger_data for the trigger + * + * Set the filter for the trigger. If the filter is NULL, just return + * without error. + * + * Return: 0 on success, errno otherwise + */ +int event_trigger_set_filter(struct event_command *cmd_ops, + struct trace_event_file *file, + char *param, + struct event_trigger_data *trigger_data) +{ + if (param && cmd_ops->set_filter) + return cmd_ops->set_filter(param, trigger_data, file); + + return 0; +} + +/** + * event_trigger_reset_filter - reset an event trigger's filter + * @cmd_ops: The event_command operations for the trigger + * @trigger_data: The trigger_data for the trigger + * + * Reset the filter for the trigger to no filter. + */ +void event_trigger_reset_filter(struct event_command *cmd_ops, + struct event_trigger_data *trigger_data) +{ + if (cmd_ops->set_filter) + cmd_ops->set_filter(NULL, trigger_data, NULL); +} + +/** + * event_trigger_register - register an event trigger + * @cmd_ops: The event_command operations for the trigger + * @file: The event file for the trigger's event + * @glob: The trigger command string, with optional remove(!) operator + * @cmd: The cmd string + * @param: The param string + * @trigger_data: The trigger_data for the trigger + * @n_registered: optional outparam, the number of triggers registered + * + * Register an event trigger. The @cmd_ops are used to call the + * cmd_ops->reg() function which actually does the registration. The + * cmd_ops->reg() function returns the number of triggers registered, + * which is assigned to n_registered, if n_registered is non-NULL. + * + * Return: 0 on success, errno otherwise + */ +int event_trigger_register(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, + char *cmd, + char *param, + struct event_trigger_data *trigger_data, + int *n_registered) +{ + int ret; + + if (n_registered) + *n_registered = 0; + + ret = cmd_ops->reg(glob, trigger_data, file); + /* + * The above returns on success the # of functions enabled, + * but if it didn't find any functions it returns zero. + * Consider no functions a failure too. + */ + if (!ret) { + cmd_ops->unreg(glob, trigger_data, file); + ret = -ENOENT; + } else if (ret > 0) { + if (n_registered) + *n_registered = ret; + /* Just return zero, not the number of enabled functions */ + ret = 0; + } + + return ret; +} + +/* + * End event trigger parsing helper functions. + */ + /** - * event_trigger_callback - Generic event_command @func implementation + * event_trigger_parse - Generic event_command @parse implementation * @cmd_ops: The command ops, used for trigger registration * @file: The trace_event_file associated with the event * @glob: The raw string used to register the trigger @@ -632,15 +972,15 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, * Common implementation for event command parsing and trigger * instantiation. * - * Usually used directly as the @func method in event command + * Usually used directly as the @parse method in event command * implementations. * * Return: 0 on success, errno otherwise */ static int -event_trigger_callback(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param) +event_trigger_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param) { struct event_trigger_data *trigger_data; struct event_trigger_ops *trigger_ops; @@ -673,7 +1013,7 @@ event_trigger_callback(struct event_command *cmd_ops, INIT_LIST_HEAD(&trigger_data->named_list); if (glob[0] == '!') { - cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + cmd_ops->unreg(glob+1, trigger_data, file); kfree(trigger_data); ret = 0; goto out; @@ -708,14 +1048,14 @@ event_trigger_callback(struct event_command *cmd_ops, out_reg: /* Up the trigger_data count to make sure reg doesn't free it on failure */ event_trigger_init(trigger_ops, trigger_data); - ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); + ret = cmd_ops->reg(glob, trigger_data, file); /* * The above returns on success the # of functions enabled, * but if it didn't find any functions it returns zero. * Consider no functions a failure too. */ if (!ret) { - cmd_ops->unreg(glob, trigger_ops, trigger_data, file); + cmd_ops->unreg(glob, trigger_data, file); ret = -ENOENT; } else if (ret > 0) ret = 0; @@ -1023,28 +1363,28 @@ traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, } static struct event_trigger_ops traceon_trigger_ops = { - .func = traceon_trigger, + .trigger = traceon_trigger, .print = traceon_trigger_print, .init = event_trigger_init, .free = event_trigger_free, }; static struct event_trigger_ops traceon_count_trigger_ops = { - .func = traceon_count_trigger, + .trigger = traceon_count_trigger, .print = traceon_trigger_print, .init = event_trigger_init, .free = event_trigger_free, }; static struct event_trigger_ops traceoff_trigger_ops = { - .func = traceoff_trigger, + .trigger = traceoff_trigger, .print = traceoff_trigger_print, .init = event_trigger_init, .free = event_trigger_free, }; static struct event_trigger_ops traceoff_count_trigger_ops = { - .func = traceoff_count_trigger, + .trigger = traceoff_count_trigger, .print = traceoff_trigger_print, .init = event_trigger_init, .free = event_trigger_free, @@ -1069,7 +1409,7 @@ onoff_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_traceon_cmd = { .name = "traceon", .trigger_type = ETT_TRACE_ONOFF, - .func = event_trigger_callback, + .parse = event_trigger_parse, .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, @@ -1080,7 +1420,7 @@ static struct event_command trigger_traceoff_cmd = { .name = "traceoff", .trigger_type = ETT_TRACE_ONOFF, .flags = EVENT_CMD_FL_POST_TRIGGER, - .func = event_trigger_callback, + .parse = event_trigger_parse, .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = onoff_get_trigger_ops, @@ -1116,14 +1456,14 @@ snapshot_count_trigger(struct event_trigger_data *data, } static int -register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, +register_snapshot_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { if (tracing_alloc_snapshot_instance(file->tr) != 0) return 0; - return register_trigger(glob, ops, data, file); + return register_trigger(glob, data, file); } static int @@ -1135,14 +1475,14 @@ snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, } static struct event_trigger_ops snapshot_trigger_ops = { - .func = snapshot_trigger, + .trigger = snapshot_trigger, .print = snapshot_trigger_print, .init = event_trigger_init, .free = event_trigger_free, }; static struct event_trigger_ops snapshot_count_trigger_ops = { - .func = snapshot_count_trigger, + .trigger = snapshot_count_trigger, .print = snapshot_trigger_print, .init = event_trigger_init, .free = event_trigger_free, @@ -1157,7 +1497,7 @@ snapshot_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_snapshot_cmd = { .name = "snapshot", .trigger_type = ETT_SNAPSHOT, - .func = event_trigger_callback, + .parse = event_trigger_parse, .reg = register_snapshot_trigger, .unreg = unregister_trigger, .get_trigger_ops = snapshot_get_trigger_ops, @@ -1226,14 +1566,14 @@ stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, } static struct event_trigger_ops stacktrace_trigger_ops = { - .func = stacktrace_trigger, + .trigger = stacktrace_trigger, .print = stacktrace_trigger_print, .init = event_trigger_init, .free = event_trigger_free, }; static struct event_trigger_ops stacktrace_count_trigger_ops = { - .func = stacktrace_count_trigger, + .trigger = stacktrace_count_trigger, .print = stacktrace_trigger_print, .init = event_trigger_init, .free = event_trigger_free, @@ -1249,7 +1589,7 @@ static struct event_command trigger_stacktrace_cmd = { .name = "stacktrace", .trigger_type = ETT_STACKTRACE, .flags = EVENT_CMD_FL_POST_TRIGGER, - .func = event_trigger_callback, + .parse = event_trigger_parse, .reg = register_trigger, .unreg = unregister_trigger, .get_trigger_ops = stacktrace_get_trigger_ops, @@ -1353,36 +1693,36 @@ void event_enable_trigger_free(struct event_trigger_ops *ops, } static struct event_trigger_ops event_enable_trigger_ops = { - .func = event_enable_trigger, + .trigger = event_enable_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops event_enable_count_trigger_ops = { - .func = event_enable_count_trigger, + .trigger = event_enable_count_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops event_disable_trigger_ops = { - .func = event_enable_trigger, + .trigger = event_enable_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; static struct event_trigger_ops event_disable_count_trigger_ops = { - .func = event_enable_count_trigger, + .trigger = event_enable_count_trigger, .print = event_enable_trigger_print, .init = event_trigger_init, .free = event_enable_trigger_free, }; -int event_enable_trigger_func(struct event_command *cmd_ops, - struct trace_event_file *file, - char *glob, char *cmd, char *param) +int event_enable_trigger_parse(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, char *cmd, char *param) { struct trace_event_file *event_enable_file; struct enable_trigger_data *enable_data; @@ -1455,7 +1795,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, trigger_data->private_data = enable_data; if (glob[0] == '!') { - cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); + cmd_ops->unreg(glob+1, trigger_data, file); kfree(trigger_data); kfree(enable_data); ret = 0; @@ -1502,7 +1842,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, ret = trace_event_enable_disable(event_enable_file, 1, 1); if (ret < 0) goto out_put; - ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); + ret = cmd_ops->reg(glob, trigger_data, file); /* * The above returns on success the # of functions enabled, * but if it didn't find any functions it returns zero. @@ -1532,7 +1872,6 @@ int event_enable_trigger_func(struct event_command *cmd_ops, } int event_enable_register_trigger(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file) { @@ -1574,7 +1913,6 @@ out: } void event_enable_unregister_trigger(char *glob, - struct event_trigger_ops *ops, struct event_trigger_data *test, struct trace_event_file *file) { @@ -1628,7 +1966,7 @@ event_enable_get_trigger_ops(char *cmd, char *param) static struct event_command trigger_enable_cmd = { .name = ENABLE_EVENT_STR, .trigger_type = ETT_EVENT_ENABLE, - .func = event_enable_trigger_func, + .parse = event_enable_trigger_parse, .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, @@ -1638,7 +1976,7 @@ static struct event_command trigger_enable_cmd = { static struct event_command trigger_disable_cmd = { .name = DISABLE_EVENT_STR, .trigger_type = ETT_EVENT_ENABLE, - .func = event_enable_trigger_func, + .parse = event_enable_trigger_parse, .reg = event_enable_register_trigger, .unreg = event_enable_unregister_trigger, .get_trigger_ops = event_enable_get_trigger_ops, diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 56bb7b890578..d440ddd5fd8b 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -491,18 +491,14 @@ static void stop_per_cpu_kthreads(void) static int start_cpu_kthread(unsigned int cpu) { struct task_struct *kthread; - char comm[24]; - snprintf(comm, 24, "hwlatd/%d", cpu); - - kthread = kthread_create_on_cpu(kthread_fn, NULL, cpu, comm); + kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); return -ENOMEM; } per_cpu(hwlat_per_cpu_data, cpu).kthread = kthread; - wake_up_process(kthread); return 0; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 4e1257f50aa3..508f14af4f2c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -328,11 +328,9 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk) static void __disable_trace_kprobe(struct trace_probe *tp) { - struct trace_probe *pos; struct trace_kprobe *tk; - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tk = container_of(pos, struct trace_kprobe, tp); + list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) { if (!trace_kprobe_is_registered(tk)) continue; if (trace_kprobe_is_return(tk)) @@ -349,7 +347,7 @@ static void __disable_trace_kprobe(struct trace_probe *tp) static int enable_trace_kprobe(struct trace_event_call *call, struct trace_event_file *file) { - struct trace_probe *pos, *tp; + struct trace_probe *tp; struct trace_kprobe *tk; bool enabled; int ret = 0; @@ -370,8 +368,7 @@ static int enable_trace_kprobe(struct trace_event_call *call, if (enabled) return 0; - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tk = container_of(pos, struct trace_kprobe, tp); + list_for_each_entry(tk, trace_probe_probe_list(tp), tp.list) { if (trace_kprobe_has_gone(tk)) continue; ret = __enable_trace_kprobe(tk); @@ -560,11 +557,9 @@ static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig, struct trace_kprobe *comp) { struct trace_probe_event *tpe = orig->tp.event; - struct trace_probe *pos; int i; - list_for_each_entry(pos, &tpe->probes, list) { - orig = container_of(pos, struct trace_kprobe, tp); + list_for_each_entry(orig, &tpe->probes, tp.list) { if (strcmp(trace_kprobe_symbol(orig), trace_kprobe_symbol(comp)) || trace_kprobe_offset(orig) != trace_kprobe_offset(comp)) @@ -1176,15 +1171,18 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; struct trace_kprobe *tk; + unsigned long nmissed; if (!is_trace_kprobe(ev)) return 0; tk = to_trace_kprobe(ev); + nmissed = trace_kprobe_is_return(tk) ? + tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; seq_printf(m, " %-44s %15lu %15lu\n", trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), - tk->rp.kp.nmissed); + nmissed); return 0; } @@ -1384,17 +1382,11 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, if (trace_trigger_soft_disabled(trace_file)) return; - fbuffer.trace_ctx = tracing_gen_ctx(); - fbuffer.trace_file = trace_file; - dsize = __get_data_size(&tk->tp, regs); - fbuffer.event = - trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, - call->event.type, - sizeof(*entry) + tk->tp.size + dsize, - fbuffer.trace_ctx); - if (!fbuffer.event) + entry = trace_event_buffer_reserve(&fbuffer, trace_file, + sizeof(*entry) + tk->tp.size + dsize); + if (!entry) return; fbuffer.regs = regs; @@ -1431,16 +1423,11 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (trace_trigger_soft_disabled(trace_file)) return; - fbuffer.trace_ctx = tracing_gen_ctx(); - fbuffer.trace_file = trace_file; - dsize = __get_data_size(&tk->tp, regs); - fbuffer.event = - trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, - call->event.type, - sizeof(*entry) + tk->tp.size + dsize, - fbuffer.trace_ctx); - if (!fbuffer.event) + + entry = trace_event_buffer_reserve(&fbuffer, trace_file, + sizeof(*entry) + tk->tp.size + dsize); + if (!entry) return; fbuffer.regs = regs; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 7520d43aed55..870a08da5b48 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -138,8 +138,7 @@ static void osnoise_unregister_instance(struct trace_array *tr) if (!found) return; - synchronize_rcu(); - kfree(inst); + kvfree_rcu(inst); } /* @@ -1701,7 +1700,7 @@ static int start_kthread(unsigned int cpu) snprintf(comm, 24, "osnoise/%d", cpu); } - kthread = kthread_create_on_cpu(main, NULL, cpu, comm); + kthread = kthread_run_on_cpu(main, NULL, cpu, comm); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); @@ -1710,7 +1709,6 @@ static int start_kthread(unsigned int cpu) } per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread; - wake_up_process(kthread); return 0; } @@ -2123,6 +2121,13 @@ out_unhook_irq: return -EINVAL; } +static void osnoise_unhook_events(void) +{ + unhook_thread_events(); + unhook_softirq_events(); + unhook_irq_events(); +} + /* * osnoise_workload_start - start the workload and hook to events */ @@ -2155,7 +2160,14 @@ static int osnoise_workload_start(void) retval = start_per_cpu_kthreads(); if (retval) { - unhook_irq_events(); + trace_osnoise_callback_enabled = false; + /* + * Make sure that ftrace_nmi_enter/exit() see + * trace_osnoise_callback_enabled as false before continuing. + */ + barrier(); + + osnoise_unhook_events(); return retval; } @@ -2186,9 +2198,7 @@ static void osnoise_workload_stop(void) stop_per_cpu_kthreads(); - unhook_irq_events(); - unhook_softirq_events(); - unhook_thread_events(); + osnoise_unhook_events(); } static void osnoise_tracer_start(struct trace_array *tr) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3547e7176ff7..8aa493d25c73 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -445,14 +445,18 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) char irqs_off; int hardirq; int softirq; + int bh_off; int nmi; nmi = entry->flags & TRACE_FLAG_NMI; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + bh_off = entry->flags & TRACE_FLAG_BH_OFF; irqs_off = + (entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' : (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + bh_off ? 'b' : (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.'; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ed2a3f37297..73d90179b51b 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -356,6 +356,8 @@ static int __parse_imm_string(char *str, char **pbuf, int offs) return -EINVAL; } *pbuf = kstrndup(str, len - 1, GFP_KERNEL); + if (!*pbuf) + return -ENOMEM; return 0; } @@ -1138,8 +1140,7 @@ int trace_probe_remove_file(struct trace_probe *tp, return -ENOENT; list_del_rcu(&link->list); - synchronize_rcu(); - kfree(link); + kvfree_rcu(link); if (list_empty(&tp->event->files)) trace_probe_clear_flag(tp, TP_FLAG_TRACE); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 8bfcd3b09422..f755bde42fd0 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -323,8 +323,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) trace_ctx = tracing_gen_ctx(); - buffer = tr->array_buffer.buffer; - event = trace_buffer_lock_reserve(buffer, + event = trace_event_buffer_lock_reserve(&buffer, trace_file, sys_data->enter_event->event.type, size, trace_ctx); if (!event) return; @@ -367,8 +366,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) trace_ctx = tracing_gen_ctx(); - buffer = tr->array_buffer.buffer; - event = trace_buffer_lock_reserve(buffer, + event = trace_event_buffer_lock_reserve(&buffer, trace_file, sys_data->exit_event->event.type, sizeof(*entry), trace_ctx); if (!event) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 4f35514a48f3..9711589273cd 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -410,12 +410,10 @@ static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, struct trace_uprobe *comp) { struct trace_probe_event *tpe = orig->tp.event; - struct trace_probe *pos; struct inode *comp_inode = d_real_inode(comp->path.dentry); int i; - list_for_each_entry(pos, &tpe->probes, list) { - orig = container_of(pos, struct trace_uprobe, tp); + list_for_each_entry(orig, &tpe->probes, tp.list) { if (comp_inode != d_real_inode(orig->path.dentry) || comp->offset != orig->offset) continue; @@ -950,8 +948,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; - struct trace_buffer *buffer; - struct ring_buffer_event *event; + struct trace_event_buffer fbuffer; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); @@ -966,12 +963,10 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; - event = trace_event_buffer_lock_reserve(&buffer, trace_file, - call->event.type, size, 0); - if (!event) + entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); + if (!entry) return; - entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); @@ -983,7 +978,7 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, memcpy(data, ucb->buf, tu->tp.size + dsize); - event_trigger_unlock_commit(trace_file, buffer, event, entry, 0); + trace_event_buffer_commit(&fbuffer); } /* uprobe handler */ @@ -1076,14 +1071,12 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) static void __probe_event_disable(struct trace_probe *tp) { - struct trace_probe *pos; struct trace_uprobe *tu; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tu = container_of(pos, struct trace_uprobe, tp); + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { if (!tu->inode) continue; @@ -1095,7 +1088,7 @@ static void __probe_event_disable(struct trace_probe *tp) static int probe_event_enable(struct trace_event_call *call, struct trace_event_file *file, filter_func_t filter) { - struct trace_probe *pos, *tp; + struct trace_probe *tp; struct trace_uprobe *tu; bool enabled; int ret; @@ -1130,8 +1123,7 @@ static int probe_event_enable(struct trace_event_call *call, if (ret) goto err_flags; - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tu = container_of(pos, struct trace_uprobe, tp); + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { ret = trace_uprobe_enable(tu, filter); if (ret) { __probe_event_disable(tp); @@ -1276,7 +1268,7 @@ static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, static int uprobe_perf_close(struct trace_event_call *call, struct perf_event *event) { - struct trace_probe *pos, *tp; + struct trace_probe *tp; struct trace_uprobe *tu; int ret = 0; @@ -1288,8 +1280,7 @@ static int uprobe_perf_close(struct trace_event_call *call, if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) return 0; - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tu = container_of(pos, struct trace_uprobe, tp); + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; @@ -1301,7 +1292,7 @@ static int uprobe_perf_close(struct trace_event_call *call, static int uprobe_perf_open(struct trace_event_call *call, struct perf_event *event) { - struct trace_probe *pos, *tp; + struct trace_probe *tp; struct trace_uprobe *tu; int err = 0; @@ -1313,8 +1304,7 @@ static int uprobe_perf_open(struct trace_event_call *call, if (trace_uprobe_filter_add(tu->tp.event->filter, event)) return 0; - list_for_each_entry(pos, trace_probe_probe_list(tp), list) { - tu = container_of(pos, struct trace_uprobe, tp); + list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); @@ -1620,6 +1610,11 @@ create_local_trace_uprobe(char *name, unsigned long offs, tu->path = path; tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); + if (!tu->filename) { + ret = -ENOMEM; + goto error; + } + init_trace_event_call(tu); ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index f00de83d0246..1d261fbe367b 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -38,11 +38,10 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); stats->ac_btime64 = btime; - if (thread_group_leader(tsk)) { + if (tsk->flags & PF_EXITING) stats->ac_exitcode = tsk->exit_code; - if (tsk->flags & PF_FORKNOEXEC) - stats->ac_flag |= AFORK; - } + if (thread_group_leader(tsk) && (tsk->flags & PF_FORKNOEXEC)) + stats->ac_flag |= AFORK; if (tsk->flags & PF_SUPERPRIV) stats->ac_flag |= ASU; if (tsk->flags & PF_DUMPCORE) diff --git a/kernel/ucount.c b/kernel/ucount.c index 7b32c356ebc5..65b597431c86 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -190,6 +190,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) kfree(new); } else { hlist_add_head(&new->node, hashent); + get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } @@ -210,6 +211,7 @@ void put_ucounts(struct ucounts *ucounts) if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); + put_user_ns(ucounts->ns); kfree(ucounts); } } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index ad912511a0c0..99afb88d2e85 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -740,6 +740,106 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, mutex_unlock(&watchdog_mutex); return err; } + +static const int sixty = 60; + +static struct ctl_table watchdog_sysctls[] = { + { + .procname = "watchdog", + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "watchdog_thresh", + .data = &watchdog_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog_thresh, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&sixty, + }, + { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, + .proc_handler = proc_nmi_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "watchdog_cpumask", + .data = &watchdog_cpumask_bits, + .maxlen = NR_CPUS, + .mode = 0644, + .proc_handler = proc_watchdog_cpumask, + }, +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + { + .procname = "soft_watchdog", + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR + { + .procname = "hardlockup_panic", + .data = &hardlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#ifdef CONFIG_SMP + { + .procname = "hardlockup_all_cpu_backtrace", + .data = &sysctl_hardlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif + {} +}; + +static void __init watchdog_sysctl_init(void) +{ + register_sysctl_init("kernel", watchdog_sysctls); +} +#else +#define watchdog_sysctl_init() do { } while (0) #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) @@ -753,4 +853,5 @@ void __init lockup_detector_init(void) if (!watchdog_nmi_probe()) nmi_watchdog_available = true; lockup_detector_setup(); + watchdog_sysctl_init(); } |