From cb87481ee89dbd6609e227afbf64900fb4e5c930 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 26 Jul 2017 22:46:27 +1000 Subject: kbuild: linker script do not match C names unless LD_DEAD_CODE_DATA_ELIMINATION is configured The .data and .bss sections were modified in the generic linker script to pull in sections named .data., which are generated by gcc with -ffunction-sections and -fdata-sections options. The problem with this pattern is it can also match section names that Linux defines explicitly, e.g., .data.unlikely. This can cause Linux sections to get moved into the wrong place. The way to avoid this is to use ".." separators for explicit section names (the dot character is valid in a section name but not a C identifier). However currently there are sections which don't follow this rule, so for now just disable the wild card by default. Example: http://marc.info/?l=linux-arm-kernel&m=150106824024221&w=2 Cc: # 4.9 Fixes: b67067f1176df ("kbuild: allow archs to select link dead code/data elimination") Signed-off-by: Nicholas Piggin Signed-off-by: Masahiro Yamada --- include/asm-generic/vmlinux.lds.h | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index da0be9a8d1de..9623d78f8494 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -59,6 +59,22 @@ /* Align . to a 8 byte boundary equals to maximum function alignment. */ #define ALIGN_FUNCTION() . = ALIGN(8) +/* + * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which + * generates .data.identifier sections, which need to be pulled in with + * .data. We don't want to pull in .data..other sections, which Linux + * has defined. Same for text and bss. + */ +#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION +#define TEXT_MAIN .text .text.[0-9a-zA-Z_]* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* +#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* +#else +#define TEXT_MAIN .text +#define DATA_MAIN .data +#define BSS_MAIN .bss +#endif + /* * Align to a 32 byte boundary equal to the * alignment gcc 4.5 uses for a struct @@ -198,12 +214,9 @@ /* * .data section - * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates - * .data.identifier which needs to be pulled in with .data, but don't want to - * pull in .data..stuff which has its own requirements. Same for bss. */ #define DATA_DATA \ - *(.data .data.[0-9a-zA-Z_]*) \ + *(DATA_MAIN) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data) \ @@ -434,16 +447,17 @@ VMLINUX_SYMBOL(__security_initcall_end) = .; \ } -/* .text section. Map to function alignment to avoid address changes +/* + * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map - * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates - * .text.identifier which needs to be pulled in with .text , but some - * architectures define .text.foo which is not intended to be pulled in here. - * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have - * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */ + * + * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead + * code elimination is enabled, so these sections should be converted + * to use ".." first. + */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot .text .text.fixup .text.unlikely) \ + *(.text.hot TEXT_MAIN .text.fixup .text.unlikely) \ *(.ref.text) \ MEM_KEEP(init.text) \ MEM_KEEP(exit.text) \ @@ -613,7 +627,7 @@ BSS_FIRST_SECTIONS \ *(.bss..page_aligned) \ *(.dynbss) \ - *(.bss .bss.[0-9a-zA-Z_]*) \ + *(BSS_MAIN) \ *(COMMON) \ } -- cgit v1.2.3 From 56236a59556cfd3bae7bffb7e5f438b5ef0af880 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:05 -0700 Subject: mm: refactor TLB gathering API This patch is a preparatory patch for solving race problems caused by TLB batch. For that, we will increase/decrease TLB flush pending count of mm_struct whenever tlb_[gather|finish]_mmu is called. Before making it simple, this patch separates architecture specific part and rename it to arch_tlb_[gather|finish]_mmu and generic part just calls it. It shouldn't change any behavior. Link: http://lkml.kernel.org/r/20170802000818.4760-5-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Acked-by: Mel Gorman Cc: Ingo Molnar Cc: Russell King Cc: Tony Luck Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Jeff Dike Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Hugh Dickins Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 8afa4335e5b2..8f71521e7a44 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -112,10 +112,11 @@ struct mmu_gather { #define HAVE_GENERIC_MMU_GATHER -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); +void arch_tlb_gather_mmu(struct mmu_gather *tlb, + struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); -void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, - unsigned long end); +void arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); -- cgit v1.2.3 From 99baac21e4585f4258f919502c6e23f1e5edc98c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 10 Aug 2017 15:24:12 -0700 Subject: mm: fix MADV_[FREE|DONTNEED] TLB flush miss problem Nadav reported parallel MADV_DONTNEED on same range has a stale TLB problem and Mel fixed it[1] and found same problem on MADV_FREE[2]. Quote from Mel Gorman: "The race in question is CPU 0 running madv_free and updating some PTEs while CPU 1 is also running madv_free and looking at the same PTEs. CPU 1 may have writable TLB entries for a page but fail the pte_dirty check (because CPU 0 has updated it already) and potentially fail to flush. Hence, when madv_free on CPU 1 returns, there are still potentially writable TLB entries and the underlying PTE is still present so that a subsequent write does not necessarily propagate the dirty bit to the underlying PTE any more. Reclaim at some unknown time at the future may then see that the PTE is still clean and discard the page even though a write has happened in the meantime. I think this is possible but I could have missed some protection in madv_free that prevents it happening." This patch aims for solving both problems all at once and is ready for other problem with KSM, MADV_FREE and soft-dirty story[3]. TLB batch API(tlb_[gather|finish]_mmu] uses [inc|dec]_tlb_flush_pending and mmu_tlb_flush_pending so that when tlb_finish_mmu is called, we can catch there are parallel threads going on. In that case, forcefully, flush TLB to prevent for user to access memory via stale TLB entry although it fail to gather page table entry. I confirmed this patch works with [4] test program Nadav gave so this patch supersedes "mm: Always flush VMA ranges affected by zap_page_range v2" in current mmotm. NOTE: This patch modifies arch-specific TLB gathering interface(x86, ia64, s390, sh, um). It seems most of architecture are straightforward but s390 need to be careful because tlb_flush_mmu works only if mm->context.flush_mm is set to non-zero which happens only a pte entry really is cleared by ptep_get_and_clear and friends. However, this problem never changes the pte entries but need to flush to prevent memory access from stale tlb. [1] http://lkml.kernel.org/r/20170725101230.5v7gvnjmcnkzzql3@techsingularity.net [2] http://lkml.kernel.org/r/20170725100722.2dxnmgypmwnrfawp@suse.de [3] http://lkml.kernel.org/r/BD3A0EBE-ECF4-41D4-87FA-C755EA9AB6BD@gmail.com [4] https://patchwork.kernel.org/patch/9861621/ [minchan@kernel.org: decrease tlb flush pending count in tlb_finish_mmu] Link: http://lkml.kernel.org/r/20170808080821.GA31730@bbox Link: http://lkml.kernel.org/r/20170802000818.4760-7-namit@vmware.com Signed-off-by: Minchan Kim Signed-off-by: Nadav Amit Reported-by: Nadav Amit Reported-by: Mel Gorman Acked-by: Mel Gorman Cc: Ingo Molnar Cc: Russell King Cc: Tony Luck Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Jeff Dike Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Hugh Dickins Cc: Mel Gorman Cc: Nadav Amit Cc: Rik van Riel Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 8f71521e7a44..faddde44de8c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -116,7 +116,7 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool force); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); -- cgit v1.2.3