From 903575f1b008e275bae8e55adf12907efc012f72 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 29 Jan 2015 10:51:32 -0800 Subject: [PATCH] vm: add VM_FAULT_SIGSEGV handling support commit 33692f27597fcab536d7cbbcc8f52905133e4aa7 upstream. The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: Takashi Iwai Tested-by: Jan Engelhardt Acked-by: Heiko Carstens # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Signed-off-by: Linus Torvalds [ luis: backported to 3.16: - file renamed: arch/powerpc/mm/copro_fault.c -> arch/powerpc/platforms/cell/spu_fault.c - dropped changes to arch/nios2/mm/fault.c ] Signed-off-by: Luis Henriques --- arch/alpha/mm/fault.c | 2 ++ arch/arc/mm/fault.c | 2 ++ arch/avr32/mm/fault.c | 2 ++ arch/cris/mm/fault.c | 2 ++ arch/frv/mm/fault.c | 2 ++ arch/ia64/mm/fault.c | 2 ++ arch/m32r/mm/fault.c | 2 ++ arch/m68k/mm/fault.c | 2 ++ arch/metag/mm/fault.c | 2 ++ arch/microblaze/mm/fault.c | 2 ++ arch/mips/mm/fault.c | 2 ++ arch/mn10300/mm/fault.c | 2 ++ arch/openrisc/mm/fault.c | 2 ++ arch/parisc/mm/fault.c | 2 ++ arch/powerpc/mm/fault.c | 2 ++ arch/powerpc/platforms/cell/spu_fault.c | 2 +- arch/s390/mm/fault.c | 6 ++++++ arch/score/mm/fault.c | 2 ++ arch/sh/mm/fault.c | 2 ++ arch/sparc/mm/fault_32.c | 2 ++ arch/sparc/mm/fault_64.c | 2 ++ arch/tile/mm/fault.c | 2 ++ arch/um/kernel/trap.c | 2 ++ arch/x86/mm/fault.c | 2 ++ arch/xtensa/mm/fault.c | 2 ++ drivers/staging/lustre/lustre/llite/vvp_io.c | 2 +- include/linux/mm.h | 6 ++++-- mm/gup.c | 4 ++-- mm/ksm.c | 2 +- 29 files changed, 61 insertions(+), 7 deletions(-) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 98838a05ba6d8..9d0ac091a52a7 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -156,6 +156,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 9c69552350c49..15879a1f864cc 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -162,6 +162,8 @@ good_area: /* TBD: switch to pagefault_out_of_memory() */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 0eca933271950..d223a8b57c1ea 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -142,6 +142,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 1790f22e71a21..2686a7aa8ec82 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -176,6 +176,8 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 9a66372fc7c76..ec4917ddf6787 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 7225dad87094d..ba5ba7accd0d6 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -172,6 +172,8 @@ retry: */ if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto bad_area; } else if (fault & VM_FAULT_SIGBUS) { signal = SIGBUS; goto bad_area; diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index e9c6a8014bd64..e3d4d4890104c 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -200,6 +200,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 2bd7487440c45..b2f04aee46ecc 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -145,6 +145,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto map_err; else if (fault & VM_FAULT_SIGBUS) goto bus_err; BUG(); diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index 332680e5ebf23..2de5dc695a87f 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -141,6 +141,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index fa4cf52aa7a6d..d46a5ebb7570e 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -224,6 +224,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index becc42bb18495..70ab5d6643326 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -158,6 +158,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 3516cbdf1ee93..0c2cc5d39c8e3 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -262,6 +262,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 0703acf7d3276..230ac20ae7944 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -171,6 +171,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 3ca9c1131cfe0..e5120e653240c 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -256,6 +256,8 @@ good_area: */ if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto bad_area; BUG(); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 51ab9e7e6c391..010fabf3828c0 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -432,6 +432,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (fault & VM_FAULT_SIGSEGV) + goto bad_area; rc = mm_fault_error(regs, address, fault); if (rc >= MM_FAULT_RETURN) goto bail; diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c index 641e7273d75ae..62f3e4e48a0b2 100644 --- a/arch/powerpc/platforms/cell/spu_fault.c +++ b/arch/powerpc/platforms/cell/spu_fault.c @@ -75,7 +75,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea, if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; goto out_unlock; - } else if (*flt & VM_FAULT_SIGBUS) { + } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { ret = -EFAULT; goto out_unlock; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 3f3b35403d0a4..6da2b0bf6a325 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault) do_no_context(regs); else pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) + do_no_context(regs); + else + do_sigsegv(regs, SEGV_MAPERR); } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 52238983527d6..6860beb2a280d 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -114,6 +114,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 541dc61015088..a58fec9b55e01 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); + else if (fault & VM_FAULT_SIGSEGV) + bad_area(regs, error_code, address); else BUG(); } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 908e8c17c902b..70d817154fe8b 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -249,6 +249,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 18fcd71670959..4798232494294 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -446,6 +446,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 6c0571216a9d6..c6d2a76d91a81 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -444,6 +444,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 5678c3571e7cb..209617302df89 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -80,6 +80,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; + } else if (fault & VM_FAULT_SIGSEGV) { + goto out; } else if (fault & VM_FAULT_SIGBUS) { err = -EACCES; goto out; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 36642793e315f..6d0e5472a5e50 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -902,6 +902,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); + else if (fault & VM_FAULT_SIGSEGV) + bad_area_nosemaphore(regs, error_code, address); else BUG(); } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index b57c4f91f487e..9e3571a6535c3 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -117,6 +117,8 @@ good_area: if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; + else if (fault & VM_FAULT_SIGSEGV) + goto bad_area; else if (fault & VM_FAULT_SIGBUS) goto do_sigbus; BUG(); diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c index 0e0b404cb5e6c..3ade29c40f794 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_io.c +++ b/drivers/staging/lustre/lustre/llite/vvp_io.c @@ -629,7 +629,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio) return 0; } - if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) { + if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) { CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address); return -EFAULT; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 663ad81d3c66e..8ab91ce464870 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1033,6 +1033,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ +#define VM_FAULT_SIGSEGV 0x0040 #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ @@ -1041,8 +1042,9 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ - VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \ + VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ + VM_FAULT_FALLBACK) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) diff --git a/mm/gup.c b/mm/gup.c index cc5a9e7adea77..3840fdbad19eb 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -283,7 +283,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } @@ -551,7 +551,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } diff --git a/mm/ksm.c b/mm/ksm.c index 346ddc9e4c0da..691f1bf55858c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) else ret = VM_FAULT_WRITE; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM))); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop because handle_mm_fault() may back out if there's * any difficulty e.g. if pte accessed bit gets updated concurrently. -- 2.47.3