diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 19 | ||||
-rw-r--r-- | kernel/bpf/disasm.c | 16 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 150 | ||||
-rw-r--r-- | kernel/cgroup/cgroup-v1.c | 4 | ||||
-rw-r--r-- | kernel/dma/ops_helpers.c | 12 | ||||
-rw-r--r-- | kernel/smpboot.c | 2 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c | 10 | ||||
-rw-r--r-- | kernel/time/timer.c | 8 | ||||
-rw-r--r-- | kernel/ucount.c | 10 | ||||
-rw-r--r-- | kernel/workqueue.c | 20 |
10 files changed, 120 insertions, 131 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9b1577498373..b1a5fc04492b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,8 @@ #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> + +#include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ @@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, @@ -1621,7 +1624,21 @@ out: COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP - /* STX and ST and LDX*/ + /* ST, STX and LDX*/ + ST_NOSPEC: + /* Speculation barrier for mitigating Speculative Store Bypass. + * In case of arm64, we rely on the firmware mitigation as + * controlled via the ssbd kernel parameter. Whenever the + * mitigation is enabled, it works for all of the kernel code + * with no need to provide any additional instructions here. + * In case of x86, we use 'lfence' insn for mitigation. We + * reuse preexisting logic from Spectre v1 mitigation that + * happens to produce the required code on x86 for v4 as well. + */ +#ifdef CONFIG_X86 + barrier_nospec(); +#endif + CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index bbfc6bb79240..ca3cd9aaa6ce 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_%02x\n", insn->code); } } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) == BPF_MEM) { + verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { + verbose(cbs->private_data, "(%02x) nospec\n", insn->code); + } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); - return; } - verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42a4063de7cd..f9bda5476ea5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; + if (!env->bypass_spec_v4) { + bool sanitize = reg && is_spillable_regtype(reg->type); + + for (i = 0; i < size; i++) { + if (state->stack[spi].slot_type[i] == STACK_INVALID) { + sanitize = true; + break; + } + } + + if (sanitize) + env->insn_aux_data[insn_idx].sanitize_stack_spill = true; + } if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { @@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "invalid size of register spill\n"); return -EACCES; } - if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - - if (!env->bypass_spec_v4) { - bool sanitize = false; - - if (state->stack[spi].slot_type[0] == STACK_SPILL && - register_is_const(&state->stack[spi].spilled_ptr)) - sanitize = true; - for (i = 0; i < BPF_REG_SIZE; i++) - if (state->stack[spi].slot_type[i] == STACK_MISC) { - sanitize = true; - break; - } - if (sanitize) { - int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; - int soff = (-spi - 1) * BPF_REG_SIZE; - - /* detected reuse of integer stack slot with a pointer - * which means either llvm is reusing stack slot or - * an attacker is trying to exploit CVE-2018-3639 - * (speculative store bypass) - * Have to sanitize that slot with preemptive - * store of zero. - */ - if (*poff && *poff != soff) { - /* disallow programs where single insn stores - * into two different stack slots, since verifier - * cannot sanitize them - */ - verbose(env, - "insn %d cannot access two stack slots fp%d and fp%d", - insn_idx, *poff, soff); - return -EINVAL; - } - *poff = soff; - } - } save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; @@ -3677,6 +3653,8 @@ continue_func: if (tail_call_reachable) for (j = 0; j < frame; j++) subprog[ret_prog[j]].tail_call_reachable = true; + if (subprog[0].tail_call_reachable) + env->prog->aux->tail_call_reachable = true; /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT @@ -6559,6 +6537,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + /* Limit pruning on unknown scalars to enable deep search for + * potential masking differences from other program paths. + */ + if (!off_is_imm) + env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); @@ -9934,8 +9918,8 @@ next: } /* Returns true if (rold safe implies rcur safe) */ -static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct bpf_id_pair *idmap) +static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, + struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { bool equal; @@ -9961,6 +9945,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; switch (rold->type) { case SCALAR_VALUE: + if (env->explore_alu_limits) + return false; if (rcur->type == SCALAR_VALUE) { if (!rold->precise && !rcur->precise) return true; @@ -10051,9 +10037,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } -static bool stacksafe(struct bpf_func_state *old, - struct bpf_func_state *cur, - struct bpf_id_pair *idmap) +static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, + struct bpf_func_state *cur, struct bpf_id_pair *idmap) { int i, spi; @@ -10098,9 +10083,8 @@ static bool stacksafe(struct bpf_func_state *old, continue; if (old->stack[spi].slot_type[0] != STACK_SPILL) continue; - if (!regsafe(&old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, - idmap)) + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -10157,10 +10141,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) - if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + if (!regsafe(env, &old->regs[i], &cur->regs[i], + env->idmap_scratch)) return false; - if (!stacksafe(old, cur, env->idmap_scratch)) + if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; if (!refsafe(old, cur)) @@ -11904,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; + bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || - insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) + insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; - else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || - insn->code == (BPF_STX | BPF_MEM | BPF_H) || - insn->code == (BPF_STX | BPF_MEM | BPF_W) || - insn->code == (BPF_STX | BPF_MEM | BPF_DW)) + ctx_access = true; + } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || + insn->code == (BPF_STX | BPF_MEM | BPF_H) || + insn->code == (BPF_STX | BPF_MEM | BPF_W) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW) || + insn->code == (BPF_ST | BPF_MEM | BPF_B) || + insn->code == (BPF_ST | BPF_MEM | BPF_H) || + insn->code == (BPF_ST | BPF_MEM | BPF_W) || + insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; - else + ctx_access = BPF_CLASS(insn->code) == BPF_STX; + } else { continue; + } if (type == BPF_WRITE && - env->insn_aux_data[i + delta].sanitize_stack_off) { + env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { - /* Sanitize suspicious stack slot with zero. - * There are no memory dependencies for this store, - * since it's only using frame pointer and immediate - * constant of zero - */ - BPF_ST_MEM(BPF_DW, BPF_REG_FP, - env->insn_aux_data[i + delta].sanitize_stack_off, - 0), - /* the original STX instruction will immediately - * overwrite the same stack slot with appropriate value - */ *insn, + BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); @@ -11946,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } + if (!ctx_access) + continue; + switch (env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) @@ -12750,37 +12736,6 @@ static void free_states(struct bpf_verifier_env *env) } } -/* The verifier is using insn_aux_data[] to store temporary data during - * verification and to store information for passes that run after the - * verification like dead code sanitization. do_check_common() for subprogram N - * may analyze many other subprograms. sanitize_insn_aux_data() clears all - * temporary data after do_check_common() finds that subprogram N cannot be - * verified independently. pass_cnt counts the number of times - * do_check_common() was run and insn->aux->seen tells the pass number - * insn_aux_data was touched. These variables are compared to clear temporary - * data from failed pass. For testing and experiments do_check_common() can be - * run multiple times even when prior attempt to verify is unsuccessful. - * - * Note that special handling is needed on !env->bypass_spec_v1 if this is - * ever called outside of error path with subsequent program rejection. - */ -static void sanitize_insn_aux_data(struct bpf_verifier_env *env) -{ - struct bpf_insn *insn = env->prog->insnsi; - struct bpf_insn_aux_data *aux; - int i, class; - - for (i = 0; i < env->prog->len; i++) { - class = BPF_CLASS(insn[i].code); - if (class != BPF_LDX && class != BPF_STX) - continue; - aux = &env->insn_aux_data[i]; - if (aux->seen != env->pass_cnt) - continue; - memset(aux, 0, offsetof(typeof(*aux), orig_idx)); - } -} - static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); @@ -12857,9 +12812,6 @@ out: if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); - if (ret) - /* clean aux data in case subprog was rejected */ - sanitize_insn_aux_data(env); return ret; } diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8d6bf56ed77a..de2c432dee20 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { - struct super_block *sb = fc->root->d_sb; - dput(fc->root); - deactivate_locked_super(sb); + fc_drop_locked(fc); ret = 1; } diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c index 910ae69cae77..af4a6ef48ce0 100644 --- a/kernel/dma/ops_helpers.c +++ b/kernel/dma/ops_helpers.c @@ -5,6 +5,13 @@ */ #include <linux/dma-map-ops.h> +static struct page *dma_common_vaddr_to_page(void *cpu_addr) +{ + if (is_vmalloc_addr(cpu_addr)) + return vmalloc_to_page(cpu_addr); + return virt_to_page(cpu_addr); +} + /* * Create scatter-list for the already allocated DMA buffer. */ @@ -12,7 +19,7 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct page *page = virt_to_page(cpu_addr); + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret; ret = sg_alloc_table(sgt, 1, GFP_KERNEL); @@ -32,6 +39,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + struct page *page = dma_common_vaddr_to_page(cpu_addr); int ret = -ENXIO; vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); @@ -43,7 +51,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return -ENXIO; return remap_pfn_range(vma, vma->vm_start, - page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff, + page_to_pfn(page) + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); #else return -ENXIO; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index e4163042c4d6..cf6acab78538 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -47,7 +47,7 @@ void __init idle_thread_set_boot_cpu(void) * * Creates the thread if it does not exist. */ -static inline void idle_init(unsigned int cpu) +static __always_inline void idle_init(unsigned int cpu) { struct task_struct *tsk = per_cpu(idle_threads, cpu); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 29a5e54e6e10..517be7fd175e 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -991,6 +991,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) if (!p) goto out; + /* Protect timer list r/w in arm_timer() */ + sighand = lock_task_sighand(p, &flags); + if (unlikely(sighand == NULL)) + goto out; + /* * Fetch the current sample and update the timer's expiry time. */ @@ -1001,11 +1006,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) bump_cpu_timer(timer, now); - /* Protect timer list r/w in arm_timer() */ - sighand = lock_task_sighand(p, &flags); - if (unlikely(sighand == NULL)) - goto out; - /* * Now re-arm for the new expiry time. */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 3fadb58fc9d7..9eb11c2209e5 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -207,6 +207,7 @@ struct timer_base { unsigned int cpu; bool next_expiry_recalc; bool is_idle; + bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; + base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } @@ -1582,6 +1584,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) } base->next_expiry_recalc = false; + base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); return next; } @@ -1633,7 +1636,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; - bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1646,7 +1648,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; - is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); /* * We have a fresh next event. Check whether we can forward the @@ -1664,7 +1665,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - if (!is_max_delta) + if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. @@ -1947,6 +1948,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->timers_pending = false; base->is_idle = false; } return 0; diff --git a/kernel/ucount.c b/kernel/ucount.c index 87799e2379bd..77be3bbe3cc4 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -160,6 +160,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; + long overflow; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -184,8 +185,12 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) return new; } } + overflow = atomic_add_negative(1, &ucounts->count); spin_unlock_irq(&ucounts_lock); - ucounts = get_ucounts(ucounts); + if (overflow) { + put_ucounts(ucounts); + return NULL; + } return ucounts; } @@ -193,8 +198,7 @@ void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - if (atomic_dec_and_test(&ucounts->count)) { - spin_lock_irqsave(&ucounts_lock, flags); + if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 50142fc08902..f148eacda55a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3676,15 +3676,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work) unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; - bool is_last; + bool is_last = false; - if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) - return; + /* + * when @pwq is not linked, it doesn't hold any reference to the + * @wq, and @wq is invalid to access. + */ + if (!list_empty(&pwq->pwqs_node)) { + if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) + return; - mutex_lock(&wq->mutex); - list_del_rcu(&pwq->pwqs_node); - is_last = list_empty(&wq->pwqs); - mutex_unlock(&wq->mutex); + mutex_lock(&wq->mutex); + list_del_rcu(&pwq->pwqs_node); + is_last = list_empty(&wq->pwqs); + mutex_unlock(&wq->mutex); + } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); |