[v2,1/4] tracing/user_events: Prepare find/delete for same name events
Commit Message
The current code for finding and deleting events assumes that there will
never be cases when user_events are registered with the same name, but
different formats. In the future this scenario will exist to ensure
user programs can be updated or modify their events and run different
versions of their programs side-by-side without being blocked.
This change does not yet allow for multi-format events. If user_events
are registered with the same name but different arguments the programs
see the same return values as before. This change simply makes it
possible to easily accomodate for this in future changes.
Update find_user_event() to take in argument parameters and register
flags to accomodate future multi-format event scenarios. Have find
validate argument matching and return error pointers to cover address
in use cases, or allocation errors. Update callers to handle error
pointer logic.
Move delete_user_event() to use hash walking directly now that find has
changed. Delete all events found that match the register name, stop
if an error occurs and report back to the user.
Update user_fields_match() to cover list_empty() scenarios instead of
each callsite doing it now that find_user_event() uses it directly.
Signed-off-by: Beau Belgrave <beaub@linux.microsoft.com>
---
kernel/trace/trace_events_user.c | 106 +++++++++++++++++--------------
1 file changed, 58 insertions(+), 48 deletions(-)
Comments
Hello,
kernel test robot noticed "BUG:KASAN:slab-use-after-free_in_user_events_ioctl" on:
commit: fecc001d587ceeeb47043c20353f257e3f01b39f ("[PATCH v2 1/4] tracing/user_events: Prepare find/delete for same name events")
url: https://github.com/intel-lab-lkp/linux/commits/Beau-Belgrave/tracing-user_events-Prepare-find-delete-for-same-name-events/20240203-031207
patch link: https://lore.kernel.org/all/20240202184449.1674-2-beaub@linux.microsoft.com/
patch subject: [PATCH v2 1/4] tracing/user_events: Prepare find/delete for same name events
in testcase: kernel-selftests
version: kernel-selftests-x86_64-60acb023-1_20230329
with following parameters:
group: user_events
compiler: gcc-12
test machine: 36 threads 1 sockets Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz (Cascade Lake) with 32G memory
(please refer to attached dmesg/kmsg for entire log/backtrace)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202402141240.cc5aba78-oliver.sang@intel.com
[ 106.969333][ T2278] BUG: KASAN: slab-use-after-free in user_events_ioctl (kernel/trace/trace_events_user.c:2067 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.970079][ T2278] Read of size 8 at addr ffff88816644ef38 by task abi_test/2278
[ 106.970788][ T2278]
[ 106.971058][ T2278] CPU: 2 PID: 2278 Comm: abi_test Not tainted 6.7.0-rc8-00001-gfecc001d587c #1
[ 106.971881][ T2278] Hardware name: Gigabyte Technology Co., Ltd. X299 UD4 Pro/X299 UD4 Pro-CF, BIOS F8a 04/27/2021
[ 106.972829][ T2278] Call Trace:
[ 106.973185][ T2278] <TASK>
[ 106.973514][ T2278] dump_stack_lvl (lib/dump_stack.c:108)
[ 106.973966][ T2278] print_address_description+0x2c/0x3a0
[ 106.974597][ T2278] ? user_events_ioctl (kernel/trace/trace_events_user.c:2067 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.975099][ T2278] print_report (mm/kasan/report.c:476)
[ 106.975542][ T2278] ? kasan_addr_to_slab (mm/kasan/common.c:35)
[ 106.976025][ T2278] ? user_events_ioctl (kernel/trace/trace_events_user.c:2067 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.976531][ T2278] kasan_report (mm/kasan/report.c:590)
[ 106.976978][ T2278] ? user_events_ioctl (kernel/trace/trace_events_user.c:2067 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.977481][ T2278] user_events_ioctl (kernel/trace/trace_events_user.c:2067 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.977970][ T2278] __x64_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:871 fs/ioctl.c:857 fs/ioctl.c:857)
[ 106.978441][ T2278] do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
[ 106.978889][ T2278] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
[ 106.979462][ T2278] RIP: 0033:0x7f2e121c8b5b
[ 106.979907][ T2278] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1c 48 8b 44 24 18 64 48 2b 04 25 28 00 00
All code
========
0: 00 48 89 add %cl,-0x77(%rax)
3: 44 24 18 rex.R and $0x18,%al
6: 31 c0 xor %eax,%eax
8: 48 8d 44 24 60 lea 0x60(%rsp),%rax
d: c7 04 24 10 00 00 00 movl $0x10,(%rsp)
14: 48 89 44 24 08 mov %rax,0x8(%rsp)
19: 48 8d 44 24 20 lea 0x20(%rsp),%rax
1e: 48 89 44 24 10 mov %rax,0x10(%rsp)
23: b8 10 00 00 00 mov $0x10,%eax
28: 0f 05 syscall
2a:* 89 c2 mov %eax,%edx <-- trapping instruction
2c: 3d 00 f0 ff ff cmp $0xfffff000,%eax
31: 77 1c ja 0x4f
33: 48 8b 44 24 18 mov 0x18(%rsp),%rax
38: 64 fs
39: 48 rex.W
3a: 2b .byte 0x2b
3b: 04 25 add $0x25,%al
3d: 28 00 sub %al,(%rax)
...
Code starting with the faulting instruction
===========================================
0: 89 c2 mov %eax,%edx
2: 3d 00 f0 ff ff cmp $0xfffff000,%eax
7: 77 1c ja 0x25
9: 48 8b 44 24 18 mov 0x18(%rsp),%rax
e: 64 fs
f: 48 rex.W
10: 2b .byte 0x2b
11: 04 25 add $0x25,%al
13: 28 00 sub %al,(%rax)
...
[ 106.981608][ T2278] RSP: 002b:00007ffcb0ba5ed0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[ 106.982385][ T2278] RAX: ffffffffffffffda RBX: 00007ffcb0ba6228 RCX: 00007f2e121c8b5b
[ 106.983128][ T2278] RDX: 0000564d434bc6fe RSI: 0000000040082a01 RDI: 0000000000000005
[ 106.983878][ T2278] RBP: 00007ffcb0ba5f40 R08: 0000000000000000 R09: 00007f2e120c9b80
[ 106.984626][ T2278] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[ 106.986296][ T2278] R13: 00007ffcb0ba6238 R14: 0000564d434bedc8 R15: 00007f2e123cc020
[ 106.987040][ T2278] </TASK>
[ 106.987364][ T2278]
[ 106.987635][ T2278] Allocated by task 2278:
[ 106.988071][ T2278] kasan_save_stack (mm/kasan/common.c:46)
[ 106.988543][ T2278] kasan_set_track (mm/kasan/common.c:52)
[ 106.988999][ T2278] __kasan_kmalloc (mm/kasan/common.c:374 mm/kasan/common.c:383)
[ 106.989465][ T2278] user_event_parse (include/linux/slab.h:600 include/linux/slab.h:721 kernel/trace/trace_events_user.c:1978)
[ 106.989939][ T2278] user_events_ioctl_reg (kernel/trace/trace_events_user.c:2342)
[ 106.990462][ T2278] user_events_ioctl (kernel/trace/trace_events_user.c:2538)
[ 106.990954][ T2278] __x64_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:871 fs/ioctl.c:857 fs/ioctl.c:857)
[ 106.991428][ T2278] do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
[ 106.991871][ T2278] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
[ 106.992436][ T2278]
[ 106.992705][ T2278] Freed by task 2278:
[ 106.993112][ T2278] kasan_save_stack (mm/kasan/common.c:46)
[ 106.993582][ T2278] kasan_set_track (mm/kasan/common.c:52)
[ 106.994043][ T2278] kasan_save_free_info (mm/kasan/generic.c:524)
[ 106.994544][ T2278] __kasan_slab_free (mm/kasan/common.c:238 mm/kasan/common.c:200 mm/kasan/common.c:244)
[ 106.995028][ T2278] slab_free_freelist_hook (mm/slub.c:1826)
[ 106.995553][ T2278] __kmem_cache_free (mm/slub.c:3809 mm/slub.c:3822)
[ 106.996026][ T2278] destroy_user_event (kernel/trace/trace_events_user.c:1489 kernel/trace/trace_events_user.c:1467)
[ 106.996513][ T2278] user_events_ioctl (kernel/trace/trace_events_user.c:2077 kernel/trace/trace_events_user.c:2401 kernel/trace/trace_events_user.c:2543)
[ 106.997009][ T2278] __x64_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:871 fs/ioctl.c:857 fs/ioctl.c:857)
[ 106.997483][ T2278] do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
[ 106.997926][ T2278] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129)
[ 106.998496][ T2278]
[ 106.998768][ T2278] The buggy address belongs to the object at ffff88816644ee00
[ 106.998768][ T2278] which belongs to the cache kmalloc-cg-512 of size 512
[ 107.000035][ T2278] The buggy address is located 312 bytes inside of
[ 107.000035][ T2278] freed 512-byte region [ffff88816644ee00, ffff88816644f000)
[ 107.001266][ T2278]
[ 107.001532][ T2278] The buggy address belongs to the physical page:
[ 107.002142][ T2278] page:ffffea0005991200 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88816644b800 pfn:0x166448
[ 107.003179][ T2278] head:ffffea0005991200 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[ 107.003996][ T2278] memcg:ffff888160dfc4e9
[ 107.004425][ T2278] flags: 0x17ffffc0000840(slab|head|node=0|zone=2|lastcpupid=0x1fffff)
[ 107.005189][ T2278] page_type: 0xffffffff()
[ 107.005635][ T2278] raw: 0017ffffc0000840 ffff888100051700 ffffea0004050810 ffff888100043dc8
[ 107.006434][ T2278] raw: ffff88816644b800 0000000000150008 00000001ffffffff ffff888160dfc4e9
[ 107.007223][ T2278] page dumped because: kasan: bad access detected
[ 107.007841][ T2278]
[ 107.008111][ T2278] Memory state around the buggy address:
[ 107.008660][ T2278] ffff88816644ee00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 107.009416][ T2278] ffff88816644ee80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 107.010161][ T2278] >ffff88816644ef00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 107.010907][ T2278] ^
[ 107.011471][ T2278] ffff88816644ef80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 107.012215][ T2278] ffff88816644f000: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 107.012967][ T2278] ==================================================================
[ 107.013787][ T2278] Disabling lock debugging due to kernel taint
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240214/202402141240.cc5aba78-oliver.sang@intel.com
@@ -202,6 +202,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
static void user_event_mm_put(struct user_event_mm *mm);
static int destroy_user_event(struct user_event *user);
+static bool user_fields_match(struct user_event *user, int argc,
+ const char **argv);
static u32 user_event_key(char *name)
{
@@ -1493,17 +1495,24 @@ static int destroy_user_event(struct user_event *user)
}
static struct user_event *find_user_event(struct user_event_group *group,
- char *name, u32 *outkey)
+ char *name, int argc, const char **argv,
+ u32 flags, u32 *outkey)
{
struct user_event *user;
u32 key = user_event_key(name);
*outkey = key;
- hash_for_each_possible(group->register_table, user, node, key)
- if (!strcmp(EVENT_NAME(user), name))
+ hash_for_each_possible(group->register_table, user, node, key) {
+ if (strcmp(EVENT_NAME(user), name))
+ continue;
+
+ if (user_fields_match(user, argc, argv))
return user_event_get(user);
+ return ERR_PTR(-EADDRINUSE);
+ }
+
return NULL;
}
@@ -1860,6 +1869,9 @@ static bool user_fields_match(struct user_event *user, int argc,
struct list_head *head = &user->fields;
int i = 0;
+ if (argc == 0)
+ return list_empty(head);
+
list_for_each_entry_reverse(field, head, link) {
if (!user_field_match(field, argc, argv, &i))
return false;
@@ -1880,10 +1892,8 @@ static bool user_event_match(const char *system, const char *event,
match = strcmp(EVENT_NAME(user), event) == 0 &&
(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
- if (match && argc > 0)
+ if (match)
match = user_fields_match(user, argc, argv);
- else if (match && argc == 0)
- match = list_empty(&user->fields);
return match;
}
@@ -1922,11 +1932,11 @@ static int user_event_parse(struct user_event_group *group, char *name,
char *args, char *flags,
struct user_event **newuser, int reg_flags)
{
- int ret;
- u32 key;
struct user_event *user;
+ char **argv = NULL;
int argc = 0;
- char **argv;
+ int ret;
+ u32 key;
/* Currently don't support any text based flags */
if (flags != NULL)
@@ -1935,41 +1945,34 @@ static int user_event_parse(struct user_event_group *group, char *name,
if (!user_event_capable(reg_flags))
return -EPERM;
+ if (args) {
+ argv = argv_split(GFP_KERNEL, args, &argc);
+
+ if (!argv)
+ return -ENOMEM;
+ }
+
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
- user = find_user_event(group, name, &key);
+ user = find_user_event(group, name, argc, (const char **)argv,
+ reg_flags, &key);
mutex_unlock(&event_mutex);
- if (user) {
- if (args) {
- argv = argv_split(GFP_KERNEL, args, &argc);
- if (!argv) {
- ret = -ENOMEM;
- goto error;
- }
+ if (argv)
+ argv_free(argv);
- ret = user_fields_match(user, argc, (const char **)argv);
- argv_free(argv);
-
- } else
- ret = list_empty(&user->fields);
-
- if (ret) {
- *newuser = user;
- /*
- * Name is allocated by caller, free it since it already exists.
- * Caller only worries about failure cases for freeing.
- */
- kfree(name);
- } else {
- ret = -EADDRINUSE;
- goto error;
- }
+ if (IS_ERR(user))
+ return PTR_ERR(user);
+
+ if (user) {
+ *newuser = user;
+ /*
+ * Name is allocated by caller, free it since it already exists.
+ * Caller only worries about failure cases for freeing.
+ */
+ kfree(name);
return 0;
-error:
- user_event_put(user, false);
- return ret;
}
user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
@@ -2052,25 +2055,32 @@ static int user_event_parse(struct user_event_group *group, char *name,
}
/*
- * Deletes a previously created event if it is no longer being used.
+ * Deletes previously created events if they are no longer being used.
*/
static int delete_user_event(struct user_event_group *group, char *name)
{
- u32 key;
- struct user_event *user = find_user_event(group, name, &key);
+ struct user_event *user;
+ u32 key = user_event_key(name);
+ int ret = -ENOENT;
- if (!user)
- return -ENOENT;
+ /* Attempt to delete all event(s) with the name passed in */
+ hash_for_each_possible(group->register_table, user, node, key) {
+ if (strcmp(EVENT_NAME(user), name))
+ continue;
- user_event_put(user, true);
+ if (!user_event_last_ref(user))
+ return -EBUSY;
- if (!user_event_last_ref(user))
- return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
- if (!user_event_capable(user->reg_flags))
- return -EPERM;
+ ret = destroy_user_event(user);
- return destroy_user_event(user);
+ if (ret)
+ goto out;
+ }
+out:
+ return ret;
}
/*