From b0a0c2566f28e71e5e32121992ac8060cec75510 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 4 Aug 2017 14:20:54 +0200 Subject: bpf, s390: fix jit branch offset related to ldimm64 While testing some other work that required JIT modifications, I run into test_bpf causing a hang when JIT enabled on s390. The problematic test case was the one from ddc665a4bb4b (bpf, arm64: fix jit branch offset related to ldimm64), and turns out that we do have a similar issue on s390 as well. In bpf_jit_prog() we update next instruction address after returning from bpf_jit_insn() with an insn_count. bpf_jit_insn() returns either -1 in case of error (e.g. unsupported insn), 1 or 2. The latter is only the case for ldimm64 due to spanning 2 insns, however, next address is only set to i + 1 not taking actual insn_count into account, thus fix is to use insn_count instead of 1. bpf_jit_enable in mode 2 provides also disasm on s390: Before fix: 000003ff800349b6: a7f40003 brc 15,3ff800349bc ; target 000003ff800349ba: 0000 unknown 000003ff800349bc: e3b0f0700024 stg %r11,112(%r15) 000003ff800349c2: e3e0f0880024 stg %r14,136(%r15) 000003ff800349c8: 0db0 basr %r11,%r0 000003ff800349ca: c0ef00000000 llilf %r14,0 000003ff800349d0: e320b0360004 lg %r2,54(%r11) 000003ff800349d6: e330b03e0004 lg %r3,62(%r11) 000003ff800349dc: ec23ffeda065 clgrj %r2,%r3,10,3ff800349b6 ; jmp 000003ff800349e2: e3e0b0460004 lg %r14,70(%r11) 000003ff800349e8: e3e0b04e0004 lg %r14,78(%r11) 000003ff800349ee: b904002e lgr %r2,%r14 000003ff800349f2: e3b0f0700004 lg %r11,112(%r15) 000003ff800349f8: e3e0f0880004 lg %r14,136(%r15) 000003ff800349fe: 07fe bcr 15,%r14 After fix: 000003ff80ef3db4: a7f40003 brc 15,3ff80ef3dba 000003ff80ef3db8: 0000 unknown 000003ff80ef3dba: e3b0f0700024 stg %r11,112(%r15) 000003ff80ef3dc0: e3e0f0880024 stg %r14,136(%r15) 000003ff80ef3dc6: 0db0 basr %r11,%r0 000003ff80ef3dc8: c0ef00000000 llilf %r14,0 000003ff80ef3dce: e320b0360004 lg %r2,54(%r11) 000003ff80ef3dd4: e330b03e0004 lg %r3,62(%r11) 000003ff80ef3dda: ec230006a065 clgrj %r2,%r3,10,3ff80ef3de6 ; jmp 000003ff80ef3de0: e3e0b0460004 lg %r14,70(%r11) 000003ff80ef3de6: e3e0b04e0004 lg %r14,78(%r11) ; target 000003ff80ef3dec: b904002e lgr %r2,%r14 000003ff80ef3df0: e3b0f0700004 lg %r11,112(%r15) 000003ff80ef3df6: e3e0f0880004 lg %r14,136(%r15) 000003ff80ef3dfc: 07fe bcr 15,%r14 test_bpf.ko suite runs fine after the fix. Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Signed-off-by: Daniel Borkmann Tested-by: Michael Holzheu Signed-off-by: David S. Miller --- arch/s390/net/bpf_jit_comp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 01c6fbc3e85b..1803797fc885 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1253,7 +1253,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) insn_count = bpf_jit_insn(jit, fp, i); if (insn_count < 0) return -1; - jit->addrs[i + 1] = jit->prg; /* Next instruction address */ + /* Next instruction address */ + jit->addrs[i + insn_count] = jit->prg; } bpf_jit_epilogue(jit); -- 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 --- arch/s390/include/asm/tlb.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 7317b3108a88..d574d0820dc8 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -47,10 +47,9 @@ struct mmu_table_batch { extern void tlb_table_flush(struct mmu_gather *tlb); extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -static inline void tlb_gather_mmu(struct mmu_gather *tlb, - struct mm_struct *mm, - unsigned long start, - unsigned long end) +static inline void +arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) { tlb->mm = mm; tlb->start = start; @@ -76,8 +75,9 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -static inline void tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end) +static inline void +arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end) { tlb_flush_mmu(tlb); } -- 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 --- arch/s390/include/asm/tlb.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index d574d0820dc8..2eb8ff0d6fca 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -77,8 +77,13 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) static inline void arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, bool force) { + if (force) { + tlb->start = start; + tlb->end = end; + } + tlb_flush_mmu(tlb); } -- cgit v1.2.3