From e12e4044aede97974f2222eb7f0ed726a5179a32 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 11:09:16 +0200 Subject: s390/mm: fix mis-accounting of pgtable_bytes In case a fork or a clone system fails in copy_process and the error handling does the mmput() at the bad_fork_cleanup_mm label, the following warning messages will appear on the console: BUG: non-zero pgtables_bytes on freeing mm: 16384 The reason for that is the tricks we play with mm_inc_nr_puds() and mm_inc_nr_pmds() in init_new_context(). A normal 64-bit process has 3 levels of page table, the p4d level and the pud level are folded. On process termination the free_pud_range() function in mm/memory.c will subtract 16KB from pgtable_bytes with a mm_dec_nr_puds() call, but there actually is not really a pud table. One issue with this is the fact that pgtable_bytes is usually off by a few kilobytes, but the more severe problem is that for a failed fork or clone the free_pgtables() function is not called. In this case there is no mm_dec_nr_puds() or mm_dec_nr_pmds() that go together with the mm_inc_nr_puds() and mm_inc_nr_pmds in init_new_context(). The pgtable_bytes will be off by 16384 or 32768 bytes and we get the BUG message. The message itself is purely cosmetic, but annoying. To fix this override the mm_pmd_folded, mm_pud_folded and mm_p4d_folded function to check for the true size of the address space. Reported-by: Li Wang Tested-by: Li Wang Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/mmu_context.h | 5 ----- arch/s390/include/asm/pgalloc.h | 6 +++--- arch/s390/include/asm/pgtable.h | 18 ++++++++++++++++++ arch/s390/include/asm/tlb.h | 6 +++--- 4 files changed, 24 insertions(+), 11 deletions(-) (limited to 'arch/s390/include') diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index dbd689d556ce..ccbb53e22024 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; - /* pgd_alloc() did not account this pud */ - mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not account this pmd */ - mm_inc_nr_pmds(mm); - mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index f0f9bcf94c03..5ee733720a57 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry) static inline unsigned long pgd_entry_type(struct mm_struct *mm) { - if (mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(mm)) return _SEGMENT_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(mm)) return _REGION3_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(mm)) return _REGION2_ENTRY_EMPTY; return _REGION1_ENTRY_EMPTY; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 411d435e7a7d..063732414dfb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr) _REGION_ENTRY_PROTECT | \ _REGION_ENTRY_NOEXEC) +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION1_SIZE; +} +#define mm_p4d_folded(mm) mm_p4d_folded(mm) + +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION2_SIZE; +} +#define mm_pud_folded(mm) mm_pud_folded(mm) + +static inline bool mm_pmd_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION3_SIZE; +} +#define mm_pmd_folded(mm) mm_pmd_folded(mm) + static inline int mm_has_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..b31c779cf581 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); @@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(tlb->mm)) return; tlb_remove_table(tlb, p4d); } @@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(tlb->mm)) return; tlb_remove_table(tlb, pud); } -- cgit v1.2.3 From 9fed920e6817218ad786c3f28e14b4c877cc2aed Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 26 Oct 2018 15:29:59 +0200 Subject: s390/kasan: increase instrumented stack size to 64k 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 Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/Makefile | 2 +- arch/s390/include/asm/thread_info.h | 2 +- arch/s390/kernel/entry.S | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/s390/include') diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 0b33577932c3..e21053e5e0da 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) 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 diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 27248f42a03c..ce4e17c9aad6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,7 +14,7 @@ * 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 diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 724fba4d09d2..39191a0feed1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -236,10 +236,10 @@ ENTRY(__switch_to) 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 -- cgit v1.2.3