diff options
Diffstat (limited to 'kernel')
33 files changed, 1433 insertions, 1080 deletions
diff --git a/kernel/bounds.c b/kernel/bounds.c index c373e887c066..9795d75b09b2 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -13,7 +13,7 @@ #include <linux/log2.h> #include <linux/spinlock_types.h> -void foo(void) +int main(void) { /* The enum constants to put into include/generated/bounds.h */ DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); @@ -23,4 +23,6 @@ void foo(void) #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ + + return 0; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 378cef70341c..ee4c82667d65 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2067,56 +2067,47 @@ static int btf_check_sec_info(struct btf_verifier_env *env, return 0; } -static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, - u32 btf_data_size) +static int btf_parse_hdr(struct btf_verifier_env *env) { + u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; - u32 hdr_len, hdr_copy; - /* - * Minimal part of the "struct btf_header" that - * contains the hdr_len. - */ - struct btf_min_header { - u16 magic; - u8 version; - u8 flags; - u32 hdr_len; - } __user *min_hdr; struct btf *btf; int err; btf = env->btf; - min_hdr = btf_data; + btf_data_size = btf->data_size; - if (btf_data_size < sizeof(*min_hdr)) { + if (btf_data_size < + offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } - if (get_user(hdr_len, &min_hdr->hdr_len)) - return -EFAULT; - + hdr = btf->data; + hdr_len = hdr->hdr_len; if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } - err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); - if (err) { - if (err == -E2BIG) - btf_verifier_log(env, "Unsupported btf_header"); - return err; + /* Ensure the unsupported header fields are zero */ + if (hdr_len > sizeof(btf->hdr)) { + u8 *expected_zero = btf->data + sizeof(btf->hdr); + u8 *end = btf->data + hdr_len; + + for (; expected_zero < end; expected_zero++) { + if (*expected_zero) { + btf_verifier_log(env, "Unsupported btf_header"); + return -E2BIG; + } + } } hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); - if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) - return -EFAULT; + memcpy(&btf->hdr, btf->data, hdr_copy); hdr = &btf->hdr; - if (hdr->hdr_len != hdr_len) - return -EINVAL; - btf_verifier_log_hdr(env, btf_data_size); if (hdr->magic != BTF_MAGIC) { @@ -2186,10 +2177,6 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, } env->btf = btf; - err = btf_parse_hdr(env, btf_data, btf_data_size); - if (err) - goto errout; - data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; @@ -2198,13 +2185,18 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; - btf->nohdr_data = btf->data + btf->hdr.hdr_len; if (copy_from_user(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + err = btf_parse_str_sec(env); if (err) goto errout; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7c7eeea8cffc..6377225b2082 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,10 +365,13 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) } #ifdef CONFIG_BPF_JIT +# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000) + /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; +int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -577,27 +580,64 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; } +static atomic_long_t bpf_jit_current; + +#if defined(MODULES_VADDR) +static int __init bpf_jit_charge_init(void) +{ + /* Only used as heuristic here to derive limit. */ + bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2, + PAGE_SIZE), INT_MAX); + return 0; +} +pure_initcall(bpf_jit_charge_init); +#endif + +static int bpf_jit_charge_modmem(u32 pages) +{ + if (atomic_long_add_return(pages, &bpf_jit_current) > + (bpf_jit_limit >> PAGE_SHIFT)) { + if (!capable(CAP_SYS_ADMIN)) { + atomic_long_sub(pages, &bpf_jit_current); + return -EPERM; + } + } + + return 0; +} + +static void bpf_jit_uncharge_modmem(u32 pages) +{ + atomic_long_sub(pages, &bpf_jit_current); +} + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; - unsigned int size, hole, start; + u32 size, hole, start, pages; /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); + pages = size / PAGE_SIZE; + + if (bpf_jit_charge_modmem(pages)) + return NULL; hdr = module_alloc(size); - if (hdr == NULL) + if (!hdr) { + bpf_jit_uncharge_modmem(pages); return NULL; + } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); - hdr->pages = size / PAGE_SIZE; + hdr->pages = pages; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -610,7 +650,10 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { + u32 pages = hdr->pages; + module_memfree(hdr); + bpf_jit_uncharge_modmem(pages); } /* This symbol is only overridden by archs that have different diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 141710b82a6c..191b79948424 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -512,8 +512,7 @@ static int dev_map_notification(struct notifier_block *notifier, struct bpf_dtab_netdev *dev, *odev; dev = READ_ONCE(dtab->netdev_map[i]); - if (!dev || - dev->dev->ifindex != netdev->ifindex) + if (!dev || netdev != dev->dev) continue; odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); if (dev == odev) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ab0d5e3f9892..a74972b07e74 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -99,7 +99,6 @@ BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) const struct bpf_func_proto bpf_map_pop_elem_proto = { .func = bpf_map_pop_elem, .gpl_only = false, - .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, @@ -113,7 +112,6 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) const struct bpf_func_proto bpf_map_peek_elem_proto = { .func = bpf_map_pop_elem, .gpl_only = false, - .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 12a93fb37449..8bbd72d3a121 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -122,6 +122,7 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete) raw_spin_lock_irqsave(&qs->lock, flags); if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); err = -ENOENT; goto out; } @@ -151,6 +152,7 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete) raw_spin_lock_irqsave(&qs->lock, flags); if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); err = -ENOENT; goto out; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98fa0be35370..171a2c88e77d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1387,21 +1387,24 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, enum bpf_access_type t) { switch (env->prog->type) { + /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: - /* dst_input() and dst_output() can't write for now */ + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; /* fallthrough */ + + /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - case BPF_PROG_TYPE_FLOW_DISSECTOR: if (meta) return meta->pkt_access; @@ -5706,7 +5709,11 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) bool is_narrower_load; u32 target_size; - if (ops->gen_prologue) { + if (ops->gen_prologue || env->seen_direct_write) { + if (!ops->gen_prologue) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index f14c376937e5..22a12ab5a5e9 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -4,7 +4,7 @@ * * DMA operations that map physical memory directly without using an IOMMU. */ -#include <linux/bootmem.h> /* for max_pfn */ +#include <linux/memblock.h> /* for max_pfn */ #include <linux/export.h> #include <linux/mm.h> #include <linux/dma-direct.h> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ebecaf255ea2..5731daa09a32 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -40,7 +40,7 @@ #include <asm/dma.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/iommu-helper.h> #define CREATE_TRACE_POINTS @@ -204,10 +204,10 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. */ - io_tlb_list = memblock_virt_alloc( + io_tlb_list = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), PAGE_SIZE); - io_tlb_orig_addr = memblock_virt_alloc( + io_tlb_orig_addr = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { @@ -242,7 +242,7 @@ swiotlb_init(int verbose) bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ - vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + vstart = memblock_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a97f34bc14c..8c490130c4fb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8376,30 +8376,39 @@ static struct pmu perf_tracepoint = { * * PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe * if not set, create kprobe/uprobe + * + * The following values specify a reference counter (or semaphore in the + * terminology of tools like dtrace, systemtap, etc.) Userspace Statically + * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset. + * + * PERF_UPROBE_REF_CTR_OFFSET_BITS # of bits in config as th offset + * PERF_UPROBE_REF_CTR_OFFSET_SHIFT # of bits to shift left */ enum perf_probe_config { PERF_PROBE_CONFIG_IS_RETPROBE = 1U << 0, /* [k,u]retprobe */ + PERF_UPROBE_REF_CTR_OFFSET_BITS = 32, + PERF_UPROBE_REF_CTR_OFFSET_SHIFT = 64 - PERF_UPROBE_REF_CTR_OFFSET_BITS, }; PMU_FORMAT_ATTR(retprobe, "config:0"); +#endif -static struct attribute *probe_attrs[] = { +#ifdef CONFIG_KPROBE_EVENTS +static struct attribute *kprobe_attrs[] = { &format_attr_retprobe.attr, NULL, }; -static struct attribute_group probe_format_group = { +static struct attribute_group kprobe_format_group = { .name = "format", - .attrs = probe_attrs, + .attrs = kprobe_attrs, }; -static const struct attribute_group *probe_attr_groups[] = { - &probe_format_group, +static const struct attribute_group *kprobe_attr_groups[] = { + &kprobe_format_group, NULL, }; -#endif -#ifdef CONFIG_KPROBE_EVENTS static int perf_kprobe_event_init(struct perf_event *event); static struct pmu perf_kprobe = { .task_ctx_nr = perf_sw_context, @@ -8409,7 +8418,7 @@ static struct pmu perf_kprobe = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, - .attr_groups = probe_attr_groups, + .attr_groups = kprobe_attr_groups, }; static int perf_kprobe_event_init(struct perf_event *event) @@ -8441,6 +8450,24 @@ static int perf_kprobe_event_init(struct perf_event *event) #endif /* CONFIG_KPROBE_EVENTS */ #ifdef CONFIG_UPROBE_EVENTS +PMU_FORMAT_ATTR(ref_ctr_offset, "config:32-63"); + +static struct attribute *uprobe_attrs[] = { + &format_attr_retprobe.attr, + &format_attr_ref_ctr_offset.attr, + NULL, +}; + +static struct attribute_group uprobe_format_group = { + .name = "format", + .attrs = uprobe_attrs, +}; + +static const struct attribute_group *uprobe_attr_groups[] = { + &uprobe_format_group, + NULL, +}; + static int perf_uprobe_event_init(struct perf_event *event); static struct pmu perf_uprobe = { .task_ctx_nr = perf_sw_context, @@ -8450,12 +8477,13 @@ static struct pmu perf_uprobe = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, - .attr_groups = probe_attr_groups, + .attr_groups = uprobe_attr_groups, }; static int perf_uprobe_event_init(struct perf_event *event) { int err; + unsigned long ref_ctr_offset; bool is_retprobe; if (event->attr.type != perf_uprobe.type) @@ -8471,7 +8499,8 @@ static int perf_uprobe_event_init(struct perf_event *event) return -EOPNOTSUPP; is_retprobe = event->attr.config & PERF_PROBE_CONFIG_IS_RETPROBE; - err = perf_uprobe_init(event, is_retprobe); + ref_ctr_offset = event->attr.config >> PERF_UPROBE_REF_CTR_OFFSET_SHIFT; + err = perf_uprobe_init(event, ref_ctr_offset, is_retprobe); if (err) return err; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2bf792d22087..96d4bee83489 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -73,6 +73,7 @@ struct uprobe { struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; + loff_t ref_ctr_offset; unsigned long flags; /* @@ -88,6 +89,15 @@ struct uprobe { struct arch_uprobe arch; }; +struct delayed_uprobe { + struct list_head list; + struct uprobe *uprobe; + struct mm_struct *mm; +}; + +static DEFINE_MUTEX(delayed_uprobe_lock); +static LIST_HEAD(delayed_uprobe_list); + /* * Execute out of line area: anonymous executable mapping installed * by the probed task to execute the copy of the original instruction @@ -282,6 +292,166 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t return 1; } +static struct delayed_uprobe * +delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct delayed_uprobe *du; + + list_for_each_entry(du, &delayed_uprobe_list, list) + if (du->uprobe == uprobe && du->mm == mm) + return du; + return NULL; +} + +static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct delayed_uprobe *du; + + if (delayed_uprobe_check(uprobe, mm)) + return 0; + + du = kzalloc(sizeof(*du), GFP_KERNEL); + if (!du) + return -ENOMEM; + + du->uprobe = uprobe; + du->mm = mm; + list_add(&du->list, &delayed_uprobe_list); + return 0; +} + +static void delayed_uprobe_delete(struct delayed_uprobe *du) +{ + if (WARN_ON(!du)) + return; + list_del(&du->list); + kfree(du); +} + +static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct list_head *pos, *q; + struct delayed_uprobe *du; + + if (!uprobe && !mm) + return; + + list_for_each_safe(pos, q, &delayed_uprobe_list) { + du = list_entry(pos, struct delayed_uprobe, list); + + if (uprobe && du->uprobe != uprobe) + continue; + if (mm && du->mm != mm) + continue; + + delayed_uprobe_delete(du); + } +} + +static bool valid_ref_ctr_vma(struct uprobe *uprobe, + struct vm_area_struct *vma) +{ + unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset); + + return uprobe->ref_ctr_offset && + vma->vm_file && + file_inode(vma->vm_file) == uprobe->inode && + (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && + vma->vm_start <= vaddr && + vma->vm_end > vaddr; +} + +static struct vm_area_struct * +find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct vm_area_struct *tmp; + + for (tmp = mm->mmap; tmp; tmp = tmp->vm_next) + if (valid_ref_ctr_vma(uprobe, tmp)) + return tmp; + + return NULL; +} + +static int +__update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) +{ + void *kaddr; + struct page *page; + struct vm_area_struct *vma; + int ret; + short *ptr; + + if (!vaddr || !d) + return -EINVAL; + + ret = get_user_pages_remote(NULL, mm, vaddr, 1, + FOLL_WRITE, &page, &vma, NULL); + if (unlikely(ret <= 0)) { + /* + * We are asking for 1 page. If get_user_pages_remote() fails, + * it may return 0, in that case we have to return error. + */ + return ret == 0 ? -EBUSY : ret; + } + + kaddr = kmap_atomic(page); + ptr = kaddr + (vaddr & ~PAGE_MASK); + + if (unlikely(*ptr + d < 0)) { + pr_warn("ref_ctr going negative. vaddr: 0x%lx, " + "curr val: %d, delta: %d\n", vaddr, *ptr, d); + ret = -EINVAL; + goto out; + } + + *ptr += d; + ret = 0; +out: + kunmap_atomic(kaddr); + put_page(page); + return ret; +} + +static void update_ref_ctr_warn(struct uprobe *uprobe, + struct mm_struct *mm, short d) +{ + pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " + "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", + d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, + (unsigned long long) uprobe->offset, + (unsigned long long) uprobe->ref_ctr_offset, mm); +} + +static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, + short d) +{ + struct vm_area_struct *rc_vma; + unsigned long rc_vaddr; + int ret = 0; + + rc_vma = find_ref_ctr_vma(uprobe, mm); + + if (rc_vma) { + rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset); + ret = __update_ref_ctr(mm, rc_vaddr, d); + if (ret) + update_ref_ctr_warn(uprobe, mm, d); + + if (d > 0) + return ret; + } + + mutex_lock(&delayed_uprobe_lock); + if (d > 0) + ret = delayed_uprobe_add(uprobe, mm); + else + delayed_uprobe_remove(uprobe, mm); + mutex_unlock(&delayed_uprobe_lock); + + return ret; +} + /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for @@ -302,9 +472,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { + struct uprobe *uprobe; struct page *old_page, *new_page; struct vm_area_struct *vma; - int ret; + int ret, is_register, ref_ctr_updated = 0; + + is_register = is_swbp_insn(&opcode); + uprobe = container_of(auprobe, struct uprobe, arch); retry: /* Read the page with vaddr into memory */ @@ -317,6 +491,15 @@ retry: if (ret <= 0) goto put_old; + /* We are going to replace instruction, update ref_ctr. */ + if (!ref_ctr_updated && uprobe->ref_ctr_offset) { + ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); + if (ret) + goto put_old; + + ref_ctr_updated = 1; + } + ret = anon_vma_prepare(vma); if (ret) goto put_old; @@ -337,6 +520,11 @@ put_old: if (unlikely(ret == -EAGAIN)) goto retry; + + /* Revert back reference counter if instruction update failed. */ + if (ret && is_register && ref_ctr_updated) + update_ref_ctr(uprobe, mm, -1); + return ret; } @@ -378,8 +566,15 @@ static struct uprobe *get_uprobe(struct uprobe *uprobe) static void put_uprobe(struct uprobe *uprobe) { - if (atomic_dec_and_test(&uprobe->ref)) + if (atomic_dec_and_test(&uprobe->ref)) { + /* + * If application munmap(exec_vma) before uprobe_unregister() + * gets called, we don't get a chance to remove uprobe from + * delayed_uprobe_list from remove_breakpoint(). Do it here. + */ + delayed_uprobe_remove(uprobe, NULL); kfree(uprobe); + } } static int match_uprobe(struct uprobe *l, struct uprobe *r) @@ -484,7 +679,18 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe) return u; } -static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) +static void +ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe) +{ + pr_warn("ref_ctr_offset mismatch. inode: 0x%lx offset: 0x%llx " + "ref_ctr_offset(old): 0x%llx ref_ctr_offset(new): 0x%llx\n", + uprobe->inode->i_ino, (unsigned long long) uprobe->offset, + (unsigned long long) cur_uprobe->ref_ctr_offset, + (unsigned long long) uprobe->ref_ctr_offset); +} + +static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, + loff_t ref_ctr_offset) { struct uprobe *uprobe, *cur_uprobe; @@ -494,6 +700,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = inode; uprobe->offset = offset; + uprobe->ref_ctr_offset = ref_ctr_offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); @@ -501,6 +708,12 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) cur_uprobe = insert_uprobe(uprobe); /* a uprobe exists for this inode:offset combination */ if (cur_uprobe) { + if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) { + ref_ctr_mismatch_warn(cur_uprobe, uprobe); + put_uprobe(cur_uprobe); + kfree(uprobe); + return ERR_PTR(-EINVAL); + } kfree(uprobe); uprobe = cur_uprobe; } @@ -895,7 +1108,7 @@ EXPORT_SYMBOL_GPL(uprobe_unregister); * else return 0 (success) */ static int __uprobe_register(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc) + loff_t ref_ctr_offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; @@ -912,9 +1125,12 @@ static int __uprobe_register(struct inode *inode, loff_t offset, return -EINVAL; retry: - uprobe = alloc_uprobe(inode, offset); + uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (!uprobe) return -ENOMEM; + if (IS_ERR(uprobe)) + return PTR_ERR(uprobe); + /* * We can race with uprobe_unregister()->delete_uprobe(). * Check uprobe_is_active() and retry if it is false. @@ -938,10 +1154,17 @@ static int __uprobe_register(struct inode *inode, loff_t offset, int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { - return __uprobe_register(inode, offset, uc); + return __uprobe_register(inode, offset, 0, uc); } EXPORT_SYMBOL_GPL(uprobe_register); +int uprobe_register_refctr(struct inode *inode, loff_t offset, + loff_t ref_ctr_offset, struct uprobe_consumer *uc) +{ + return __uprobe_register(inode, offset, ref_ctr_offset, uc); +} +EXPORT_SYMBOL_GPL(uprobe_register_refctr); + /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. @@ -1060,6 +1283,35 @@ static void build_probe_list(struct inode *inode, spin_unlock(&uprobes_treelock); } +/* @vma contains reference counter, not the probed instruction. */ +static int delayed_ref_ctr_inc(struct vm_area_struct *vma) +{ + struct list_head *pos, *q; + struct delayed_uprobe *du; + unsigned long vaddr; + int ret = 0, err = 0; + + mutex_lock(&delayed_uprobe_lock); + list_for_each_safe(pos, q, &delayed_uprobe_list) { + du = list_entry(pos, struct delayed_uprobe, list); + + if (du->mm != vma->vm_mm || + !valid_ref_ctr_vma(du->uprobe, vma)) + continue; + + vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset); + ret = __update_ref_ctr(vma->vm_mm, vaddr, 1); + if (ret) { + update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1); + if (!err) + err = ret; + } + delayed_uprobe_delete(du); + } + mutex_unlock(&delayed_uprobe_lock); + return err; +} + /* * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * @@ -1072,7 +1324,15 @@ int uprobe_mmap(struct vm_area_struct *vma) struct uprobe *uprobe, *u; struct inode *inode; - if (no_uprobe_events() || !valid_vma(vma, true)) + if (no_uprobe_events()) + return 0; + + if (vma->vm_file && + (vma->vm_flags & (VM_WRITE|VM_S |