diff options
author | Vignesh Raghavendra <vigneshr@ti.com> | 2023-02-19 22:54:26 +0530 |
---|---|---|
committer | Vignesh Raghavendra <vigneshr@ti.com> | 2023-02-19 22:54:26 +0530 |
commit | b7d17caaf466f5d94253a20f5c92588f2eaef6a5 (patch) | |
tree | 9747e304b21e6f789134824facb57c4d92893b06 /kernel | |
parent | bf9eae98488c3bd7917a9a688bb82efba8e40369 (diff) | |
parent | 707c48210a5384a72c82655a37895b7e822755f2 (diff) |
Merge tag 'v5.10.168' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux into ti-linux-5.10.y-cicd
This is the 5.10.168 stable release
* tag 'v5.10.168' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux: (286 commits)
Linux 5.10.168
Fix page corruption caused by racy check in __free_pages
arm64: dts: meson-axg: Make mmc host controller interrupts level-sensitive
arm64: dts: meson-g12-common: Make mmc host controller interrupts level-sensitive
arm64: dts: meson-gx: Make mmc host controller interrupts level-sensitive
riscv: Fixup race condition on PG_dcache_clean in flush_icache_pte
ceph: flush cap releases when the session is flushed
usb: typec: altmodes/displayport: Fix probe pin assign check
usb: core: add quirk for Alcor Link AK9563 smartcard reader
btrfs: free device in btrfs_close_devices for a single device filesystem
net: USB: Fix wrong-direction WARNING in plusb.c
cifs: Fix use-after-free in rdata->read_into_pages()
pinctrl: intel: Restore the pins that used to be in Direct IRQ mode
spi: dw: Fix wrong FIFO level setting for long xfers
pinctrl: single: fix potential NULL dereference
pinctrl: aspeed: Fix confusing types in return value
ALSA: pci: lx6464es: fix a debug loop
selftests: forwarding: lib: quote the sysctl values
rds: rds_rm_zerocopy_callback() use list_first_entry()
net/mlx5: fw_tracer, Zero consumer index when reloading the tracer
...
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/verifier.c | 106 | ||||
-rw-r--r-- | kernel/exit.c | 72 | ||||
-rw-r--r-- | kernel/kcsan/kcsan-test.c | 7 | ||||
-rw-r--r-- | kernel/kcsan/report.c | 4 | ||||
-rw-r--r-- | kernel/module.c | 26 | ||||
-rw-r--r-- | kernel/panic.c | 90 | ||||
-rw-r--r-- | kernel/sched/core.c | 3 | ||||
-rw-r--r-- | kernel/sysctl.c | 11 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 6 | ||||
-rw-r--r-- | kernel/trace/trace.c | 5 | ||||
-rw-r--r-- | kernel/trace/trace.h | 1 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 2 | ||||
-rw-r--r-- | kernel/trace/trace_output.c | 3 |
13 files changed, 265 insertions, 71 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 232c93357b90..9e5f1ebe67d7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,6 +570,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static void scrub_spilled_slot(u8 *stype) +{ + if (*stype != STACK_INVALID) + *stype = STACK_MISC; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -1876,8 +1882,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -1900,8 +1904,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); @@ -2272,16 +2274,33 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, - int spi, struct bpf_reg_state *reg) + int spi, struct bpf_reg_state *reg, + int size) { int i; - state->stack[spi].spilled_ptr = *reg; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + copy_register_state(&state->stack[spi].spilled_ptr, reg); + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + + for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) + state->stack[spi].slot_type[i - 1] = STACK_SPILL; - for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_SPILL; + /* size < 8 bytes spill */ + for (; i; i--) + scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, @@ -2319,7 +2338,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } @@ -2329,7 +2350,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } - if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit @@ -2342,7 +2363,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -2354,7 +2375,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else { u8 type = STACK_MISC; @@ -2363,7 +2384,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -2570,35 +2591,56 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; - u8 *stype; + u8 *stype, type; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { - if (size != BPF_REG_SIZE) { + u8 spill_size = 1; + + for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) + spill_size++; + + if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } - if (dst_regno >= 0) { + + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + if (dst_regno < 0) + return 0; + + if (!(off % BPF_REG_SIZE) && size == spill_size) { + /* The earlier check_reg_arg() has decided the + * subreg_def for this insn. Save it first. + */ + s32 subreg_def = state->regs[dst_regno].subreg_def; + + copy_register_state(&state->regs[dst_regno], reg); + state->regs[dst_regno].subreg_def = subreg_def; + } else { + for (i = 0; i < size; i++) { + type = stype[(slot - i) % BPF_REG_SIZE]; + if (type == STACK_SPILL) + continue; + if (type == STACK_MISC) + continue; + verbose(env, "invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } mark_reg_unknown(env, state->regs, dst_regno); - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } - mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } - for (i = 1; i < BPF_REG_SIZE; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { - verbose(env, "corrupted spill memory\n"); - return -EACCES; - } - } if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -2617,8 +2659,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { - u8 type; - for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) @@ -4104,7 +4144,7 @@ static int check_stack_range_initialized( if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) - state->stack[spi].slot_type[j] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } @@ -5861,7 +5901,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -7115,7 +7155,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -7126,7 +7166,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -7946,7 +7986,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } diff --git a/kernel/exit.c b/kernel/exit.c index 8989e1d1f79b..bacdaf980933 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -64,11 +64,58 @@ #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> +#include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/mmu_context.h> +/* + * The default value should be high enough to not crash a system that randomly + * crashes its kernel from time to time, but low enough to at least not permit + * overflowing 32-bit refcounts or the ldsem writer count. + */ +static unsigned int oops_limit = 10000; + +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_exit_table[] = { + { + .procname = "oops_limit", + .data = &oops_limit, + .maxlen = sizeof(oops_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_exit_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_exit_table); + return 0; +} +late_initcall(kernel_exit_sysctls_init); +#endif + +static atomic_t oops_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); +} + +static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); + +static __init int kernel_exit_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_exit_sysfs_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -863,6 +910,31 @@ void __noreturn do_exit(long code) } EXPORT_SYMBOL_GPL(do_exit); +void __noreturn make_task_dead(int signr) +{ + /* + * Take the task off the cpu after something catastrophic has + * happened. + */ + unsigned int limit; + + /* + * Every time the system oopses, if the oops happens while a reference + * to an object was held, the reference leaks. + * If the oops doesn't also leak memory, repeated oopsing can cause + * reference counters to wrap around (if they're not using refcount_t). + * This means that repeated oopsing can make unexploitable-looking bugs + * exploitable through repeated oopsing. + * To make sure this can't happen, place an upper bound on how often the + * kernel may oops without panic(). + */ + limit = READ_ONCE(oops_limit); + if (atomic_inc_return(&oops_count) >= limit && limit) + panic("Oopsed too often (kernel.oops_limit is %d)", limit); + + do_exit(signr); +} + void complete_and_exit(struct completion *comp, long code) { if (comp) diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan-test.c index ebe7fd245104..8a8ccaf4f38f 100644 --- a/kernel/kcsan/kcsan-test.c +++ b/kernel/kcsan/kcsan-test.c @@ -149,7 +149,7 @@ static bool report_matches(const struct expect_report *r) const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; bool ret = false; unsigned long flags; - typeof(observed.lines) expect; + typeof(*observed.lines) *expect; const char *end; char *cur; int i; @@ -158,6 +158,10 @@ static bool report_matches(const struct expect_report *r) if (!report_available()) return false; + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + /* Generate expected report contents. */ /* Title */ @@ -241,6 +245,7 @@ static bool report_matches(const struct expect_report *r) strstr(observed.lines[2], expect[1]))); out: spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); return ret; } diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c index d3bf87e6007c..069830f5a5d2 100644 --- a/kernel/kcsan/report.c +++ b/kernel/kcsan/report.c @@ -630,8 +630,8 @@ void kcsan_report(const volatile void *ptr, size_t size, int access_type, bool reported = value_change != KCSAN_VALUE_CHANGE_FALSE && print_report(value_change, type, &ai, other_info); - if (reported && panic_on_warn) - panic("panic_on_warn set ...\n"); + if (reported) + check_panic_on_warn("KCSAN"); release_report(&flags, other_info); } diff --git a/kernel/module.c b/kernel/module.c index 6a0fd245c048..33d1dc6d4cd6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3661,7 +3661,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; @@ -3827,20 +3828,35 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; -again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); diff --git a/kernel/panic.c b/kernel/panic.c index 332736a72a58..bc39e2b27d31 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -31,6 +31,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <linux/sysfs.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 @@ -41,7 +42,9 @@ * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; @@ -54,6 +57,7 @@ bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; +static unsigned int warn_limit __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -70,6 +74,56 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_panic_table[] = { +#ifdef CONFIG_SMP + { + .procname = "oops_all_cpu_backtrace", + .data = &sysctl_oops_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif + { + .procname = "warn_limit", + .data = &warn_limit, + .maxlen = sizeof(warn_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_panic_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_panic_table); + return 0; +} +late_initcall(kernel_panic_sysctls_init); +#endif + +static atomic_t warn_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); +} + +static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); + +static __init int kernel_panic_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_panic_sysfs_init); +#endif + static long no_blink(int state) { return 0; @@ -166,6 +220,19 @@ static void panic_print_sys_info(void) ftrace_dump(DUMP_ALL); } +void check_panic_on_warn(const char *origin) +{ + unsigned int limit; + + if (panic_on_warn) + panic("%s: panic_on_warn set ...\n", origin); + + limit = READ_ONCE(warn_limit); + if (atomic_inc_return(&warn_count) >= limit && limit) + panic("%s: system warned too often (kernel.warn_limit is %d)", + origin, limit); +} + /** * panic - halt the system * @fmt: The text string to print @@ -183,6 +250,16 @@ void panic(const char *fmt, ...) int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; + if (panic_on_warn) { + /* + * This thread may hit another WARN() in the panic path. + * Resetting this prevents additional WARN() from panicking the + * system on this thread. Other threads are blocked by the + * panic_mutex in panic(). + */ + panic_on_warn = 0; + } + /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since @@ -594,16 +671,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (regs) show_regs(regs); - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; - panic("panic_on_warn set ...\n"); - } + check_panic_on_warn("kernel"); if (!regs) dump_stack(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a875bc59804e..1303a2607f1f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4280,8 +4280,7 @@ static noinline void __schedule_bug(struct task_struct *prev) pr_err("Preemption disabled at:"); print_ip_sym(KERN_ERR, preempt_disable_ip); } - if (panic_on_warn) - panic("scheduling while atomic\n"); + check_panic_on_warn("scheduling while atomic"); dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3eb527f8a269..d8b7b2846313 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2199,17 +2199,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_SMP - { - .procname = "oops_all_cpu_backtrace", - .data = &sysctl_oops_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ { .procname = "pid_max", .data = &pid_max, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a9e074769881..94e51d36fb49 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1055,6 +1055,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -1072,6 +1073,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; + /* Task should not be pid=1 to avoid kernel panic. */ + if (unlikely(is_global_init(current))) + return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, @@ -1088,7 +1092,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c7c92b0eed04..8637eab2986e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8569,9 +8569,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; @@ -9680,6 +9677,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8d67f7f44840..37f616bf5fa9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1673,6 +1673,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0ae3e4454ff2..ccc99cd23f3c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1646,6 +1646,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, unsigned long fl = flags & ~HIST_FIELD_FL_LOG2; hist_field->fn = hist_field_log2; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 000e9dc224c6..b3ee8d9b6b62 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1378,7 +1378,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1396,4 +1396,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); |