1
linux/io_uring/filetable.c
Lin Ma 9d94c04c0d io_uring/filetable: fix file reference underflow
There is an interesting reference bug when -ENOMEM occurs in calling of
io_install_fixed_file(). KASan report like below:

[   14.057131] ==================================================================
[   14.059161] BUG: KASAN: use-after-free in unix_get_socket+0x10/0x90
[   14.060975] Read of size 8 at addr ffff88800b09cf20 by task kworker/u8:2/45
[   14.062684]
[   14.062768] CPU: 2 PID: 45 Comm: kworker/u8:2 Not tainted 6.1.0-rc4 #1
[   14.063099] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
[   14.063666] Workqueue: events_unbound io_ring_exit_work
[   14.063936] Call Trace:
[   14.064065]  <TASK>
[   14.064175]  dump_stack_lvl+0x34/0x48
[   14.064360]  print_report+0x172/0x475
[   14.064547]  ? _raw_spin_lock_irq+0x83/0xe0
[   14.064758]  ? __virt_addr_valid+0xef/0x170
[   14.064975]  ? unix_get_socket+0x10/0x90
[   14.065167]  kasan_report+0xad/0x130
[   14.065353]  ? unix_get_socket+0x10/0x90
[   14.065553]  unix_get_socket+0x10/0x90
[   14.065744]  __io_sqe_files_unregister+0x87/0x1e0
[   14.065989]  ? io_rsrc_refs_drop+0x1c/0xd0
[   14.066199]  io_ring_exit_work+0x388/0x6a5
[   14.066410]  ? io_uring_try_cancel_requests+0x5bf/0x5bf
[   14.066674]  ? try_to_wake_up+0xdb/0x910
[   14.066873]  ? virt_to_head_page+0xbe/0xbe
[   14.067080]  ? __schedule+0x574/0xd20
[   14.067273]  ? read_word_at_a_time+0xe/0x20
[   14.067492]  ? strscpy+0xb5/0x190
[   14.067665]  process_one_work+0x423/0x710
[   14.067879]  worker_thread+0x2a2/0x6f0
[   14.068073]  ? process_one_work+0x710/0x710
[   14.068284]  kthread+0x163/0x1a0
[   14.068454]  ? kthread_complete_and_exit+0x20/0x20
[   14.068697]  ret_from_fork+0x22/0x30
[   14.068886]  </TASK>
[   14.069000]
[   14.069088] Allocated by task 289:
[   14.069269]  kasan_save_stack+0x1e/0x40
[   14.069463]  kasan_set_track+0x21/0x30
[   14.069652]  __kasan_slab_alloc+0x58/0x70
[   14.069899]  kmem_cache_alloc+0xc5/0x200
[   14.070100]  __alloc_file+0x20/0x160
[   14.070283]  alloc_empty_file+0x3b/0xc0
[   14.070479]  path_openat+0xc3/0x1770
[   14.070689]  do_filp_open+0x150/0x270
[   14.070888]  do_sys_openat2+0x113/0x270
[   14.071081]  __x64_sys_openat+0xc8/0x140
[   14.071283]  do_syscall_64+0x3b/0x90
[   14.071466]  entry_SYSCALL_64_after_hwframe+0x63/0xcd
[   14.071791]
[   14.071874] Freed by task 0:
[   14.072027]  kasan_save_stack+0x1e/0x40
[   14.072224]  kasan_set_track+0x21/0x30
[   14.072415]  kasan_save_free_info+0x2a/0x50
[   14.072627]  __kasan_slab_free+0x106/0x190
[   14.072858]  kmem_cache_free+0x98/0x340
[   14.073075]  rcu_core+0x427/0xe50
[   14.073249]  __do_softirq+0x110/0x3cd
[   14.073440]
[   14.073523] Last potentially related work creation:
[   14.073801]  kasan_save_stack+0x1e/0x40
[   14.074017]  __kasan_record_aux_stack+0x97/0xb0
[   14.074264]  call_rcu+0x41/0x550
[   14.074436]  task_work_run+0xf4/0x170
[   14.074619]  exit_to_user_mode_prepare+0x113/0x120
[   14.074858]  syscall_exit_to_user_mode+0x1d/0x40
[   14.075092]  do_syscall_64+0x48/0x90
[   14.075272]  entry_SYSCALL_64_after_hwframe+0x63/0xcd
[   14.075529]
[   14.075612] Second to last potentially related work creation:
[   14.075900]  kasan_save_stack+0x1e/0x40
[   14.076098]  __kasan_record_aux_stack+0x97/0xb0
[   14.076325]  task_work_add+0x72/0x1b0
[   14.076512]  fput+0x65/0xc0
[   14.076657]  filp_close+0x8e/0xa0
[   14.076825]  __x64_sys_close+0x15/0x50
[   14.077019]  do_syscall_64+0x3b/0x90
[   14.077199]  entry_SYSCALL_64_after_hwframe+0x63/0xcd
[   14.077448]
[   14.077530] The buggy address belongs to the object at ffff88800b09cf00
[   14.077530]  which belongs to the cache filp of size 232
[   14.078105] The buggy address is located 32 bytes inside of
[   14.078105]  232-byte region [ffff88800b09cf00, ffff88800b09cfe8)
[   14.078685]
[   14.078771] The buggy address belongs to the physical page:
[   14.079046] page:000000001bd520e7 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88800b09de00 pfn:0xb09c
[   14.079575] head:000000001bd520e7 order:1 compound_mapcount:0 compound_pincount:0
[   14.079946] flags: 0x100000000010200(slab|head|node=0|zone=1)
[   14.080244] raw: 0100000000010200 0000000000000000 dead000000000001 ffff88800493cc80
[   14.080629] raw: ffff88800b09de00 0000000080190018 00000001ffffffff 0000000000000000
[   14.081016] page dumped because: kasan: bad access detected
[   14.081293]
[   14.081376] Memory state around the buggy address:
[   14.081618]  ffff88800b09ce00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   14.081974]  ffff88800b09ce80: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
[   14.082336] >ffff88800b09cf00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   14.082690]                                ^
[   14.082909]  ffff88800b09cf80: fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc
[   14.083266]  ffff88800b09d000: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
[   14.083622] ==================================================================

The actual tracing of this bug is shown below:

commit 8c71fe7502 ("io_uring: ensure fput() called correspondingly
when direct install fails") adds an additional fput() in
io_fixed_fd_install() when io_file_bitmap_get() returns error values. In
that case, the routine will never make it to io_install_fixed_file() due
to an early return.

static int io_fixed_fd_install(...)
{
  if (alloc_slot) {
    ...
    ret = io_file_bitmap_get(ctx);
    if (unlikely(ret < 0)) {
      io_ring_submit_unlock(ctx, issue_flags);
      fput(file);
      return ret;
    }
    ...
  }
  ...
  ret = io_install_fixed_file(req, file, issue_flags, file_slot);
  ...
}

In the above scenario, the reference is okay as io_fixed_fd_install()
ensures the fput() is called when something bad happens, either via
bitmap or via inner io_install_fixed_file().

However, the commit 61c1b44a21 ("io_uring: fix deadlock on iowq file
slot alloc") breaks the balance because it places fput() into the common
path for both io_file_bitmap_get() and io_install_fixed_file(). Since
io_install_fixed_file() handles the fput() itself, the reference
underflow come across then.

There are some extra commits make the current code into
io_fixed_fd_install() -> __io_fixed_fd_install() ->
io_install_fixed_file()

However, the fact that there is an extra fput() is called if
io_install_fixed_file() calls fput(). Traversing through the code, I
find that the existing two callers to __io_fixed_fd_install():
io_fixed_fd_install() and io_msg_send_fd() have fput() when handling
error return, this patch simply removes the fput() in
io_install_fixed_file() to fix the bug.

Fixes: 61c1b44a21 ("io_uring: fix deadlock on iowq file slot alloc")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Link: https://lore.kernel.org/r/be4ba4b.5d44.184a0a406a4.Coremail.linma@zju.edu.cn
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-11-25 06:54:46 -07:00

192 lines
4.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/nospec.h>
#include <linux/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
#include "rsrc.h"
#include "filetable.h"
static int io_file_bitmap_get(struct io_ring_ctx *ctx)
{
struct io_file_table *table = &ctx->file_table;
unsigned long nr = ctx->file_alloc_end;
int ret;
do {
ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
if (ret != nr)
return ret;
if (table->alloc_hint == ctx->file_alloc_start)
break;
nr = table->alloc_hint;
table->alloc_hint = ctx->file_alloc_start;
} while (1);
return -ENFILE;
}
bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files)
{
table->files = kvcalloc(nr_files, sizeof(table->files[0]),
GFP_KERNEL_ACCOUNT);
if (unlikely(!table->files))
return false;
table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT);
if (unlikely(!table->bitmap)) {
kvfree(table->files);
return false;
}
return true;
}
void io_free_file_tables(struct io_file_table *table)
{
kvfree(table->files);
bitmap_free(table->bitmap);
table->files = NULL;
table->bitmap = NULL;
}
static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
u32 slot_index)
__must_hold(&req->ctx->uring_lock)
{
bool needs_switch = false;
struct io_fixed_file *file_slot;
int ret;
if (io_is_uring_fops(file))
return -EBADF;
if (!ctx->file_data)
return -ENXIO;
if (slot_index >= ctx->nr_user_files)
return -EINVAL;
slot_index = array_index_nospec(slot_index, ctx->nr_user_files);
file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);
if (file_slot->file_ptr) {
struct file *old_file;
ret = io_rsrc_node_switch_start(ctx);
if (ret)
goto err;
old_file = (struct file *)(file_slot->file_ptr & FFS_MASK);
ret = io_queue_rsrc_removal(ctx->file_data, slot_index,
ctx->rsrc_node, old_file);
if (ret)
goto err;
file_slot->file_ptr = 0;
io_file_bitmap_clear(&ctx->file_table, slot_index);
needs_switch = true;
}
ret = io_scm_file_account(ctx, file);
if (!ret) {
*io_get_tag_slot(ctx->file_data, slot_index) = 0;
io_fixed_file_set(file_slot, file);
io_file_bitmap_set(&ctx->file_table, slot_index);
}
err:
if (needs_switch)
io_rsrc_node_switch(ctx, ctx->file_data);
return ret;
}
int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
unsigned int file_slot)
{
bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
int ret;
if (alloc_slot) {
ret = io_file_bitmap_get(ctx);
if (unlikely(ret < 0))
return ret;
file_slot = ret;
} else {
file_slot--;
}
ret = io_install_fixed_file(ctx, file, file_slot);
if (!ret && alloc_slot)
ret = file_slot;
return ret;
}
/*
* Note when io_fixed_fd_install() returns error value, it will ensure
* fput() is called correspondingly.
*/
int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
struct file *file, unsigned int file_slot)
{
struct io_ring_ctx *ctx = req->ctx;
int ret;
io_ring_submit_lock(ctx, issue_flags);
ret = __io_fixed_fd_install(ctx, file, file_slot);
io_ring_submit_unlock(ctx, issue_flags);
if (unlikely(ret < 0))
fput(file);
return ret;
}
int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset)
{
struct io_fixed_file *file_slot;
struct file *file;
int ret;
if (unlikely(!ctx->file_data))
return -ENXIO;
if (offset >= ctx->nr_user_files)
return -EINVAL;
ret = io_rsrc_node_switch_start(ctx);
if (ret)
return ret;
offset = array_index_nospec(offset, ctx->nr_user_files);
file_slot = io_fixed_file_slot(&ctx->file_table, offset);
if (!file_slot->file_ptr)
return -EBADF;
file = (struct file *)(file_slot->file_ptr & FFS_MASK);
ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file);
if (ret)
return ret;
file_slot->file_ptr = 0;
io_file_bitmap_clear(&ctx->file_table, offset);
io_rsrc_node_switch(ctx, ctx->file_data);
return 0;
}
int io_register_file_alloc_range(struct io_ring_ctx *ctx,
struct io_uring_file_index_range __user *arg)
{
struct io_uring_file_index_range range;
u32 end;
if (copy_from_user(&range, arg, sizeof(range)))
return -EFAULT;
if (check_add_overflow(range.off, range.len, &end))
return -EOVERFLOW;
if (range.resv || end > ctx->nr_user_files)
return -EINVAL;
io_file_table_set_alloc_range(ctx, range.off, range.len);
return 0;
}