* [PATCH 1/2 v2] core dump: drop VM_ALWAYSDUMP flag
2012-03-08 21:29 [PATCH 0/2 v2] core dump: re-purpose VM_ALWAYSDUMP to user controlled VM_NODUMP Jason Baron
@ 2012-03-08 21:29 ` Jason Baron
2012-03-08 21:38 ` Roland McGrath
2012-03-08 21:29 ` [PATCH 2/2 v2] core dump: add VM_NODUMP, MADV_NODUMP, MADV_CLEAR_NODUMP Jason Baron
1 sibling, 1 reply; 6+ messages in thread
From: Jason Baron @ 2012-03-08 21:29 UTC (permalink / raw)
To: roland, akpm; +Cc: torvalds, avi, cmetcalf, linux-kernel
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 <jbaron@redhat.com>
---
arch/arm/kernel/process.c | 2 +-
arch/hexagon/kernel/vdso.c | 3 +--
arch/mips/kernel/vdso.c | 3 +--
arch/powerpc/kernel/vdso.c | 10 ++--------
arch/s390/kernel/vdso.c | 10 ++--------
arch/sh/kernel/vsyscall/vsyscall.c | 3 +--
arch/tile/mm/elf.c | 8 +-------
arch/unicore32/kernel/process.c | 2 +-
arch/x86/um/mem_32.c | 8 --------
arch/x86/um/vdso/vma.c | 3 +--
arch/x86/vdso/vdso32-setup.c | 17 ++---------------
arch/x86/vdso/vma.c | 3 +--
fs/binfmt_elf.c | 27 +++++++++++++++++++++++++--
include/linux/mm.h | 1 -
mm/memory.c | 8 +-------
15 files changed, 40 insertions(+), 68 deletions(-)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 971d65c..565ac89 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -536,7 +536,7 @@ int vectors_user_mapping(void)
return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
VM_READ | VM_EXEC |
VM_MAYREAD | VM_MAYEXEC |
- VM_ALWAYSDUMP | VM_RESERVED,
+ VM_RESERVED,
NULL);
}
diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c
index 16277c3..f212a45 100644
--- a/arch/hexagon/kernel/vdso.c
+++ b/arch/hexagon/kernel/vdso.c
@@ -78,8 +78,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
/* MAYWRITE to allow gdb to COW and set breakpoints. */
ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&vdso_page);
if (ret)
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index e5cdfd6..0f1af58 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -88,8 +88,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
ret = install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&vdso_page);
if (ret)
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 7d14bb6..d36ee10 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -263,17 +263,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
* the "data" page of the vDSO or you'll stop getting kernel updates
* and your nice userland gettimeofday will be totally dead.
* It's fine to use that for setting breakpoints in the vDSO code
- * pages though
- *
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
+ * pages though.
*/
rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pagelist);
if (rc) {
current->mm->context.vdso_base = 0;
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index d73630b..904df23 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -253,17 +253,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
* on the "data" page of the vDSO or you'll stop getting kernel
* updates and your nice userland gettimeofday will be totally dead.
* It's fine to use that for setting breakpoints in the vDSO code
- * pages though
- *
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
+ * pages though.
*/
rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pagelist);
if (rc)
current->mm->context.vdso_base = 0;
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index 1d6d51a..5ca5797 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -73,8 +73,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
ret = install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ | VM_EXEC |
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC |
- VM_ALWAYSDUMP,
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
syscall_pages);
if (unlikely(ret))
goto up_fail;
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 55e58e9..1a00fb6 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -117,17 +117,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
/*
* MAYWRITE to allow gdb to COW and set breakpoints
- *
- * Make sure the vDSO gets into every core dump. Dumping its
- * contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to
- * see what PC values meant.
*/
vdso_base = VDSO_BASE;
retval = install_special_mapping(mm, vdso_base, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pages);
#ifndef __tilegx__
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 52edc2b..432b429 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -381,7 +381,7 @@ int vectors_user_mapping(void)
return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
VM_READ | VM_EXEC |
VM_MAYREAD | VM_MAYEXEC |
- VM_ALWAYSDUMP | VM_RESERVED,
+ VM_RESERVED,
NULL);
}
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 639900a..f40281e 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -23,14 +23,6 @@ static int __init gate_vma_init(void)
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
gate_vma.vm_page_prot = __P101;
- /*
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
- */
- gate_vma.vm_flags |= VM_ALWAYSDUMP;
-
return 0;
}
__initcall(gate_vma_init);
diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c
index 91f4ec9..af91901 100644
--- a/arch/x86/um/vdso/vma.c
+++ b/arch/x86/um/vdso/vma.c
@@ -64,8 +64,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdsop);
up_write(&mm->mmap_sem);
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 468d591..a944020 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -250,13 +250,7 @@ static int __init gate_vma_init(void)
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
gate_vma.vm_page_prot = __P101;
- /*
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
- */
- gate_vma.vm_flags |= VM_ALWAYSDUMP;
+
return 0;
}
@@ -343,17 +337,10 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (compat_uses_vma || !compat) {
/*
* MAYWRITE to allow gdb to COW and set breakpoints
- *
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully
- * interpretable later without matching up the same
- * kernel and hardware config to see what PC values
- * meant.
*/
ret = install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso32_pages);
if (ret)
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 153407c..17e1827 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -124,8 +124,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
ret = install_special_mapping(mm, addr, vdso_size,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pages);
if (ret) {
current->mm->context.vdso = NULL;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 07d096c..93b7adb 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1095,6 +1095,29 @@ out:
*/
/*
+ * 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.
*/
static unsigned long vma_dump_size(struct vm_area_struct *vma,
@@ -1102,8 +1125,8 @@ 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 */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 17b27cd..a296709 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -111,7 +111,6 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HUGEPAGE 0x01000000 /* MADV_HUGEPAGE marked this vma */
#endif
#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */
-#define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */
#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
diff --git a/mm/memory.c b/mm/memory.c
index fa2f04e..9b55ab0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3611,13 +3611,7 @@ static int __init gate_vma_init(void)
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
gate_vma.vm_page_prot = __P101;
- /*
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
- */
- gate_vma.vm_flags |= VM_ALWAYSDUMP;
+
return 0;
}
__initcall(gate_vma_init);
--
1.7.7.6
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH 2/2 v2] core dump: add VM_NODUMP, MADV_NODUMP, MADV_CLEAR_NODUMP
2012-03-08 21:29 [PATCH 0/2 v2] core dump: re-purpose VM_ALWAYSDUMP to user controlled VM_NODUMP Jason Baron
2012-03-08 21:29 ` [PATCH 1/2 v2] core dump: drop VM_ALWAYSDUMP flag Jason Baron
@ 2012-03-08 21:29 ` Jason Baron
2012-03-08 21:44 ` Roland McGrath
1 sibling, 1 reply; 6+ messages in thread
From: Jason Baron @ 2012-03-08 21:29 UTC (permalink / raw)
To: roland, akpm; +Cc: torvalds, avi, cmetcalf, linux-kernel
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_NODUMP,
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_CLEAR_NODUMP.
Signed-off-by: Jason Baron <jbaron@redhat.com>
---
fs/binfmt_elf.c | 3 +++
include/asm-generic/mman-common.h | 4 ++++
include/linux/mm.h | 1 +
mm/madvise.c | 8 ++++++++
4 files changed, 16 insertions(+), 0 deletions(-)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 93b7adb..2bbf26f 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1129,6 +1129,9 @@ 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))
diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h
index 787abbb..57e6324 100644
--- a/include/asm-generic/mman-common.h
+++ b/include/asm-generic/mman-common.h
@@ -48,6 +48,10 @@
#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */
#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */
+#define MADV_NODUMP 16 /* Explicity exclude from the core dump,
+ overrides the coredump filter bits */
+#define MADV_CLEAR_NODUMP 17 /* Clear the MADV_NODUMP flag */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a296709..c3b70b5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -111,6 +111,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HUGEPAGE 0x01000000 /* MADV_HUGEPAGE marked this vma */
#endif
#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */
+#define VM_NODUMP 0x04000000 /* Do not include in the core dump */
#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
diff --git a/mm/madvise.c b/mm/madvise.c
index 74bf193..eb89826 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -65,6 +65,12 @@ static long madvise_behavior(struct vm_area_struct * vma,
}
new_flags &= ~VM_DONTCOPY;
break;
+ case MADV_NODUMP:
+ new_flags |= VM_NODUMP;
+ break;
+ case MADV_CLEAR_NODUMP:
+ new_flags &= ~VM_NODUMP;
+ break;
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
error = ksm_madvise(vma, start, end, behavior, &new_flags);
@@ -293,6 +299,8 @@ madvise_behavior_valid(int behavior)
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
#endif
+ case MADV_NODUMP:
+ case MADV_CLEAR_NODUMP:
return 1;
default:
--
1.7.7.6
^ permalink raw reply related [flat|nested] 6+ messages in thread