diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 4 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 21 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 48 | ||||
| -rw-r--r-- | kernel/configs/kvm_guest.config | 1 | ||||
| -rw-r--r-- | kernel/events/core.c | 2 | ||||
| -rw-r--r-- | kernel/fork.c | 3 | ||||
| -rw-r--r-- | kernel/irq/matrix.c | 2 | ||||
| -rw-r--r-- | kernel/kexec_file.c | 2 | ||||
| -rw-r--r-- | kernel/stackleak.c | 132 | ||||
| -rw-r--r-- | kernel/sysctl.c | 16 | ||||
| -rw-r--r-- | kernel/trace/blktrace.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace_printk.c | 2 |
12 files changed, 180 insertions, 57 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 7a63d567fdb5..7343b3a9bff0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -117,6 +117,10 @@ obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o +KASAN_SANITIZE_stackleak.o := n +KCOV_INSTRUMENT_stackleak.o := n + $(obj)/configs.o: $(obj)/config_data.h targets += config_data.gz diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 171a2c88e77d..1971ca325fb4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2852,10 +2852,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || fn->ret_type == RET_PTR_TO_MAP_VALUE) { - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - else - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -2868,7 +2864,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; - regs[BPF_REG_0].id = ++env->id_gen; + if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; + } else { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; + } } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { int id = acquire_reference_state(env, insn_idx); if (id < 0) @@ -3046,7 +3047,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off @@ -3076,10 +3077,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_SUB: @@ -3108,7 +3110,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known @@ -3134,11 +3136,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_AND: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8b79318810ad..6aaf5dd5383b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -493,7 +493,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, } /** - * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * @@ -502,8 +502,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ -static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, - struct cgroup_subsys *ss) +static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); @@ -524,35 +524,6 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, } /** - * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem - * @cgrp: the cgroup of interest - * @ss: the subsystem of interest - * - * Find and get the effective css of @cgrp for @ss. The effective css is - * defined as the matching css of the nearest ancestor including self which - * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, - * the root css is returned, so this function always returns a valid css. - * - * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. - */ -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, - struct cgroup_subsys *ss) -{ - struct cgroup_subsys_state *css; - - do { - css = cgroup_css(cgrp, ss); - - if (css) - return css; - cgrp = cgroup_parent(cgrp); - } while (cgrp); - - return init_css_set.subsys[ss->id]; -} - -/** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest @@ -634,11 +605,10 @@ EXPORT_SYMBOL_GPL(of_css); * * Should be called under cgroup_[tree_]mutex. */ -#define for_each_e_css(css, ssid, cgrp) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((css) = cgroup_e_css_by_mask(cgrp, \ - cgroup_subsys[(ssid)]))) \ - ; \ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ + ; \ else /** @@ -1037,7 +1007,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ - template[i] = cgroup_e_css_by_mask(cgrp, ss); + template[i] = cgroup_e_css(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want @@ -3054,7 +3024,7 @@ static int cgroup_apply_control(struct cgroup *cgrp) return ret; /* - * At this point, cgroup_e_css_by_mask() results reflect the new csses + * At this point, cgroup_e_css() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config index 108fecc20fc1..208481d91090 100644 --- a/kernel/configs/kvm_guest.config +++ b/kernel/configs/kvm_guest.config @@ -20,6 +20,7 @@ CONFIG_PARAVIRT=y CONFIG_KVM_GUEST=y CONFIG_S390_GUEST=y CONFIG_VIRTIO=y +CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BLK=y CONFIG_VIRTIO_CONSOLE=y diff --git a/kernel/events/core.c b/kernel/events/core.c index 8c490130c4fb..84530ab358c3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -750,7 +750,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) __update_cgrp_time(event->cgrp); } diff --git a/kernel/fork.c b/kernel/fork.c index 8f82a3bdcb8f..07cddff89c7b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -91,6 +91,7 @@ #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> +#include <linux/stackleak.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -1926,6 +1927,8 @@ static __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; + stackleak_task_init(p); + if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 6e6d467f3dec..1f0985adf193 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -8,7 +8,7 @@ #include <linux/cpu.h> #include <linux/irq.h> -#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long)) +#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS)) struct cpumap { unsigned int available; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c6a3b6851372..35cf0ad29718 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -25,8 +25,6 @@ #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/kernel.h> -#include <linux/kexec.h> -#include <linux/slab.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> #include "kexec_internal.h" diff --git a/kernel/stackleak.c b/kernel/stackleak.c new file mode 100644 index 000000000000..e42892926244 --- /dev/null +++ b/kernel/stackleak.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code fills the used part of the kernel stack with a poison value + * before returning to userspace. It's part of the STACKLEAK feature + * ported from grsecurity/PaX. + * + * Author: Alexander Popov <alex.popov@linux.com> + * + * STACKLEAK reduces the information which kernel stack leak bugs can + * reveal and blocks some uninitialized stack variable attacks. + */ + +#include <linux/stackleak.h> + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include <linux/jump_label.h> +#include <linux/sysctl.h> + +static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); + +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); + int prev_state = state; + + table->data = &state; + table->maxlen = sizeof(int); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + state = !!state; + if (ret || !write || state == prev_state) + return ret; + + if (state) + static_branch_disable(&stack_erasing_bypass); + else + static_branch_enable(&stack_erasing_bypass); + + pr_warn("stackleak: kernel stack erasing is %s\n", + state ? "enabled" : "disabled"); + return ret; +} + +#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) +#else +#define skip_erasing() false +#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ + +asmlinkage void stackleak_erase(void) +{ + /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ + unsigned long kstack_ptr = current->lowest_stack; + unsigned long boundary = (unsigned long)end_of_stack(current); + unsigned int poison_count = 0; + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + + if (skip_erasing()) + return; + + /* Check that 'lowest_stack' value is sane */ + if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) + kstack_ptr = boundary; + + /* Search for the poison value in the kernel stack */ + while (kstack_ptr > boundary && poison_count <= depth) { + if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON) + poison_count++; + else + poison_count = 0; + + kstack_ptr -= sizeof(unsigned long); + } + + /* + * One 'long int' at the bottom of the thread stack is reserved and + * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y). + */ + if (kstack_ptr == boundary) + kstack_ptr += sizeof(unsigned long); + +#ifdef CONFIG_STACKLEAK_METRICS + current->prev_lowest_stack = kstack_ptr; +#endif + + /* + * Now write the poison value to the kernel stack. Start from + * 'kstack_ptr' and move up till the new 'boundary'. We assume that + * the stack pointer doesn't change when we write poison. + */ + if (on_thread_stack()) + boundary = current_stack_pointer; + else + boundary = current_top_of_stack(); + + while (kstack_ptr < boundary) { + *(unsigned long *)kstack_ptr = STACKLEAK_POISON; + kstack_ptr += sizeof(unsigned long); + } + + /* Reset the 'lowest_stack' value for the next syscall */ + current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; +} + +void __used stackleak_track_stack(void) +{ + /* + * N.B. stackleak_erase() fills the kernel stack with the poison value, + * which has the register width. That code assumes that the value + * of 'lowest_stack' is aligned on the register width boundary. + * + * That is true for x86 and x86_64 because of the kernel stack + * alignment on these platforms (for details, see 'cc_stack_align' in + * arch/x86/Makefile). Take care of that when you port STACKLEAK to + * new platforms. + */ + unsigned long sp = (unsigned long)&sp; + + /* + * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than + * STACKLEAK_SEARCH_DEPTH makes the poison search in + * stackleak_erase() unreliable. Let's prevent that. + */ + BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH); + + if (sp < current->lowest_stack && + sp >= (unsigned long)task_stack_page(current) + + sizeof(unsigned long)) { + current->lowest_stack = sp; + } +} +EXPORT_SYMBOL(stackleak_track_stack); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cc02050fd0c4..5fc724e4e454 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -66,7 +66,6 @@ #include <linux/kexec.h> #include <linux/bpf.h> #include <linux/mount.h> -#include <linux/pipe_fs_i.h> #include <linux/uaccess.h> #include <asm/processor.h> @@ -91,7 +90,9 @@ #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 @@ -1233,6 +1234,17 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { } }; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fac0ddf8a8e2..2868d85f1fb1 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_blkg) + if (!bio->bi_css) return NULL; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_get_kernfs_id(bio->bi_css->cgroup); } #else static union kernfs_node_id * diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index b0875b327f5c..c3fd849d4a8f 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -115,7 +115,7 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self, * section, then we need to read the link list pointers. The trick is * we pass the address of the string to the seq function just like * we do for the kernel core formats. To get back the structure that - * holds the format, we simply use containerof() and then go to the + * holds the format, we simply use container_of() and then go to the * next format in the list. */ static const char ** |