Increase kasan instrumented kernel stack size from 32k to 64k. Other
architectures seems to get away with just doubling kernel stack size under
kasan, but on s390 this appears to be not enough due to bigger frame size.
The particular pain point is kasan inlined checks (CONFIG_KASAN_INLINE
vs CONFIG_KASAN_OUTLINE). With inlined checks one particular case hitting
stack overflow is fs sync on xfs filesystem:
#0 [
9a0681e8] 704 bytes check_usage at 34b1fc
#1 [
9a0684a8] 432 bytes check_usage at 34c710
#2 [
9a068658] 1048 bytes validate_chain at 35044a
#3 [
9a068a70] 312 bytes __lock_acquire at 3559fe
#4 [
9a068ba8] 440 bytes lock_acquire at 3576ee
#5 [
9a068d60] 104 bytes _raw_spin_lock at
21b44e0
#6 [
9a068dc8] 1992 bytes enqueue_entity at 2dbf72
#7 [
9a069590] 1496 bytes enqueue_task_fair at 2df5f0
#8 [
9a069b68] 64 bytes ttwu_do_activate at 28f438
#9 [
9a069ba8] 552 bytes try_to_wake_up at 298c4c
#10 [
9a069dd0] 168 bytes wake_up_worker at 23f97c
#11 [
9a069e78] 200 bytes insert_work at 23fc2e
#12 [
9a069f40] 648 bytes __queue_work at 2487c0
#13 [
9a06a1c8] 200 bytes __queue_delayed_work at 24db28
#14 [
9a06a290] 248 bytes mod_delayed_work_on at 24de84
#15 [
9a06a388] 24 bytes kblockd_mod_delayed_work_on at
153e2a0
#16 [
9a06a3a0] 288 bytes __blk_mq_delay_run_hw_queue at
158168c
#17 [
9a06a4c0] 192 bytes blk_mq_run_hw_queue at
1581a3c
#18 [
9a06a580] 184 bytes blk_mq_sched_insert_requests at
15a2192
#19 [
9a06a638] 1024 bytes blk_mq_flush_plug_list at
1590f3a
#20 [
9a06aa38] 704 bytes blk_flush_plug_list at
1555028
#21 [
9a06acf8] 320 bytes schedule at
219e476
#22 [
9a06ae38] 760 bytes schedule_timeout at
21b0aac
#23 [
9a06b130] 408 bytes wait_for_common at
21a1706
#24 [
9a06b2c8] 360 bytes xfs_buf_iowait at fa1540
#25 [
9a06b430] 256 bytes __xfs_buf_submit at fadae6
#26 [
9a06b530] 264 bytes xfs_buf_read_map at fae3f6
#27 [
9a06b638] 656 bytes xfs_trans_read_buf_map at
10ac9a8
#28 [
9a06b8c8] 304 bytes xfs_btree_kill_root at e72426
#29 [
9a06b9f8] 288 bytes xfs_btree_lookup_get_block at e7bc5e
#30 [
9a06bb18] 624 bytes xfs_btree_lookup at e7e1a6
#31 [
9a06bd88] 2664 bytes xfs_alloc_ag_vextent_near at dfa070
#32 [
9a06c7f0] 144 bytes xfs_alloc_ag_vextent at dff3ca
#33 [
9a06c880] 1128 bytes xfs_alloc_vextent at e05fce
#34 [
9a06cce8] 584 bytes xfs_bmap_btalloc at e58342
#35 [
9a06cf30] 1336 bytes xfs_bmapi_write at e618de
#36 [
9a06d468] 776 bytes xfs_iomap_write_allocate at ff678e
#37 [
9a06d770] 720 bytes xfs_map_blocks at f82af8
#38 [
9a06da40] 928 bytes xfs_writepage_map at f83cd6
#39 [
9a06dde0] 320 bytes xfs_do_writepage at f85872
#40 [
9a06df20] 1320 bytes write_cache_pages at 73dfe8
#41 [
9a06e448] 208 bytes xfs_vm_writepages at f7f892
#42 [
9a06e518] 88 bytes do_writepages at 73fe6a
#43 [
9a06e570] 872 bytes __writeback_single_inode at a20cb6
#44 [
9a06e8d8] 664 bytes writeback_sb_inodes at a23be2
#45 [
9a06eb70] 296 bytes __writeback_inodes_wb at a242e0
#46 [
9a06ec98] 928 bytes wb_writeback at a2500e
#47 [
9a06f038] 848 bytes wb_do_writeback at a260ae
#48 [
9a06f388] 536 bytes wb_workfn at a28228
#49 [
9a06f5a0] 1088 bytes process_one_work at 24a234
#50 [
9a06f9e0] 1120 bytes worker_thread at 24ba26
#51 [
9a06fe40] 104 bytes kthread at 26545a
#52 [
9a06fea8] kernel_thread_starter at
21b6b62
To be able to increase the stack size to 64k reuse LLILL instruction
in __switch_to function to load 64k - STACK_FRAME_OVERHEAD - __PT_SIZE
(65192) value as unsigned.
Reported-by: Benjamin Block <bblock@linux.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
UTS_MACHINE := s390x
-STACK_SIZE := $(if $(CONFIG_KASAN),32768,16384)
+STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384)
CHECKFLAGS += -D__s390__ -D__s390x__
export LD_BFD
* General size of kernel stacks
*/
#ifdef CONFIG_KASAN
-#define THREAD_SIZE_ORDER 3
+#define THREAD_SIZE_ORDER 4
#else
#define THREAD_SIZE_ORDER 2
#endif
stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task
lghi %r4,__TASK_stack
lghi %r1,__TASK_thread
- lg %r5,0(%r4,%r3) # start of kernel stack of next
+ llill %r5,STACK_INIT
stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev
- lgr %r15,%r5
- aghi %r15,STACK_INIT # end of kernel stack of next
+ lg %r15,0(%r4,%r3) # start of kernel stack of next
+ agr %r15,%r5 # end of kernel stack of next
stg %r3,__LC_CURRENT # store task struct of next
stg %r15,__LC_KERNEL_STACK # store end of kernel stack
lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next