litmus-rt.git - The LITMUS^RT kernel.

/*
 * User-space Probes (UProbes)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) IBM Corporation, 2008-2012
 * Authors:
 *	Srikar Dronamraju
 *	Jim Keniston
 * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 */

#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/export.h>
#include <linux/rmap.h>		/* anon_vma_prepare */
#include <linux/mmu_notifier.h>	/* set_pte_at_notify */
#include <linux/swap.h>		/* try_to_free_swap */
#include <linux/ptrace.h>	/* user_enable_single_step */
#include <linux/kdebug.h>	/* notifier mechanism */
#include "../../mm/internal.h"	/* munlock_vma_page */
#include <linux/percpu-rwsem.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_SPINLOCK(uprobes_treelock);	/* serialize rbtree access */

#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])

static struct percpu_rw_semaphore dup_mmap_sem;

/* Have a copy of original instruction */
#define UPROBE_COPY_INSN	0
/* Can skip singlestep */
#define UPROBE_SKIP_SSTEP	1

struct uprobe {
	struct rb_node		rb_node;	/* node in the rb tree */
	atomic_t		ref;
	struct rw_semaphore	register_rwsem;
	struct rw_semaphore	consumer_rwsem;
	struct list_head	pending_list;
	struct uprobe_consumer	*consumers;
	struct inode		*inode;		/* Also hold a ref to inode */
	loff_t			offset;
	unsigned long		flags;
	struct arch_uprobe	arch;
};

/*
 * 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_SHARED;

	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
 * @page:     the cowed page we are replacing by kpage
 * @kpage:    the modified page we replace page by
 *
 * Returns 0 on success, -EFAULT on failure.
 */
static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
				struct page *page, struct page *kpage)
{
	struct mm_struct *mm = vma->vm_mm;
	spinlock_t *ptl;
	pte_t *ptep;
	int err;
	/* For mmu_notifiers */
	const unsigned long mmun_start = addr;
	const unsigned long mmun_end   = addr + PAGE_SIZE;

	/* For try_to_free_swap() and munlock_vma_page() below */
	lock_page(page);

	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	err = -EAGAIN;
	ptep = page_check_address(page, mm, addr, &ptl, 0);
	if (!ptep)
		goto unlock;

	get_page(kpage);
	page_add_new_anon_rmap(kpage, vma, addr);

	if (!PageAnon(page)) {
		dec_mm_counter(mm, MM_FILEPAGES);
		inc_mm_counter(mm, MM_ANONPAGES);
	}

	flush_cache_page(vma, addr, pte_pfn(*ptep));
	ptep_clear_flush(vma, addr, ptep);
	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));

	page_remove_rmap(page);
	if (!page_mapped(page))
		try_to_free_swap(page);
	pte_unmap_unlock(ptep, ptl);

	if (vma->vm_flags & VM_LOCKED)
		munlock_vma_page(page);
	put_page(page);

	err = 0;
 unlock:
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	unlock_page(page);
	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;
}

static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode)
{
	void *kaddr = kmap_atomic(page);
	memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE);
	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;

	copy_opcode(page, vaddr, &old_opcode);
	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;
}

/*
 * 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_swbp_at_addr and
 * write_opcode accordingly. This would never be a problem for archs that
 * have fixed length instructions.
 */

/*
 * write_opcode - write the opcode at a given virtual address.
 * @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_sem held (for read and with a reference to
 * mm).
 *
 * For mm @mm, write the opcode at @vaddr.
 * Return 0 (success) or a negative errno.
 */
static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
			uprobe_opcode_t opcode)
{
	struct page *old_page, *new_page;
	void *vaddr_old, *vaddr_new;
	struct vm_area_struct *vma;
	int ret;

retry:
	/* Read the page with vaddr into memory */
	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
	if (ret <= 0)
		return ret;

	ret = verify_opcode(old_page, vaddr, &opcode);
	if (ret <= 0)
		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 the page now that we've got it stable */
	vaddr_old = kmap_atomic(old_page);
	vaddr_new = kmap_atomic(new_page);

	memcpy(vaddr_new, vaddr_old, PAGE_SIZE);
	memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE);

	kunmap_atomic(vaddr_new);
	kunmap_atomic(vaddr_old);

	ret = anon_vma_prepare(vma);
	if (ret)
		goto put_new;

	ret = __replace_page(vma, vaddr, old_page, new_page);

put_new:
	page_cache_release(new_page);
put_old:
	put_page(old_page);

	if (unlikely(ret == -EAGAIN))
		goto retry;
	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 write_opcode(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 write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
}

static int match_uprobe(struct uprobe *l, 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;
}

static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe u = { .inode = inode, .offset = offset };
	struct rb_node *n = uprobes_tree.rb_node;
	struct uprobe *uprobe;
	int match;

	while (n) {
		uprobe = rb_entry(n, struct uprobe, rb_node);
		match = match_uprobe(&u, uprobe);
		if (!match) {
			atomic_inc(&uprobe->ref);
			return uprobe;
		}

		if (match < 0)
			n = n->rb_left;
		else
			n = n->rb_right;
	}
	return NULL;
}

/*
 * Find a uprobe corresponding to a given inode:offset
 * Acquires uprobes_treelock
 */
static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe *uprobe;

	spin_lock(&uprobes_treelock);
	uprobe = __find_uprobe(inode, offset);
	spin_unlock(&uprobes_treelock);

	return uprobe;
}

static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
{
	struct rb_node **p = &uprobes_tree.rb_node;
	struct rb_node *parent = NULL;
	struct uprobe *u;
	int match;

	while (*p) {
		parent = *p;
		u = rb_entry(parent, struct uprobe, rb_node);
		match = match_uprobe(uprobe, u);
		if (!match) {
			atomic_inc(&u->ref);
			return u;
		}

		if (match < 0)
			p = &parent->rb_left;
		else
			p = &parent->rb_right;

	}

	u = NULL;
	rb_link_node(&uprobe->rb_node, parent, p);
	rb_insert_color(&uprobe->rb_node, &uprobes_tree);
	/* get access + creation ref */
	atomic_set(&uprobe->ref, 2);

	return u;
}

/*
 * Acquire uprobes_treelock.
 * Matching uprobe already exists in rbtree;
 *	increment (access refcount) and return the matching uprobe.
 *
 * No matching uprobe; insert the uprobe in rb_tree;
 *	get a double refcount (access + creation) and return NULL.
 */
static struct uprobe *insert_uprobe(struct uprobe *uprobe)
{
	struct uprobe *u;

	spin_lock(&uprobes_treelock);
	u = __insert_uprobe(uprobe);
	spin_unlock(&uprobes_treelock);

	return u;
}

static void put_uprobe(struct uprobe *uprobe)
{
	if (atomic_dec_and_test(&uprobe->ref))
		kfree(uprobe);
}

static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe *uprobe, *cur_uprobe;

	uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL);
	if (!uprobe)
		return NULL;

	uprobe->inode = igrab(inode);
	uprobe->offset = offset;
	init_rwsem(&uprobe->register_rwsem);
	init_rwsem(&uprobe->consumer_rwsem);
	/* For now assume that the instruction need not be single-stepped */
	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);

	/* add to uprobes_tree, sorted on inode:offset */
	cur_uprobe = insert_uprobe(uprobe);

	/* a uprobe exists for this inode:offset combination */
	if (cur_uprobe) {
		kfree(uprobe);
		uprobe = cur_uprobe;
		iput(inode);
	}

	return uprobe;
}

static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	down_write(&uprobe->consumer_rwsem);
	uc->next = uprobe->consumers;
	uprobe->consumers = uc;
	up_write(&uprobe->consumer_rwsem);
}

/*
 * For uprobe @uprobe, delete the consumer @uc.
 * Return true if the @uc is deleted successfully
 * or return false.
 */
static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	struct uprobe_consumer **con;
	bool ret = false;

	down_write(&uprobe->consumer_rwsem);
	for (con = &uprobe->consumers; *con; con = &(*con)->next) {
		if (*con == uc) {
			*con = uc->next;
			ret = true;
			break;
		}
	}
	up_write(&uprobe->consumer_rwsem);

	return ret;
}

static int
__copy_insn(struct address_space *mapping, struct file *filp, char *insn,
			unsigned long nbytes, loff_t offset)
{
	struct page *page;
	void *vaddr;
	unsigned long off;
	pgoff_t idx;

	if (!filp)
		return -EINVAL;

	if (!mapping->a_ops->readpage)
		return -EIO;

	idx = offset >> PAGE_CACHE_SHIFT;
	off = offset & ~PAGE_MASK;

	/*
	 * Ensure that the page that has the original instruction is
	 * populated and in page-cache.
	 */
	page = read_mapping_page(mapping, idx, filp);
	if (IS_ERR(page))
		return PTR_ERR(page);

	vaddr = kmap_atomic(page);
	memcpy(insn, vaddr + off, nbytes);
	kunmap_atomic(vaddr);
	page_cache_release(page);

	return 0;
}

static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
	struct address_space *mapping;
	unsigned long nbytes;
	int bytes;

	nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK);
	mapping = uprobe->inode->i_mapping;

	/* Instruction at end of binary; copy only available bytes */
	if (uprobe->offset + MAX_UINSN_BYTES > uprobe->inode->i_size)
		bytes = uprobe->inode->i_size - uprobe->offset;
	else
		bytes = MAX_UINSN_BYTES;

	/* Instruction at the page-boundary; copy bytes in second page */
	if (nbytes < bytes) {
		int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes,
				bytes - nbytes, uprobe->offset + nbytes);
		if (err)
			return err;
		bytes = nbytes;
	}
	return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
}

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_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
		goto out;

	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
	if (ret)
		goto out;

	/* write_opcode() assumes we don't cross page boundary */
	BUG_ON((uprobe->offset & ~PAGE_MASK) +
			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);

	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
	set_bit(UPROBE_COPY_INSN, &uprobe->flags);

 out:
	up_write(&uprobe->consumer_rwsem);

	return ret;
}

static inline bool consumer_filter(struct uprobe_consumer *uc,
				   enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
	return !uc->filter || uc->filter(uc, ctx, mm);
}

static bool filter_chain(struct uprobe *uprobe,
			 enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
	struct uprobe_consumer *uc;
	bool ret = false;

	down_read(&uprobe->consumer_rwsem);
	for (uc = uprobe->consumers; uc; uc = uc->next) {
		ret = consumer_filter(uc, ctx, 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);
}

static inline bool uprobe_is_active(struct uprobe *uprobe)
{
	return !RB_EMPTY_NODE(&uprobe->rb_node);
}
/*
 * There could be threads that have already hit the breakpoint. They
 * will recheck the current insn and restart if find_uprobe() fails.
 * See find_active_uprobe().
 */
static void delete_uprobe(struct uprobe *uprobe)
{
	if (WARN_ON(!uprobe_is_active(uprobe)))
		return;

	spin_lock(&uprobes_treelock);
	rb_erase(&uprobe->rb_node, &uprobes_tree);
	spin_unlock(&uprobes_treelock);
	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
	iput(uprobe->inode);
	put_uprobe(uprobe);
}

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:
	mutex_lock(&mapping->i_mmap_mutex);
	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_mutex 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 (!atomic_inc_not_zero(&vma->vm_mm->mm_users))
			continue;

		info = prev;
		prev = prev->next;
		info->next = curr;
		curr = info;

		info->mm = vma->vm_mm;
		info->vaddr = offset_to_vaddr(vma, offset);
	}
	mutex_unlock(&mapping->i_mmap_mutex);

	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;

		down_write(&mm->mmap_sem);
		vma = find_vma(mm, info->vaddr);
		if (!vma || !valid_vma(vma, is_register) ||
		    vma->vm_file->f_mapping->host != 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,
					UPROBE_FILTER_REGISTER, mm))
				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
			if (!filter_chain(uprobe,
					UPROBE_FILTER_UNREGISTER, mm))
				err |= remove_breakpoint(uprobe, mm, info->vaddr);
		}

 unlock:
		up_write(&mm->mmap_sem);
 free:
		mmput(mm);
		info = free_map_info(info);
	}
 out:
	percpu_up_write(&dup_mmap_sem);
	return err;
}

static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	consumer_add(uprobe, uc);
	return register_for_each_vma(uprobe, uc);
}

static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	int err;

	if (!consumer_del(uprobe, uc))	/* WARN? */
		return;

	err = register_for_each_vma(uprobe, NULL);
	/* TODO : cant unregister? schedule a worker thread */
	if (!uprobe->consumers && !err)
		delete_uprobe(uprobe);
}

/*
 * uprobe_register - register a probe
 * @inode: the file in which the probe has to be placed.
 * @offset: offset from the start of the file.
 * @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.
 *
 * Return errno if it cannot successully install probes
 * else return 0 (success)
 */
int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
{
	struct uprobe *uprobe;
	int ret;

	/* Racy, just to catch the obvious mistakes */
	if (offset > i_size_read(inode))
		return -EINVAL;

 retry:
	uprobe = alloc_uprobe(inode, offset);
	if (!uprobe)
		return -ENOMEM;
	/*
	 * We can race with uprobe_unregister()->delete_uprobe().
	 * Check uprobe_is_active() and retry if it is false.
	 */
	down_write(&uprobe->register_rwsem);
	ret = -EAGAIN;
	if (likely(uprobe_is_active(uprobe))) {
		ret = __uprobe_register(uprobe, uc);
		if (ret)
			__uprobe_unregister(uprobe, uc);
	}
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);

	if (unlikely(ret == -EAGAIN))
		goto retry;
	return ret;
}
EXPORT_SYMBOL_GPL(uprobe_register);

/*
 * uprobe_apply - unregister a already registered probe.
 * @inode: the file in which the probe has to be removed.
 * @offset: offset from the start of the file.
 * @uc: consumer which wants to add more or remove some breakpoints
 * @add: add or remove the breakpoints
 */
int uprobe_apply(struct inode *inode, loff_t offset,
			struct uprobe_consumer *uc, bool add)
{
	struct uprobe *uprobe;
	struct uprobe_consumer *con;
	int ret = -ENOENT;

	uprobe = find_uprobe(inode, offset);
	if (!uprobe)
		return ret;

	down_write(&uprobe->register_rwsem);
	for (con = uprobe->consumers; con && con != uc ; con = con->next)
		;
	if (con)
		ret = register_for_each_vma(uprobe, add ? uc : NULL);
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);

	return ret;
}

/*
 * uprobe_unregister - unregister a already registered probe.
 * @inode: the file in which the probe has to be removed.
 * @offset: offset from the start of the file.
 * @uc: identify which probe if multiple probes are colocated.
 */
void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
{
	struct uprobe *uprobe;

	uprobe = find_uprobe(inode, offset);
	if (!uprobe)
		return;

	down_write(&uprobe->register_rwsem);
	__uprobe_unregister(uprobe, uc);
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);
}
EXPORT_SYMBOL_GPL(uprobe_unregister);

static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	int err = 0;

	down_read(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		unsigned long vaddr;
		loff_t offset;

		if (!valid_vma(vma, false) ||
		    vma->vm_file->f_mapping->host != 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);
	}
	up_read(&mm->mmap_sem);

	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;


context:
space:
mode: