// SPDX-License-Identifier: GPL-2.0+
/*
* User-space Probes (UProbes)
*
* Copyright (C) IBM Corporation, 2008-2012
* Authors:
* Srikar Dronamraju
* Jim Keniston
* Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
*/
#include <linux/kernel.h>
#include <linux/highmem.h>
#include <linux/pagemap.h> /* read_mapping_page */
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/export.h>
#include <linux/rmap.h> /* anon_vma_prepare */
#include <linux/mmu_notifier.h>
#include <linux/swap.h> /* folio_free_swap */
#include <linux/ptrace.h> /* user_enable_single_step */
#include <linux/kdebug.h> /* notifier mechanism */
#include <linux/percpu-rwsem.h>
#include <linux/task_work.h>
#include <linux/shmem_fs.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES)
#define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE
static struct rb_root uprobes_tree = RB_ROOT;
/*
* allows us to skip the uprobe_mmap if there are no uprobe events active
* at this time. Probably a fine grained per inode count is better?
*/
#define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree)
static DEFINE_RWLOCK(uprobes_treelock); /* serialize rbtree access */
static seqcount_rwlock_t uprobes_seqcount = SEQCNT_RWLOCK_ZERO(uprobes_seqcount, &uprobes_treelock);
DEFINE_STATIC_SRCU(uprobes_srcu);
#define UPROBES_HASH_SZ 13
/* serialize uprobe->pending_list */
static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
DEFINE_STATIC_PERCPU_RWSEM(dup_mmap_sem);
/* Have a copy of original instruction */
#define UPROBE_COPY_INSN 0
struct uprobe {
struct rb_node rb_node; /* node in the rb tree */
refcount_t ref;
struct rw_semaphore register_rwsem;
struct rw_semaphore consumer_rwsem;
struct list_head pending_list;
struct list_head consumers;
struct inode *inode; /* Also hold a ref to inode */
struct rcu_head rcu;
loff_t offset;
loff_t ref_ctr_offset;
unsigned long flags;
/*
* The generic code assumes that it has two members of unknown type
* owned by the arch-specific code:
*
* insn - copy_insn() saves the original instruction here for
* arch_uprobe_analyze_insn().
*
* ixol - potentially modified instruction to execute out of
* line, copied to xol_area by xol_get_insn_slot().
*/
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
* mangled by set_swbp().
*
* On a breakpoint hit, thread contests for a slot. It frees the
* slot after singlestep. Currently a fixed number of slots are
* allocated.
*/
struct xol_area {
wait_queue_head_t wq; /* if all slots are busy */
atomic_t slot_count; /* number of in-use slots */
unsigned long *bitmap; /* 0 = free slot */
struct page *page;
/*
* We keep the vma's vm_start rather than a pointer to the vma
* itself. The probed process or a naughty kernel module could make
* the vma go away, and we must handle that reasonably gracefully.
*/
unsigned long vaddr; /* Page(s) of instruction slots */
};
static void uprobe_warn(struct task_struct *t, const char *msg)
{
pr_warn("uprobe: %s:%d failed to %s\n", current->comm, current->pid, msg);
}
/*
* valid_vma: Verify if the specified vma is an executable vma
* Relax restrictions while unregistering: vm_flags might have
* changed after breakpoint was inserted.
* - is_register: indicates if we are in register context.
* - Return 1 if the specified virtual address is in an
* executable vma.
*/
static bool valid_vma(struct vm_area_struct *vma, bool is_register)
{
vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE;
if (is_register)
flags |= VM_WRITE;
return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC;
}
static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
{
return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
}
static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
{
return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start);
}
/**
* __replace_page - replace page in vma by new page.
* based on replace_page in mm/ksm.c
*
* @vma: vma that holds the pte pointing to page
* @addr: address the old @page is mapped at
* @old_page: the page we are replacing by new_page
* @new_page: the modified page we replace page by
*
* If @new_page is NULL, only unmap @old_page.
*
* Returns 0 on success, negative error code otherwise.
*/
static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
struct page *old_page, struct page *new_page)
{
struct folio *old_folio = page_folio(old_page);
struct folio *new_folio;
struct mm_struct *mm = vma->vm_mm;
DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
int err;
struct mmu_notifier_range range;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
addr + PAGE_SIZE);
if (new_page) {
new_folio = page_folio(new_page);
err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
if (err)
return err;
}
/* For folio_free_swap() below */
folio_lock(old_folio);
mmu_notifier_invalidate_range_start(&range);
err = -EAGAIN;
if (!page_vma_mapped_walk(&pvmw))
goto unlock;
VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
if (new_page) {
folio_get(new_folio);
folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE);
folio_add_lru_vma(new_folio, vma);
} else
/* no new page, just dec_mm_counter for old_page */
dec_mm_counter(mm, MM_ANONPAGES);
if (!folio_test_anon(old_folio)) {
dec_mm_counter(mm, mm_counter_file(old_folio));
inc_mm_counter(mm, MM_ANONPAGES);
}
flush_cache_page(vma, addr, pte_pfn(ptep_get(pvmw.pte)));
ptep_clear_flush(vma, addr, pvmw.pte);
if (new_page)
set_pte_at(mm, addr, pvmw.pte,
mk_pte(new_page, vma->vm_page_prot));
folio_remove_rmap_pte(old_folio, old_page, vma);
if (!folio_mapped(old_folio))
folio_free_swap(old_folio);
page_vma_mapped_walk_done(&pvmw);
folio_put(old_folio);
err = 0;
unlock:
mmu_notifier_invalidate_range_end(&range);
folio_unlock(old_folio);
return err;
}
/**
* is_swbp_insn - check if instruction is breakpoint instruction.
* @insn: instruction to be checked.
* Default implementation of is_swbp_insn
* Returns true if @insn is a breakpoint instruction.
*/
bool __weak is_swbp_insn(uprobe_opcode_t *insn)
{
return *insn == UPROBE_SWBP_INSN;
}
/**
* is_trap_insn - check if instruction is breakpoint instruction.
* @insn: instruction to be checked.
* Default implementation of is_trap_insn
* Returns true if @insn is a breakpoint instruction.
*
* This function is needed for the case where an architecture has multiple
* trap instructions (like powerpc).
*/
bool __weak is_trap_insn(uprobe_opcode_t *insn)
{
return is_swbp_insn(insn);
}
static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len)
{
void *kaddr = kmap_atomic(page);
memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len);
kunmap_atomic(kaddr);
}
static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len)
{
void *kaddr = kmap_atomic(page);
memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
kunmap_atomic(kaddr);
}
static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
{
uprobe_opcode_t old_opcode;
bool is_swbp;
/*
* Note: We only check if the old_opcode is UPROBE_SWBP_INSN here.
* We do not check if it is any other 'trap variant' which could
* be conditional trap instruction such as the one powerpc supports.
*
* The logic is that we do not care if the underlying instruction
* is a trap variant; uprobes always wins over any other (gdb)
* breakpoint.
*/
copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE);
is_swbp = is_swbp_insn(&old_opcode);
if (is_swbp_insn(new_opcode)) {
if (is_swbp) /* register: already installed? */
return 0;
} else {
if (!is_swbp) /* unregister: was it changed by us? */
return 0;
}
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)
{
VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *tmp;
for_each_vma(vmi, tmp)
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;
int ret;
short *ptr;
if (!vaddr || !d)
return -EINVAL;
ret = get_user_pages_remote(mm, vaddr, 1,
FOLL_WRITE, &page, 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
* the architecture. If an arch has variable length instruction and the
* breakpoint instruction is not of the smallest length instruction
* supported by that architecture then we need to modify is_trap_at_addr and
* uprobe_write_opcode accordingly. This would never be a problem for archs
* that have fixed length instructions.
*
* uprobe_write_opcode - write the opcode at a given virtual address.
* @auprobe: arch specific probepoint information.
* @mm: the probed process address space.
* @vaddr: the virtual address to store the opcode.
* @opcode: opcode to be written at @vaddr.
*
* Called with mm->mmap_lock held for read or write.
* Return 0 (success) or a negative errno.
*/
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, is_register, ref_ctr_updated = 0;
bool orig_page_huge = false;
unsigned int gup_flags = FOLL_FORCE;
is_register = is_swbp_insn(&opcode);
uprobe = container_of(auprobe, struct uprobe, arch);
retry:
if (is_register)
gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
if (IS_ERR(old_page))
return PTR_ERR(old_page);
ret = verify_opcode(old_page, vaddr, &opcode);
if (ret <= 0)
goto put_old;
if (WARN(!is_register && PageCompound(old_page),
"uprobe unregister should never work on compound page\n")) {
ret = -EINVAL;
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 = 0;
if (!is_register && !PageAnon(old_page))
goto put_old;
ret = anon_vma_prepare(vma);
if (ret)
goto put_old;
ret = -ENOMEM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
if (!new_page)
goto put_old;
__SetPageUptodate(new_page);
copy_highpage(new_page, old_page);
copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
if (!is_register) {
struct page *orig_page;
pgoff_t index;
VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
index);
if (orig_page) {
if (PageUptodate(orig_page) &&
pages_identical(new_page, orig_page)) {
/* let go new_page */
put_page(new_page);
new_page = NULL;
if (PageCompound(orig_page))
orig_page_huge = true;
}
put_page(orig_page);
}
}
ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
if (new_page)
put_page(new_page);
put_old:
put_page(old_page);
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);
/* try collapse pmd for compound page */
if (!ret && orig_page_huge)
collapse_pte_mapped_thp(mm, vaddr, false);
return ret;
}
/**
* set_swbp - store breakpoint at a given address.
* @auprobe: arch specific probepoint information.
* @mm: the probed process address space.
* @vaddr: the virtual address to insert the opcode.
*
* For mm @mm, store the breakpoint instruction at @vaddr.
* Return 0 (success) or a negative errno.
*/
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
}
/**
* set_orig_insn - Restore the original instruction.
* @mm: the probed process address space.
* @auprobe: arch specific probepoint information.
* @vaddr: the virtual address to insert the opcode.
*
* For mm @mm, restore the original opcode (opcode) at @vaddr.
* Return 0 (success) or a negative errno.
*/
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
return uprobe_write_opcode(auprobe, mm, vaddr,
*(uprobe_opcode_t *)&auprobe->insn);
}
/* uprobe should have guaranteed positive refcount */
static struct uprobe *get_uprobe(struct uprobe *uprobe)
{
refcount_inc(&uprobe->ref);
return uprobe;
}
/*
* uprobe should have guaranteed lifetime, which can be either of:
* - caller already has refcount taken (and wants an extra one);
* - uprobe is RCU protected and won't be freed until after grace period;
* - we are holding uprobes_treelock (for read or write, doesn't matter).
*/
static struct uprobe *try_get_uprobe(struct uprobe *uprobe)
{
if (refcount_inc_not_zero(&uprobe->ref))
return uprobe;
return NULL;
}
static inline bool uprobe_is_active(struct uprobe *uprobe)
{
return !RB_EMPTY_NODE(&uprobe->rb_node);
}
static void uprobe_free_rcu(struct rcu_head *rcu)
{
struct uprobe *uprobe = container_of(rcu, struct uprobe, rcu);
kfree(uprobe);
}
static void put_uprobe(struct uprobe *uprobe)
{
if (!refcount_dec_and_test(&uprobe->ref))
return;
write_lock(&uprobes_treelock);
if (uprobe_is_active(uprobe)) {
write_seqcount_begin(&uprobes_seqcount);
rb_erase(&uprobe->rb_node, &uprobes_tree);
write_seqcount_end(&uprobes_seqcount);
}
write_unlock(&uprobes_treelock);
/*
* 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.
*/
mutex_lock(&delayed_uprobe_lock);
delayed_uprobe_remove(uprobe, NULL);
mutex_unlock(&delayed_uprobe_lock);
call_srcu(&uprobes_srcu, &uprobe->rcu, uprobe_free_rcu);
}
static __always_inline
int uprobe_cmp(const struct inode *l_inode, const loff_t l_offset,
const struct uprobe *r)
{
if (l_inode < r->inode)
return -1;
if (l_inode > r->inode)
return 1;
if (l_offset < r->offset)
return -1;
if (l_offset > r->offset)
return 1;
return 0;
}
#define __node_2_uprobe(node) \
rb_entry((node), struct uprobe, rb_node)
struct __uprobe_key {
struct inode *inode;
loff_t offset;
};
static inline int __uprobe_cmp_key(const void *key, const struct rb_node *b)
{
const struct __uprobe_key *a = key;
return uprobe_cmp(a->inode, a->offset, __node_2_uprobe(b));
}
static inline int __uprobe_cmp(struct rb_node *a, const struct rb_node *b)
{
struct uprobe *u = __node_2_uprobe(a);
return uprobe_cmp(u->inode, u->offset, __node_2_uprobe(b));
}
/*
* Assumes being inside RCU protected region.
* No refcount is taken on returned uprobe.
*/
static struct uprobe *find_uprobe_rcu(struct inode *inode, loff_t offset)
{
struct __uprobe_key key = {
.inode = inode,
.offset = offset,
};
struct rb_node *node;
unsigned int seq;
lockdep_assert(srcu_read_lock_held(&uprobes_srcu));
do {
seq = read_seqcount_begin(&uprobes_seqcount);
node = rb_find_rcu(&key, &uprobes_tree, __uprobe_cmp_key);
/*
* Lockless RB-tree lookups can result only in false negatives.
* If the element is found, it is correct and can be returned
* under RCU protection. If we find nothing, we need to
* validate that seqcount didn't change. If it did, we have to
* try again as we might have missed the element (false
* negative). If seqcount is unchanged, search truly failed.
*/
if (node)
return __node_2_uprobe(node);
} while (read_seqcount_retry(&uprobes_seqcount, seq));
return NULL;
}
/*
* Attempt to insert a new uprobe into uprobes_tree.
*
* If uprobe already exists (for given inode+offset), we just increment
* refcount of previously existing uprobe.
*
* If not, a provided new instance of uprobe is inserted into the tree (with
* assumed initial refcount == 1).
*
* In any case, we return a uprobe instance that ends up being in uprobes_tree.
* Caller has to clean up new uprobe instance, if it ended up not being
* inserted into the tree.
*
* We assume that uprobes_treelock is held for writing.
*/
static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
{
struct rb_node *node;
again:
node = rb_find_add_rcu(&uprobe->rb_node, &uprobes_tree, __uprobe_cmp);
if (node) {
struct uprobe *u = __node_2_uprobe(node);
if (!try_get_uprobe(u)) {
rb_erase(node, &uprobes_tree);
RB_CLEAR_NODE(&u->rb_node);
goto again;
}
return u;
}
return uprobe;
}
/*
* Acquire uprobes_treelock and insert uprobe into uprobes_tree
* (or reuse existing one, see __insert_uprobe() comments above).
*/
static struct uprobe *insert_uprobe(struct uprobe *uprobe)
{
struct uprobe *u;
write_lock(&uprobes_treelock);
write_seqcount_begin(&uprobes_seqcount);
u = __insert_uprobe(uprobe);
write_seqcount_end(&uprobes_seqcount);
write_unlock(&uprobes_treelock);
return u;
}
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;
uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL);
if (!uprobe)
return ERR_PTR(-ENOMEM);
uprobe->inode = inode;
uprobe->offset = offset;
uprobe->ref_ctr_offset = ref_ctr_offset;
INIT_LIST_HEAD(&uprobe->consumers);
init_rwsem(&uprobe->register_rwsem);
init_rwsem(&uprobe->consumer_rwsem);
RB_CLEAR_NODE(&uprobe->rb_node);
refcount_set(&uprobe->ref, 1);
/* add to uprobes_tree, sorted on inode:offset */
cur_uprobe = insert_uprobe(uprobe);
/* a uprobe exists for this inode:offset combination */
if (cur_uprobe != 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;
}
return uprobe;
}
static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
down_write(&uprobe->consumer_rwsem);
list_add_rcu(&uc->cons_node, &uprobe->consumers);
up_write(&uprobe->consumer_rwsem);
}
/*
* For uprobe @uprobe, delete the consumer @uc.
* Should never be called with consumer that's not part of @uprobe->consumers.
*/
static void consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
down_write(&uprobe->consumer_rwsem);
list_del_rcu(&uc->cons_node);
up_write(&uprobe->consumer_rwsem);
}
static int __copy_insn(struct address_space *mapping, struct file *filp,
void *insn, int nbytes, loff_t offset)
{
struct page *page;
/*
* Ensure that the page that has the original instruction is populated
* and in page-cache. If ->read_folio == NULL it must be shmem_mapping(),
* see uprobe_register().
*/
if (mapping->a_ops->read_folio)
page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp);
else
page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
if (IS_ERR(page))
return PTR_ERR(page);
copy_from_page(page, offset, insn, nbytes);
put_page(page);
return 0;
}
static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
struct address_space *mapping = uprobe->inode->i_mapping;
loff_t offs = uprobe->offset;
void *insn = &uprobe->arch.insn;
int size = sizeof(uprobe->arch.insn);
int len, err = -EIO;
/* Copy only available bytes, -EIO if nothing was read */
do {
if (offs >= i_size_read(uprobe->inode))
break;
len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK));
err = __copy_insn(mapping, filp, insn, len, offs);
if (err)
break;
insn += len;
offs += len;
size -= len;
} while (size);
return err;
}
static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
struct mm_struct *mm, unsigned long vaddr)
{
int ret = 0;
if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
return ret;
/* TODO: move this into _register, until then we abuse this sem. */
down_write(&uprobe->consumer_rwsem);
if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
goto out;
ret = copy_insn(uprobe, file);
if (ret)
goto out;
ret = -ENOTSUPP;
if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
goto out;
ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
if (ret)
goto out;
smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
set_bit(UPROBE_COPY_INSN, &uprobe->flags);
out:
up_write(&uprobe->consumer_rwsem);
return ret;
}
static inline bool consumer_filter(struct uprobe_consumer *uc, struct mm_struct *mm)
{
return !uc->filter || uc->filter(uc, mm);
}
static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
{
struct uprobe_consumer *uc;
bool ret = false;
down_read(&uprobe->consumer_rwsem);
list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
srcu_read_lock_held(&uprobes_srcu)) {
ret = consumer_filter(uc, mm);
if (ret)
break;
}
up_read(&uprobe->consumer_rwsem);
return ret;
}
static int
install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long vaddr)
{
bool first_uprobe;
int ret;
ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
if (ret)
return ret;
/*
* set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
* the task can hit this breakpoint right after __replace_page().
*/
first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags);
if (first_uprobe)
set_bit(MMF_HAS_UPROBES, &mm->flags);
ret = set_swbp(&uprobe->arch, mm, vaddr);
if (!ret)
clear_bit(MMF_RECALC_UPROBES, &mm->flags);
else if (first_uprobe)
clear_bit(MMF_HAS_UPROBES, &mm->flags);
return ret;
}
static int
remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
{
set_bit(MMF_RECALC_UPROBES, &mm->flags);
return set_orig_insn(&uprobe->arch, mm, vaddr);
}
struct map_info {
struct map_info *next;
struct mm_struct *mm;
unsigned long vaddr;
};
static inline struct map_info *free_map_info(struct map_info *info)
{
struct map_info *next = info->next;
kfree(info);
return next;
}
static struct map_info *
build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
{
unsigned long pgoff = offset >> PAGE_SHIFT;
struct vm_area_struct *vma;
struct map_info *curr = NULL;
struct map_info *prev = NULL;
struct map_info *info;
int more = 0;
again:
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
if (!valid_vma(vma, is_register))
continue;
if (!prev && !more) {
/*
* Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through
* reclaim. This is optimistic, no harm done if it fails.
*/
prev = kmalloc(sizeof(struct map_info),
GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
if (prev)
prev->next = NULL;
}
if (!prev) {
more++;
continue;
}
if (!mmget_not_zero(vma->vm_mm))
continue;
info = prev;
prev = prev->next;
info->next = curr;
curr = info;
info->mm = vma->vm_mm;
info->vaddr = offset_to_vaddr(vma, offset);
}
i_mmap_unlock_read(mapping);
if (!more)
goto out;
prev = curr;
while (curr) {
mmput(curr->mm);
curr = curr->next;
}
do {
info = kmalloc(sizeof(struct map_info), GFP_KERNEL);
if (!info) {
curr = ERR_PTR(-ENOMEM);
goto out;
}
info->next = prev;
prev = info;
} while (--more);
goto again;
out:
while (prev)
prev = free_map_info(prev);
return curr;
}
static int
register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
{
bool is_register = !!new;
struct map_info *info;
int err = 0;
percpu_down_write(&dup_mmap_sem);
info = build_map_info(uprobe->inode->i_mapping,
uprobe->offset, is_register);
if (IS_ERR(info)) {
err = PTR_ERR(info);
goto out;
}
while (info) {
struct mm_struct *mm = info->mm;
struct vm_area_struct *vma;
if (err && is_register)
goto free;
/*
* We take mmap_lock for writing to avoid the race with
* find_active_uprobe_rcu() which takes mmap_lock for reading.
* Thus this install_breakpoint() can not make
* is_trap_at_addr() true right after find_uprobe_rcu()
* returns NULL in find_active_uprobe_rcu().
*/
mmap_write_lock(mm);
vma = find_vma(mm, info->vaddr);
if (!vma || !valid_vma(vma, is_register) ||
file_inode(vma->vm_file) != uprobe->inode)
goto unlock;
if (vma->vm_start > info->vaddr ||
vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
goto unlock;
if (is_register) {
/* consult only the "caller", new consumer. */
if (consumer_filter(new, mm))
err = install_breakpoint(uprobe, mm, vma, info->vaddr);
} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
if (!filter_chain(uprobe, mm))
err |= remove_breakpoint(uprobe, mm, info->vaddr);
}
unlock:
mmap_write_unlock(mm);
free:
mmput(mm);
info = free_map_info(info);
}
out:
percpu_up_write(&dup_mmap_sem);
return err;
}
/**
* uprobe_unregister_nosync - unregister an already registered probe.
* @uprobe: uprobe to remove
* @uc: identify which probe if multiple probes are colocated.
*/
void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
int err;
down_write(&uprobe->register_rwsem);
consumer_del(uprobe, uc);
err = register_for_each_vma(uprobe, NULL);
up_write(&uprobe->register_rwsem);
/* TODO : cant unregister? schedule a worker thread */
if (unlikely(err)) {
uprobe_warn(current, "unregister, leaking uprobe");
return;
}
put_uprobe(uprobe);
}
EXPORT_SYMBOL_GPL(uprobe_unregister_nosync);
void uprobe_unregister_sync(void)
{
/*
* Now that handler_chain() and handle_uretprobe_chain() iterate over
* uprobe->consumers list under RCU protection without holding
* uprobe->register_rwsem, we need to wait for RCU grace period to
* make sure that we can't call into just unregistered
* uprobe_consumer's callbacks anymore. If we don't do that, fast and
* unlucky enough caller can free consumer's memory and cause
* handler_chain() or handle_uretprobe_chain() to do an use-after-free.
*/
synchronize_srcu(&uprobes_srcu);
}
EXPORT_SYMBOL_GPL(uprobe_unregister_sync);
/**
* uprobe_register - register a probe
* @inode: the file in which the probe has to be placed.
* @offset: offset from the start of the file.
* @ref_ctr_offset: offset of SDT marker / reference counter
* @uc: information on howto handle the probe..
*
* Apart from the access refcount, uprobe_register() takes a creation
* refcount (thro alloc_uprobe) if and only if this @uprobe is getting
* inserted into the rbtree (i.e first consumer for a @inode:@offset
* tuple). Creation refcount stops uprobe_unregister from freeing the
* @uprobe even before the register operation is complete. Creation
* refcount is released when the last @uc for the @uprobe
* unregisters. Caller of uprobe_register() is required to keep @inode
* (and the containing mount) referenced.
*
* Return: pointer to the new uprobe on success or an ERR_PTR on failure.
*/
struct uprobe *uprobe_register(struct inode *inode,
loff_t offset, loff_t ref_ctr_offset,
struct uprobe_consumer *uc)
{
struct uprobe *uprobe;
int ret;
/* Uprobe must have at least one set consumer */
if (!uc->handler && !uc->ret_handler)
return ERR_PTR(-EINVAL);
/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
if (!inode->i_mapping->a_ops->read_folio &&
!shmem_mapping(inode->i_mapping))
return ERR_PTR(-EIO);
/* Racy, just to catch the obvious mistakes */
if (offset > i_size_read(inode))
return ERR_PTR(-EINVAL);
/*
* This ensures that copy_from_page(), copy_to_page() and
* __update_ref_ctr() can't cross page boundary.
*/
if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE))
return ERR_PTR(-EINVAL);
if (!IS_ALIGNED(ref_ctr_offset, sizeof(short)))
return ERR_PTR(-EINVAL);
uprobe = alloc_uprobe(inode, offset, ref_ctr_offset);
if (IS_ERR(uprobe))
return uprobe;
down_write(&uprobe->register_rwsem);
consumer_add(uprobe, uc);
ret = register_for_each_vma(uprobe, uc);
up_write(&uprobe->register_rwsem);
if (ret) {
uprobe_unregister_nosync(uprobe, uc);
/*
* Registration might have partially succeeded, so we can have
* this consumer being called right at this time. We need to
* sync here. It's ok, it's unlikely slow path.
*/
uprobe_unregister_sync();
return ERR_PTR(ret);
}
return uprobe;
}
EXPORT_SYMBOL_GPL(uprobe_register);
/**
* uprobe_apply - add or remove the breakpoints according to @uc->filter
* @uprobe: uprobe which "owns" the breakpoint
* @uc: consumer which wants to add more or remove some breakpoints
* @add: add or remove the breakpoints
* Return: 0 on success or negative error code.
*/
int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add)
{
struct uprobe_consumer *con;
int ret = -ENOENT, srcu_idx;
down_write(&uprobe->register_rwsem);
srcu_idx = srcu_read_lock(&uprobes_srcu);
list_for_each_entry_srcu(con, &uprobe->consumers, cons_node,
srcu_read_lock_held(&uprobes_srcu)) {
if (con == uc) {
ret = register_for_each_vma(uprobe, add ? uc : NULL);
break;
}
}
srcu_read_unlock(&uprobes_srcu, srcu_idx);
up_write(&uprobe->register_rwsem);
return ret;
}
static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
{
VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *vma;
int err = 0;
mmap_read_lock(mm);
for_each_vma(vmi, vma) {
unsigned long vaddr;
loff_t offset;
if (!valid_vma(vma, false) ||
file_inode(vma->vm_file) != uprobe->inode)
continue;
offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
if (uprobe->offset < offset ||
uprobe->offset >= offset + vma->vm_end - vma->vm_start)
continue;
vaddr = offset_to_vaddr(vma, uprobe->offset);
err |= remove_breakpoint(uprobe, mm, vaddr);
}
mmap_read_unlock(mm);
return err;
}
static struct rb_node *
find_node_in_range(struct inode *inode, loff_t min, loff_t max)
{
struct rb_node *n = uprobes_tree.rb_node;
while (n) {
struct uprobe *u = rb_entry(n, struct uprobe, rb_node);
if (inode < u->inode) {
n = n->rb_left;
} else if (inode > u->inode) {
n = n->rb_right;
} else {
if (max < u->offset)
n = n->rb_left;
else if (min > u->offset)
n = n->rb_right;
else
break;
}
}
return n;
}
/*
* For a given range in vma, build a list of probes that need to be inserted.
*/
static void build_probe_list(struct inode *inode,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct list_head *head)
{
loff_t min, max;
struct rb_node *n, *t;
struct uprobe *u;
INIT_LIST_HEAD(head);
min = vaddr_to_offset(vma, start);
max = min + (end - start) - 1;
read_lock(&uprobes_treelock);
n = find_node_in_range(inode, min, max);
if (n) {
for (t = n; t; t = rb_prev(t)) {
u = rb_entry(t, struct uprobe, rb_node);
if (u->inode != inode || u->offset < min)
break;
/* if uprobe went away, it's safe to ignore it */
if (try_get_uprobe(u))
list_add(&u->pending_list, head);
}
for (t = n; (t = rb_next(t)); ) {
u = rb_entry(t, struct uprobe, rb_node);
if (u->inode != inode || u->offset > max)
break;
/* if uprobe went away, it's safe to ignore it */
if (try_get_uprobe(u))
list_add(&u->pending_list, head);
}
}
read_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_merge with mm->mmap_lock acquired.
*
* Currently we ignore all errors and always return 0, the callers
* can't handle the failure anyway.
*/
int uprobe_mmap(struct vm_area_struct *vma)
{
struct list_head tmp_list;
struct uprobe *uprobe, *u;
struct inode *inode;
if (no_uprobe_events())
return 0;
if (vma->vm_file &&
(vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE &&
test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags))
delayed_ref_ctr_inc(vma);
if (!valid_vma(vma, true))
return 0;
inode = file_inode(vma->vm_file);
if (!inode)
return 0;
mutex_lock(uprobes_mmap_hash(inode));
build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
/*
* We can race with uprobe_unregister(), this uprobe can be already
* removed. But in this case filter_chain() must return false, all
* consumers have gone away.
*/
list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
if (!fatal_signal_pending(current) &&
filter_chain(uprobe, vma->vm_mm)) {
unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
}
put_uprobe(uprobe);
}
mutex_unlock(uprobes_mmap_hash(inode));
return 0;
}
static bool
vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
loff_t min, max;
struct inode *inode;
struct rb_node *n;
inode = file_inode(vma->vm_file);
min = vaddr_to_offset(vma, start);
max = min + (end - start) - 1;
read_lock(&uprobes_treelock);
n = find_node_in_range(inode, min, max);
read_unlock(&uprobes_treelock);
return !!n;
}
/*
* Called in context of a munmap of a vma.
*/
void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
if (no_uprobe_events() || !valid_vma(vma, false))
return;
if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
return;
if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) ||
test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags))
return;
if (vma_has_uprobes(vma, start, end))
set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags);
}
static vm_fault_t xol_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct xol_area *area = vma->vm_mm->uprobes_state.xol_area;
vmf->page = area->page;
get_page(vmf->page);
return 0;
}
static const struct vm_special_mapping xol_mapping = {
.name = "[uprobes]",
.fault = xol_fault,
};
/* Slot allocation for XOL */
static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
{
struct vm_area_struct *vma;
int ret;
if (mmap_write_lock_killable(mm))
return -EINTR;
if (mm->uprobes_state.xol_area) {
ret = -EALREADY;
goto fail;
}
if (!area->vaddr) {
/* Try to map as high as possible, this is only a hint. */
area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE,
PAGE_SIZE, 0, 0);
if (IS_ERR_VALUE(area->vaddr)) {
ret = area->vaddr;
goto fail;
}
}
vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE,
VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO,
&xol_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto fail;
}
ret = 0;
/* pairs with get_xol_area() */
smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */
fail:
mmap_write_unlock(mm);
return ret;
}
void * __weak arch_uprobe_trampoline(unsigned long *psize)
{
static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
*psize = UPROBE_SWBP_INSN_SIZE;
return &insn;
}
static struct xol_area *__create_xol_area(unsigned long vaddr)
{
struct mm_struct *mm = current->mm;
unsigned long insns_size;
struct xol_area *area;
void *insns;
area = kzalloc(sizeof(*area), GFP_KERNEL);
if (unlikely(!area))
goto out;
area->bitmap = kcalloc(BITS_TO_LONGS(UINSNS_PER_PAGE), sizeof(long),
GFP_KERNEL);
if (!area->bitmap)
goto free_area;
area->page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
if (!area->page)
goto free_bitmap;
area->vaddr = vaddr;
init_waitqueue_head(&area->wq);
/* Reserve the 1st slot for get_trampoline_vaddr() */
set_bit(0, area->bitmap);
atomic_set(&area->slot_count, 1);
insns = arch_uprobe_trampoline(&insns_size);
arch_uprobe_copy_ixol(area->page, 0, insns, insns_size);
if (!xol_add_vma(mm, area))
return area;
__free_page(area->page);
free_bitmap:
kfree(area->bitmap);
free_area:
kfree(area);
out:
return NULL;
}
/*
* get_xol_area - Allocate process's xol_area if necessary.
* This area will be used for storing instructions for execution out of line.
*
* Returns the allocated area or NULL.
*/
static struct xol_area *get_xol_area(void)
{
struct mm_struct *mm = current->mm;
struct xol_area *area;
if (!mm->uprobes_state.xol_area)
__create_xol_area(0);
/* Pairs with xol_add_vma() smp_store_release() */
area = READ_ONCE(mm->uprobes_state.xol_area); /* ^^^ */
return area;
}
/*
* uprobe_clear_state - Free the area allocated for slots.
*/
void uprobe_clear_state(struct mm_struct *mm)
{
struct xol_area *area = mm->uprobes_state.xol_area;
mutex_lock(&delayed_uprobe_lock);
delayed_uprobe_remove(NULL, mm);
mutex_unlock(&delayed_uprobe_lock);
if (!area)
return;
put_page(area->page);
kfree(area->bitmap);
kfree(area);
}
void uprobe_start_dup_mmap(void)
{
percpu_down_read(&dup_mmap_sem);
}
void uprobe_end_dup_mmap(void)
{
percpu_up_read(&dup_mmap_sem);
}
void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
{
if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) {
set_bit(MMF_HAS_UPROBES, &newmm->flags);
/* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */
set_bit(MMF_RECALC_UPROBES, &newmm->flags);
}
}
/*
* - search for a free slot.
*/
static unsigned long xol_take_insn_slot(struct xol_area *area)
{
unsigned long slot_addr;
int slot_nr;
do {
slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE);
if (slot_nr < UINSNS_PER_PAGE) {
if (!test_and_set_bit(slot_nr, area->bitmap))
break;
slot_nr = UINSNS_PER_PAGE;
continue;
}
wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE));
} while (slot_nr >= UINSNS_PER_PAGE);
slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES);
atomic_inc(&area->slot_count);
return slot_addr;
}
/*
* xol_get_insn_slot - allocate a slot for xol.
* Returns the allocated slot address or 0.
*/
static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
{
struct xol_area *area;
unsigned long xol_vaddr;
area = get_xol_area();
if (!area)
return 0;
xol_vaddr = xol_take_insn_slot(area);
if (unlikely(!xol_vaddr))
return 0;
arch_uprobe_copy_ixol(area->page, xol_vaddr,
&uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
return xol_vaddr;
}
/*
* xol_free_insn_slot - If slot was earlier allocated by
* @xol_get_insn_slot(), make the slot available for
* subsequent requests.
*/
static void xol_free_insn_slot(struct task_struct *tsk)
{
struct xol_area *area;
unsigned long vma_end;
unsigned long slot_addr;
if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask)
return;
slot_addr = tsk->utask->xol_vaddr;
if (unlikely(!slot_addr))
return;
area = tsk->mm->uprobes_state.xol_area;
vma_end = area->vaddr + PAGE_SIZE;
if (area->vaddr <= slot_addr && slot_addr < vma_end) {
unsigned long offset;
int slot_nr;
offset = slot_addr - area->vaddr;
slot_nr = offset / UPROBE_XOL_SLOT_BYTES;
if (slot_nr >= UINSNS_PER_PAGE)
return;
clear_bit(slot_nr, area->bitmap);
atomic_dec(&area->slot_count);
smp_mb__after_atomic(); /* pairs with prepare_to_wait() */
if (waitqueue_active(&area->wq))
wake_up(&area->wq);
tsk->utask->xol_vaddr = 0;
}
}
void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *src, unsigned long len)
{
/* Initialize the slot */
copy_to_page(page, vaddr, src, len);
/*
* We probably need flush_icache_user_page() but it needs vma.
* This should work on most of architectures by default. If
* architecture needs to do something different it can define
* its own version of the function.
*/
flush_dcache_page(page);
}
/**
* uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
* @regs: Reflects the saved state of the task after it has hit a breakpoint
* instruction.
* Return the address of the breakpoint instruction.
*/
unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
{
return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
}
unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
{
struct uprobe_task *utask = current->utask;
if (unlikely(utask && utask->active_uprobe))
return utask->vaddr;
return instruction_pointer(regs);
}
static struct return_instance *free_ret_instance(struct return_instance *ri)
{
struct return_instance *next = ri->next;
put_uprobe(ri->uprobe);
kfree(ri);
return next;
}
/*
* Called with no locks held.
* Called in context of an exiting or an exec-ing thread.
*/
void uprobe_free_utask(struct task_struct *t)
{
struct uprobe_task *utask = t->utask;
struct return_instance *ri;
if (!utask)
return;
if (utask->active_uprobe)
put_uprobe(utask->active_uprobe);
ri = utask->return_instances;
while (ri)
ri = free_ret_instance(ri);
xol_free_insn_slot(t);
kfree(utask);
t->utask = NULL;
}
/*
* Allocate a uprobe_task object for the task if necessary.
* Called when the thread hits a breakpoint.
*
* Returns:
* - pointer to new uprobe_task on success
* - NULL otherwise
*/
static struct uprobe_task *get_utask(void)
{
if (!current->utask)
current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
return current->utask;
}
static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask)
{
struct uprobe_task *n_utask;
struct return_instance **p, *o, *n;
n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
if (!n_utask)
return -ENOMEM;
t->utask = n_utask;
p = &n_utask->return_instances;
for (o = o_utask->return_instances; o; o = o->next) {
n = kmalloc(sizeof(struct return_instance), GFP_KERNEL);
if (!n)
return -ENOMEM;
*n = *o;
/*
* uprobe's refcnt has to be positive at this point, kept by
* utask->return_instances items; return_instances can't be
* removed right now, as task is blocked due to duping; so
* get_uprobe() is safe to use here.
*/
get_uprobe(n->uprobe);
n->next = NULL;
*p = n;
p = &n->next;
n_utask->depth++;
}
return 0;
}
static void dup_xol_work(struct callback_head *work)
{
if (current->flags & PF_EXITING)
return;
if (!__create_xol_area(current->utask->dup_xol_addr) &&
!fatal_signal_pending(current))
uprobe_warn(current, "dup xol area");
}
/*
* Called in context of a new clone/fork from copy_process.
*/
void uprobe_copy_process(struct task_struct *t, unsigned long flags)
{
struct uprobe_task *utask = current->utask;
struct mm_struct *mm = current->mm;
struct xol_area *area;
t->utask = NULL;
if (!utask || !utask->return_instances)
return;
if (mm == t->mm && !(flags & CLONE_VFORK))
return;
if (dup_utask(t, utask))
return uprobe_warn(t, "dup ret instances");
/* The task can fork() after dup_xol_work() fails */
area = mm->uprobes_state.xol_area;
if (!area)
return uprobe_warn(t, "dup xol area");
if (mm == t->mm)
return;
t->utask->dup_xol_addr = area->vaddr;
init_task_work(&t->utask->dup_xol_work, dup_xol_work);
task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME);
}
/*
* Current area->vaddr notion assume the trampoline address is always
* equal area->vaddr.
*
* Returns -1 in case the xol_area is not allocated.
*/
unsigned long uprobe_get_trampoline_vaddr(void)
{
struct xol_area *area;
unsigned long trampoline_vaddr = -1;
/* Pairs with xol_add_vma() smp_store_release() */
area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */
if (area)
trampoline_vaddr = area->vaddr;
return trampoline_vaddr;
}
static void cleanup_return_instances(struct uprobe_task *utask, bool chained,
struct pt_regs *regs)
{
struct return_instance *ri = utask->return_instances;
enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL;
while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) {
ri = free_ret_instance(ri);
utask->depth--;
}
utask->return_instances = ri;
}
static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
{
struct return_instance *ri;
struct uprobe_task *utask;
unsigned long orig_ret_vaddr, trampoline_vaddr;
bool chained;
if (!get_xol_area())
return;
utask = get_utask();
if (!utask)
return;
if (utask->depth >= MAX_URETPROBE_DEPTH) {
printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to"
" nestedness limit pid/tgid=%d/%d\n",
current->pid, current->tgid);
return;
}
/* we need to bump refcount to store uprobe in utask */
if (!try_get_uprobe(uprobe))
return;
ri = kmalloc(sizeof(struct return_instance), GFP_KERNEL);
if (!ri)
goto fail;
trampoline_vaddr = uprobe_get_trampoline_vaddr();
orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
if (orig_ret_vaddr == -1)
goto fail;
/* drop the entries invalidated by longjmp() */
chained = (orig_ret_vaddr == trampoline_vaddr);
cleanup_return_instances(utask, chained, regs);
/*
* We don't want to keep trampoline address in stack, rather keep the
* original return address of first caller thru all the consequent
* instances. This also makes breakpoint unwrapping easier.
*/
if (chained) {
if (!utask->return_instances) {
/*
* This situation is not possible. Likely we have an
* attack from user-space.
*/
uprobe_warn(current, "handle tail call");
goto fail;
}
orig_ret_vaddr = utask->return_instances->orig_ret_vaddr;
}
ri->uprobe = uprobe;
ri->func = instruction_pointer(regs);
ri->stack = user_stack_pointer(regs);
ri->orig_ret_vaddr = orig_ret_vaddr;
ri->chained = chained;
utask->depth++;
ri->next = utask->return_instances;
utask->return_instances = ri;
return;
fail:
kfree(ri);
put_uprobe(uprobe);
}
/* Prepare to single-step probed instruction out of line. */
static int
pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
{
struct uprobe_task *utask;
unsigned long xol_vaddr;
int err;
utask = get_utask();
if (!utask)
return -ENOMEM;
if (!try_get_uprobe(uprobe))
return -EINVAL;
xol_vaddr = xol_get_insn_slot(uprobe);
if (!xol_vaddr) {
err = -ENOMEM;
goto err_out;
}
utask->xol_vaddr = xol_vaddr;
utask->vaddr = bp_vaddr;
err = arch_uprobe_pre_xol(&uprobe->arch, regs);
if (unlikely(err)) {
xol_free_insn_slot(current);
goto err_out;
}
utask->active_uprobe = uprobe;
utask->state = UTASK_SSTEP;
return 0;
err_out:
put_uprobe(uprobe);
return err;
}
/*
* If we are singlestepping, then ensure this thread is not connected to
* non-fatal signals until completion of singlestep. When xol insn itself
* triggers the signal, restart the original insn even if the task is
* already SIGKILL'ed (since coredump should report the correct ip). This
* is even more important if the task has a handler for SIGSEGV/etc, The
* _same_ instruction should be repeated again after return from the signal
* handler, and SSTEP can never finish in this case.
*/
bool uprobe_deny_signal(void)
{
struct task_struct *t = current;
struct uprobe_task *utask = t->utask;
if (likely(!utask || !utask->active_uprobe))
return false;
WARN_ON_ONCE(utask->state != UTASK_SSTEP);
if (task_sigpending(t)) {
spin_lock_irq(&t->sighand->siglock);
clear_tsk_thread_flag(t, TIF_SIGPENDING);
spin_unlock_irq(&t->sighand->siglock);
if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
utask->state = UTASK_SSTEP_TRAPPED;
set_tsk_thread_flag(t, TIF_UPROBE);
}
}
return true;
}
static void mmf_recalc_uprobes(struct mm_struct *mm)
{
VMA_ITERATOR(vmi, mm, 0);
struct vm_area_struct *vma;
for_each_vma(vmi, vma) {
if (!valid_vma(vma, false))
continue;
/*
* This is not strictly accurate, we can race with
* uprobe_unregister() and see the already removed
* uprobe if delete_uprobe() was not yet called.
* Or this uprobe can be filtered out.
*/
if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
return;
}
clear_bit(MMF_HAS_UPROBES, &mm->flags);
}
static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
{
struct page *page;
uprobe_opcode_t opcode;
int result;
if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE)))
return -EINVAL;
pagefault_disable();
result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr);
pagefault_enable();
if (likely(result == 0))
goto out;
result = get_user_pages(vaddr, 1, FOLL_FORCE, &page);
if (result < 0)
return result;
copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
put_page(page);
out:
/* This needs to return true for any variant of the trap insn */
return is_trap_insn(&opcode);
}
/* assumes being inside RCU protected region */
static struct uprobe *find_active_uprobe_rcu(unsigned long bp_vaddr, int *is_swbp)
{
struct mm_struct *mm = current->mm;
struct uprobe *uprobe = NULL;
struct vm_area_struct *vma;
mmap_read_lock(mm);
vma = vma_lookup(mm, bp_vaddr);
if (vma) {
if (valid_vma(vma, false)) {
struct inode *inode = file_inode(vma->vm_file);
loff_t offset = vaddr_to_offset(vma, bp_vaddr);
uprobe = find_uprobe_rcu(inode, offset);
}
if (!uprobe)
*is_swbp = is_trap_at_addr(mm, bp_vaddr);
} else {
*is_swbp = -EFAULT;
}
if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags))
mmf_recalc_uprobes(mm);
mmap_read_unlock(mm);
return uprobe;
}
static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
{
struct uprobe_consumer *uc;
int remove = UPROBE_HANDLER_REMOVE;
bool need_prep = false; /* prepare return uprobe, when needed */
bool has_consumers = false;
current->utask->auprobe = &uprobe->arch;
list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
srcu_read_lock_held(&uprobes_srcu)) {
int rc = 0;
if (uc->handler) {
rc = uc->handler(uc, regs);
WARN(rc & ~UPROBE_HANDLER_MASK,
"bad rc=0x%x from %ps()\n", rc, uc->handler);
}
if (uc->ret_handler)
need_prep = true;
remove &= rc;
has_consumers = true;
}
current->utask->auprobe = NULL;
if (need_prep && !remove)
prepare_uretprobe(uprobe, regs); /* put bp at return */
if (remove && has_consumers) {
down_read(&uprobe->register_rwsem);
/* re-check that removal is still required, this time under lock */
if (!filter_chain(uprobe, current->mm)) {
WARN_ON(!uprobe_is_active(uprobe));
unapply_uprobe(uprobe, current->mm);
}
up_read(&uprobe->register_rwsem);
}
}
static void
handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs)
{
struct uprobe *uprobe = ri->uprobe;
struct uprobe_consumer *uc;
int srcu_idx;
srcu_idx = srcu_read_lock(&uprobes_srcu);
list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
srcu_read_lock_held(&uprobes_srcu)) {
if (uc->ret_handler)
uc->ret_handler(uc, ri->func, regs);
}
srcu_read_unlock(&uprobes_srcu, srcu_idx);
}
static struct return_instance *find_next_ret_chain(struct return_instance *ri)
{
bool chained;
do {
chained = ri->chained;
ri = ri->next; /* can't be NULL if chained */
} while (chained);
return ri;
}
void uprobe_handle_trampoline(struct pt_regs *regs)
{
struct uprobe_task *utask;
struct return_instance *ri, *next;
bool valid;
utask = current->utask;
if (!utask)
goto sigill;
ri = utask->return_instances;
if (!ri)
goto sigill;
do {
/*
* We should throw out the frames invalidated by longjmp().
* If this chain is valid, then the next one should be alive
* or NULL; the latter case means that nobody but ri->func
* could hit this trampoline on return. TODO: sigaltstack().
*/
next = find_next_ret_chain(ri);
valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs);
instruction_pointer_set(regs, ri->orig_ret_vaddr);
do {
/* pop current instance from the stack of pending return instances,
* as it's not pending anymore: we just fixed up original
* instruction pointer in regs and are about to call handlers;
* this allows fixup_uretprobe_trampoline_entries() to properly fix up
* captured stack traces from uretprobe handlers, in which pending
* trampoline addresses on the stack are replaced with correct
* original return addresses
*/
utask->return_instances = ri->next;
if (valid)
handle_uretprobe_chain(ri, regs);
ri = free_ret_instance(ri);
utask->depth--;
} while (ri != next);
} while (!valid);
utask->return_instances = ri;
return;
sigill:
uprobe_warn(current, "handle uretprobe, sending SIGILL.");
force_sig(SIGILL);
}
bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs)
{
return false;
}
bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
struct pt_regs *regs)
{
return true;
}
/*
* Run handler and ask thread to singlestep.
* Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
*/
static void handle_swbp(struct pt_regs *regs)
{
struct uprobe *uprobe;
unsigned long bp_vaddr;
int is_swbp, srcu_idx;
bp_vaddr = uprobe_get_swbp_addr(regs);
if (bp_vaddr == uprobe_get_trampoline_vaddr())
return uprobe_handle_trampoline(regs);
srcu_idx = srcu_read_lock(&uprobes_srcu);
uprobe = find_active_uprobe_rcu(bp_vaddr, &is_swbp);
if (!uprobe) {
if (is_swbp > 0) {
/* No matching uprobe; signal SIGTRAP. */
force_sig(SIGTRAP);
} else {
/*
* Either we raced with uprobe_unregister() or we can't
* access this memory. The latter is only possible if
* another thread plays with our ->mm. In both cases
* we can simply restart. If this vma was unmapped we
* can pretend this insn was not executed yet and get
* the (correct) SIGSEGV after restart.
*/
instruction_pointer_set(regs, bp_vaddr);
}
goto out;
}
/* change it in advance for ->handler() and restart */
instruction_pointer_set(regs, bp_vaddr);
/*
* TODO: move copy_insn/etc into _register and remove this hack.
* After we hit the bp, _unregister + _register can install the
* new and not-yet-analyzed uprobe at the same address, restart.
*/
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
/*
* Pairs with the smp_wmb() in prepare_uprobe().
*
* Guarantees that if we see the UPROBE_COPY_INSN bit set, then
* we must also see the stores to &uprobe->arch performed by the
* prepare_uprobe() call.
*/
smp_rmb();
/* Tracing handlers use ->utask to communicate with fetch methods */
if (!get_utask())
goto out;
if (arch_uprobe_ignore(&uprobe->arch, regs))
goto out;
handler_chain(uprobe, regs);
if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
goto out;
if (pre_ssout(uprobe, regs, bp_vaddr))
goto out;
out:
/* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */
srcu_read_unlock(&uprobes_srcu, srcu_idx);
}
/*
* Perform required fix-ups and disable singlestep.
* Allow pending signals to take effect.
*/
static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
{
struct uprobe *uprobe;
int err = 0;
uprobe = utask->active_uprobe;
if (utask->state == UTASK_SSTEP_ACK)
err = arch_uprobe_post_xol(&uprobe->arch, regs);
else if (utask->state == UTASK_SSTEP_TRAPPED)
arch_uprobe_abort_xol(&uprobe->arch, regs);
else
WARN_ON_ONCE(1);
put_uprobe(uprobe);
utask->active_uprobe = NULL;
utask->state = UTASK_RUNNING;
xol_free_insn_slot(current);
spin_lock_irq(¤t->sighand->siglock);
recalc_sigpending(); /* see uprobe_deny_signal() */
spin_unlock_irq(¤t->sighand->siglock);
if (unlikely(err)) {
uprobe_warn(current, "execute the probed insn, sending SIGILL.");
force_sig(SIGILL);
}
}
/*
* On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and
* allows the thread to return from interrupt. After that handle_swbp()
* sets utask->active_uprobe.
*
* On singlestep exception, singlestep notifier sets the TIF_UPROBE flag
* and allows the thread to return from interrupt.
*
* While returning to userspace, thread notices the TIF_UPROBE flag and calls
* uprobe_notify_resume().
*/
void uprobe_notify_resume(struct pt_regs *regs)
{
struct uprobe_task *utask;
clear_thread_flag(TIF_UPROBE);
utask = current->utask;
if (utask && utask->active_uprobe)
handle_singlestep(utask, regs);
else
handle_swbp(regs);
}
/*
* uprobe_pre_sstep_notifier gets called from interrupt context as part of
* notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit.
*/
int uprobe_pre_sstep_notifier(struct pt_regs *regs)
{
if (!current->mm)
return 0;
if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) &&
(!current->utask || !current->utask->return_instances))
return 0;
set_thread_flag(TIF_UPROBE);
return 1;
}
/*
* uprobe_post_sstep_notifier gets called in interrupt context as part of notifier
* mechanism. Set TIF_UPROBE flag and indicate completion of singlestep.
*/
int uprobe_post_sstep_notifier(struct pt_regs *regs)
{
struct uprobe_task *utask = current->utask;
if (!current->mm || !utask || !utask->active_uprobe)
/* task is currently not uprobed */
return 0;
utask->state = UTASK_SSTEP_ACK;
set_thread_flag(TIF_UPROBE);
return 1;
}
static struct notifier_block uprobe_exception_nb = {
.notifier_call = arch_uprobe_exception_notify,
.priority = INT_MAX-1, /* notified after kprobes, kgdb */
};
void __init uprobes_init(void)
{
int i;
for (i = 0; i < UPROBES_HASH_SZ; i++)
mutex_init(&uprobes_mmap_mutex[i]);
BUG_ON(register_die_notifier(&uprobe_exception_nb));
}
Codebase Browser
linux