CVE-2022-50342

In the Linux kernel, the following vulnerability has been resolved:

floppy: Fix memory leak in dofloppyinit()

A memory leak was reported when floppyallocdisk() failed in dofloppyinit().

unreferenced object 0xffff888115ed25a0 (size 8): comm "modprobe", pid 727, jiffies 4295051278 (age 25.529s) hex dump (first 8 bytes): 00 ac 67 5b 81 88 ff ff ..g[.... backtrace: [<000000007f457abb>] __kmallocnode+0x4c/0xc0 [<00000000a87bfa9e>] blkmq_realloctagsettags.part.0+0x6f/0x180 [<000000006f02e8b1>] blkmqalloctagset+0x573/0x1130 [<0000000066007fd7>] 0xffffffffc06b8b08 [<0000000081f5ac40>] dooneinitcall+0xd0/0x4f0 [<00000000e26d04ee>] doinitmodule+0x1a4/0x680 [<000000001bb22407>] loadmodule+0x6249/0x7110 [<00000000ad31ac4d>] __dosysfinit_module+0x140/0x200 [<000000007bddca46>] dosyscall64+0x35/0x80 [<00000000b5afec39>] entrySYSCALL64afterhwframe+0x46/0xb0 unreferenced object 0xffff88810fc30540 (size 32): comm "modprobe", pid 727, jiffies 4295051278 (age 25.529s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000007f457abb>] __kmallocnode+0x4c/0xc0 [<000000006b91eab4>] blkmqalloctagset+0x393/0x1130 [<0000000066007fd7>] 0xffffffffc06b8b08 [<0000000081f5ac40>] dooneinitcall+0xd0/0x4f0 [<00000000e26d04ee>] doinitmodule+0x1a4/0x680 [<000000001bb22407>] loadmodule+0x6249/0x7110 [<00000000ad31ac4d>] _dosysfinitmodule+0x140/0x200 [<000000007bddca46>] dosyscall64+0x35/0x80 [<00000000b5afec39>] entrySYSCALL64afterhwframe+0x46/0xb0

If the floppyallocdisk() failed, disks of current drive will not be set, thus the lastest allocated set->tag cannot be freed in the error handling path. A simple call graph shown as below:

floppymoduleinit() floppyinit() dofloppyinit() for (drive = 0; drive < NDRIVE; drive++) blkmqalloctagset() blkmqalloctagsettags() blkmqrealloctagsettags() # set->tag allocated floppyallocdisk() blkmqalloc_disk() # error occurred, disks failed to allocated

   ->out_put_disk:
   for (drive = 0; drive < N_DRIVE; drive++)
     if (!disks[drive][0]) # the last disks is not set and loop break
       break;
     blk_mq_free_tag_set() # the latest allocated set->tag leaked

Fix this problem by free the set->tag of current drive before jump to error handling path.

[efremov: added stable list, changed title]