From 8fc3dc5a3a17aa2b353886422bd89420619af211 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 17 Mar 2012 03:05:16 -0400 Subject: __register_binfmt() made void Just don't pass NULL to it - nobody does, anyway. Signed-off-by: Al Viro --- fs/binfmt_elf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 07d096c49920..f8ac4251877e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2077,7 +2077,8 @@ out: static int __init init_elf_binfmt(void) { - return register_binfmt(&elf_format); + register_binfmt(&elf_format); + return 0; } static void __exit exit_elf_binfmt(void) -- cgit v1.2.3 From 19e5109fef2c368ab3f8a5157270f87f4a7c0326 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 23 Feb 2012 22:29:17 -0500 Subject: take removal of PF_FORKNOEXEC to flush_old_exec() Signed-off-by: Al Viro --- fs/binfmt_elf.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f8ac4251877e..81878b78c9d4 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -712,7 +712,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) goto out_free_dentry; /* OK, This is the point of no return */ - current->flags &= ~PF_FORKNOEXEC; current->mm->def_flags = def_flags; /* Do this immediately, since STACK_TOP as used in setup_arg_pages @@ -934,7 +933,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; retval = create_elf_tables(bprm, &loc->elf_ex, load_addr, interp_load_addr); if (retval < 0) { -- cgit v1.2.3 From 909af768e88867016f427264ae39d27a57b6a8ed Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 23 Mar 2012 15:02:51 -0700 Subject: coredump: remove VM_ALWAYSDUMP flag The motivation for this patchset was that I was looking at a way for a qemu-kvm process, to exclude the guest memory from its core dump, which can be quite large. There are already a number of filter flags in /proc//coredump_filter, however, these allow one to specify 'types' of kernel memory, not specific address ranges (which is needed in this case). Since there are no more vma flags available, the first patch eliminates the need for the 'VM_ALWAYSDUMP' flag. The flag is used internally by the kernel to mark vdso and vsyscall pages. However, it is simple enough to check if a vma covers a vdso or vsyscall page without the need for this flag. The second patch then replaces the 'VM_ALWAYSDUMP' flag with a new 'VM_NODUMP' flag, which can be set by userspace using new madvise flags: 'MADV_DONTDUMP', and unset via 'MADV_DODUMP'. The core dump filters continue to work the same as before unless 'MADV_DONTDUMP' is set on the region. The qemu code which implements this features is at: http://people.redhat.com/~jbaron/qemu-dump/qemu-dump.patch In my testing the qemu core dump shrunk from 383MB -> 13MB with this patch. I also believe that the 'MADV_DONTDUMP' flag might be useful for security sensitive apps, which might want to select which areas are dumped. This patch: The VM_ALWAYSDUMP flag is currently used by the coredump code to indicate that a vma is part of a vsyscall or vdso section. However, we can determine if a vma is in one these sections by checking it against the gate_vma and checking for a non-NULL return value from arch_vma_name(). Thus, freeing a valuable vma bit. Signed-off-by: Jason Baron Acked-by: Roland McGrath Cc: Chris Metcalf Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 81878b78c9d4..b64be5b5ac21 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1092,6 +1092,29 @@ out: * Jeremy Fitzhardinge */ +/* + * The purpose of always_dump_vma() is to make sure that special kernel mappings + * that are useful for post-mortem analysis are included in every core dump. + * In that way we ensure that the core dump is fully interpretable later + * without matching up the same kernel and hardware config to see what PC values + * meant. These special mappings include - vDSO, vsyscall, and other + * architecture specific mappings + */ +static bool always_dump_vma(struct vm_area_struct *vma) +{ + /* Any vsyscall mappings? */ + if (vma == get_gate_vma(vma->vm_mm)) + return true; + /* + * arch_vma_name() returns non-NULL for special architecture mappings, + * such as vDSO sections. + */ + if (arch_vma_name(vma)) + return true; + + return false; +} + /* * Decide what to dump of a segment, part, all or none. */ @@ -1100,8 +1123,8 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, { #define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type)) - /* The vma can be set up to tell us the answer directly. */ - if (vma->vm_flags & VM_ALWAYSDUMP) + /* always dump the vdso and vsyscall sections */ + if (always_dump_vma(vma)) goto whole; /* Hugetlb memory check */ -- cgit v1.2.3 From accb61fe7bb0f5c2a4102239e4981650f9048519 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 23 Mar 2012 15:02:51 -0700 Subject: coredump: add VM_NODUMP, MADV_NODUMP, MADV_CLEAR_NODUMP Since we no longer need the VM_ALWAYSDUMP flag, let's use the freed bit for 'VM_NODUMP' flag. The idea is is to add a new madvise() flag: MADV_DONTDUMP, which can be set by applications to specifically request memory regions which should not dump core. The specific application I have in mind is qemu: we can add a flag there that wouldn't dump all of guest memory when qemu dumps core. This flag might also be useful for security sensitive apps that want to absolutely make sure that parts of memory are not dumped. To clear the flag use: MADV_DODUMP. [akpm@linux-foundation.org: s/MADV_NODUMP/MADV_DONTDUMP/, s/MADV_CLEAR_NODUMP/MADV_DODUMP/, per Roland] [akpm@linux-foundation.org: fix up the architectures which broke] Signed-off-by: Jason Baron Acked-by: Roland McGrath Cc: Chris Metcalf Cc: Avi Kivity Cc: Ralf Baechle Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: "James E.J. Bottomley" Cc: Helge Deller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index b64be5b5ac21..504b6eee50a9 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1127,6 +1127,9 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, if (always_dump_vma(vma)) goto whole; + if (vma->vm_flags & VM_NODUMP) + return 0; + /* Hugetlb memory check */ if (vma->vm_flags & VM_HUGETLB) { if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED)) -- cgit v1.2.3 From 96f951edb1f1bdbbc99b0cd458f9808bb83d58ae Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 Mar 2012 18:30:03 +0100 Subject: Add #includes needed to permit the removal of asm/system.h asm/system.h is a cause of circular dependency problems because it contains commonly used primitive stuff like barrier definitions and uncommonly used stuff like switch_to() that might require MMU definitions. asm/system.h has been disintegrated by this point on all arches into the following common segments: (1) asm/barrier.h Moved memory barrier definitions here. (2) asm/cmpxchg.h Moved xchg() and cmpxchg() here. #included in asm/atomic.h. (3) asm/bug.h Moved die() and similar here. (4) asm/exec.h Moved arch_align_stack() here. (5) asm/elf.h Moved AT_VECTOR_SIZE_ARCH here. (6) asm/switch_to.h Moved switch_to() here. Signed-off-by: David Howells --- fs/binfmt_elf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 81878b78c9d4..18276531f7c6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -35,6 +35,7 @@ #include #include #include +#include static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs); static int load_elf_library(struct file *); -- cgit v1.2.3