From 0953f65d5db728df0fdc3d510a71fd811a3be758 Mon Sep 17 00:00:00 2001 From: "H. J. Lu" Date: Tue, 14 Feb 2012 13:34:52 -0800 Subject: elf: Allow core dump-related fields to be overridden Allow some core dump-related fields to be overridden. This allows core dumps to work correctly for x32. Signed-off-by: H. Peter Anvin Cc: Alexander Viro Cc: Roland McGrath Cc: Oleg Nesterov --- fs/binfmt_elf.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bcb884e2d613..43ba478c3386 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1390,6 +1390,22 @@ static void do_thread_regset_writeback(struct task_struct *task, regset->writeback(task, regset, 1); } +#ifndef PR_REG_SIZE +#define PR_REG_SIZE(S) sizeof(S) +#endif + +#ifndef PRSTATUS_SIZE +#define PRSTATUS_SIZE(S) sizeof(S) +#endif + +#ifndef PR_REG_PTR +#define PR_REG_PTR(S) (&((S)->pr_reg)) +#endif + +#ifndef SET_PR_FPVALID +#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V)) +#endif + static int fill_thread_core_info(struct elf_thread_core_info *t, const struct user_regset_view *view, long signr, size_t *total) @@ -1404,11 +1420,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, */ fill_prstatus(&t->prstatus, t->task, signr); (void) view->regsets[0].get(t->task, &view->regsets[0], - 0, sizeof(t->prstatus.pr_reg), - &t->prstatus.pr_reg, NULL); + 0, PR_REG_SIZE(t->prstatus.pr_reg), + PR_REG_PTR(&t->prstatus), NULL); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - sizeof(t->prstatus), &t->prstatus); + PRSTATUS_SIZE(t->prstatus), &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1438,7 +1454,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, regset->core_note_type, size, data); else { - t->prstatus.pr_fpvalid = 1; + SET_PR_FPVALID(&t->prstatus, 1); fill_note(&t->notes[i], "CORE", NT_PRFPREG, size, data); } -- cgit v1.2.3 From c8e252586f8d5de906385d8cf6385fee289a825e Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 2 Mar 2012 10:43:48 -0800 Subject: regset: Prevent null pointer reference on readonly regsets The regset common infrastructure assumed that regsets would always have .get and .set methods, but not necessarily .active methods. Unfortunately people have since written regsets without .set methods. Rather than putting in stub functions everywhere, handle regsets with null .get or .set methods explicitly. Signed-off-by: H. Peter Anvin Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Cc: Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 2 +- include/linux/regset.h | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'fs/binfmt_elf.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index bcb884e2d613..07d096c49920 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1421,7 +1421,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, for (i = 1; i < view->n; ++i) { const struct user_regset *regset = &view->regsets[i]; do_thread_regset_writeback(t->task, regset); - if (regset->core_note_type && + if (regset->core_note_type && regset->get && (!regset->active || regset->active(t->task, regset))) { int ret; size_t size = regset->n * regset->size; diff --git a/include/linux/regset.h b/include/linux/regset.h index 8abee6556223..5150fd16ef93 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -335,6 +335,9 @@ static inline int copy_regset_to_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->get) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_WRITE, data, size)) return -EIO; @@ -358,6 +361,9 @@ static inline int copy_regset_from_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->set) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_READ, data, size)) return -EIO; -- cgit v1.2.3 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 --- arch/alpha/kernel/binfmt_loader.c | 3 ++- arch/x86/ia32/ia32_aout.c | 3 ++- fs/binfmt_aout.c | 3 ++- fs/binfmt_elf.c | 3 ++- fs/binfmt_elf_fdpic.c | 3 ++- fs/binfmt_em86.c | 3 ++- fs/binfmt_flat.c | 3 ++- fs/binfmt_misc.c | 7 ++----- fs/binfmt_script.c | 3 ++- fs/binfmt_som.c | 3 ++- fs/exec.c | 6 ++---- include/linux/binfmts.h | 10 +++++----- 12 files changed, 27 insertions(+), 23 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/arch/alpha/kernel/binfmt_loader.c b/arch/alpha/kernel/binfmt_loader.c index 3fcfad410130..d1f474d1d44d 100644 --- a/arch/alpha/kernel/binfmt_loader.c +++ b/arch/alpha/kernel/binfmt_loader.c @@ -46,6 +46,7 @@ static struct linux_binfmt loader_format = { static int __init init_loader_binfmt(void) { - return insert_binfmt(&loader_format); + insert_binfmt(&loader_format); + return 0; } arch_initcall(init_loader_binfmt); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 39e49091f648..cdfc8dc43670 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -519,7 +519,8 @@ out: static int __init init_aout_binfmt(void) { - return register_binfmt(&aout_format); + register_binfmt(&aout_format); + return 0; } static void __exit exit_aout_binfmt(void) diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 1ff94054d35a..a543364ba29b 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -454,7 +454,8 @@ out: static int __init init_aout_binfmt(void) { - return register_binfmt(&aout_format); + register_binfmt(&aout_format); + return 0; } static void __exit exit_aout_binfmt(void) 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) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 30745f459faf..e7afcb67a2d3 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -91,7 +91,8 @@ static struct linux_binfmt elf_fdpic_format = { static int __init init_elf_fdpic_binfmt(void) { - return register_binfmt(&elf_fdpic_format); + register_binfmt(&elf_fdpic_format); + return 0; } static void __exit exit_elf_fdpic_binfmt(void) diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c index b8e8b0acf9bd..2790c7e1912e 100644 --- a/fs/binfmt_em86.c +++ b/fs/binfmt_em86.c @@ -100,7 +100,8 @@ static struct linux_binfmt em86_format = { static int __init init_em86_binfmt(void) { - return register_binfmt(&em86_format); + register_binfmt(&em86_format); + return 0; } static void __exit exit_em86_binfmt(void) diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 1bffbe0ed778..68affab88146 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -950,7 +950,8 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs) static int __init init_flat_binfmt(void) { - return register_binfmt(&flat_format); + register_binfmt(&flat_format); + return 0; } /****************************************************************************/ diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a9198dfd5f85..1ffb60355cae 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -726,11 +726,8 @@ static struct file_system_type bm_fs_type = { static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); - if (!err) { - err = insert_binfmt(&misc_format); - if (err) - unregister_filesystem(&bm_fs_type); - } + if (!err) + insert_binfmt(&misc_format); return err; } diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index 396a9884591f..d3b8c1f63155 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -105,7 +105,8 @@ static struct linux_binfmt script_format = { static int __init init_script_binfmt(void) { - return register_binfmt(&script_format); + register_binfmt(&script_format); + return 0; } static void __exit exit_script_binfmt(void) diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index cc8560f6c9b0..ec15972dd98a 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -289,7 +289,8 @@ static int load_som_library(struct file *f) static int __init init_som_binfmt(void) { - return register_binfmt(&som_format); + register_binfmt(&som_format); + return 0; } static void __exit exit_som_binfmt(void) diff --git a/fs/exec.c b/fs/exec.c index 153dee14fe55..2c5ae338773c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -79,15 +79,13 @@ static atomic_t call_count = ATOMIC_INIT(1); static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); -int __register_binfmt(struct linux_binfmt * fmt, int insert) +void __register_binfmt(struct linux_binfmt * fmt, int insert) { - if (!fmt) - return -EINVAL; + BUG_ON(!fmt); write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); - return 0; } EXPORT_SYMBOL(__register_binfmt); diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 0092102db2de..366422bc1633 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -92,17 +92,17 @@ struct linux_binfmt { unsigned long min_coredump; /* minimal dump size */ }; -extern int __register_binfmt(struct linux_binfmt *fmt, int insert); +extern void __register_binfmt(struct linux_binfmt *fmt, int insert); /* Registration of default binfmt handlers */ -static inline int register_binfmt(struct linux_binfmt *fmt) +static inline void register_binfmt(struct linux_binfmt *fmt) { - return __register_binfmt(fmt, 0); + __register_binfmt(fmt, 0); } /* Same as above, but adds a new binfmt at the top of the list */ -static inline int insert_binfmt(struct linux_binfmt *fmt) +static inline void insert_binfmt(struct linux_binfmt *fmt) { - return __register_binfmt(fmt, 1); + __register_binfmt(fmt, 1); } extern void unregister_binfmt(struct linux_binfmt *); -- 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 --- arch/x86/ia32/ia32_aout.c | 1 - fs/binfmt_aout.c | 1 - fs/binfmt_elf.c | 2 -- fs/binfmt_elf_fdpic.c | 3 --- fs/binfmt_flat.c | 1 - fs/binfmt_som.c | 1 - fs/exec.c | 2 +- 7 files changed, 1 insertion(+), 10 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index cdfc8dc43670..4c2e59a420b9 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -323,7 +323,6 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) } install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index a543364ba29b..4d5e6d26578c 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -267,7 +267,6 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) } install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; 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) { diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index e7afcb67a2d3..c64bf5ee2df4 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -335,8 +335,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, current->mm->context.exec_fdpic_loadmap = 0; current->mm->context.interp_fdpic_loadmap = 0; - current->flags &= ~PF_FORKNOEXEC; - #ifdef CONFIG_MMU elf_fdpic_arch_lay_out_mm(&exec_params, &interp_params, @@ -414,7 +412,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, #endif install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) goto error_kill; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 68affab88146..04f61f0bdfde 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -902,7 +902,6 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs) libinfo.lib_list[j].start_data:UNLOADED_LIB; install_exec_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; set_binfmt(&flat_format); diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index ec15972dd98a..e4fc746629a7 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -225,7 +225,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) goto out_free; /* OK, This is the point of no return */ - current->flags &= ~PF_FORKNOEXEC; current->personality = PER_HPUX; setup_new_exec(bprm); diff --git a/fs/exec.c b/fs/exec.c index 2c5ae338773c..60478a0e7a37 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1110,7 +1110,7 @@ int flush_old_exec(struct linux_binprm * bprm) bprm->mm = NULL; /* We're using it now */ set_fs(USER_DS); - current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD); + current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD); flush_thread(); current->personality &= ~bprm->per_clear; -- 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 --- arch/arm/kernel/process.c | 3 +-- 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(+), 69 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index c2ae3cd331fe..219e4efee1a6 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -533,8 +533,7 @@ int vectors_user_mapping(void) struct mm_struct *mm = current->mm; return install_special_mapping(mm, 0xffff0000, PAGE_SIZE, VM_READ | VM_EXEC | - VM_MAYREAD | VM_MAYEXEC | - VM_ALWAYSDUMP | VM_RESERVED, + VM_MAYREAD | VM_MAYEXEC | VM_RESERVED, NULL); } diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c index 16277c33308a..f212a453b527 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 e5cdfd603f8f..0f1af58b036a 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 7d14bb697d40..d36ee1055f88 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 e704a9965f90..9c80138206b0 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -241,17 +241,11 @@ 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 1d6d51a1ce79..5ca579720a09 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 55e58e93bfc5..1a00fb64fc88 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 52edc2b62873..432b4291f37b 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 639900a6fde9..f40281e5d6a2 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 91f4ec9a0a56..af91901babb8 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 468d591dde31..a944020fa859 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 153407c35b75..17e18279649f 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 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 */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 7330742e7973..2de2ddba51d4 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 3416b6e018d6..6105f475fa86 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3623,13 +3623,7 @@ 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); -- 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 --- arch/alpha/include/asm/mman.h | 4 ++++ arch/mips/include/asm/mman.h | 4 ++++ arch/parisc/include/asm/mman.h | 4 ++++ arch/xtensa/include/asm/mman.h | 4 ++++ fs/binfmt_elf.c | 3 +++ include/asm-generic/mman-common.h | 4 ++++ include/linux/mm.h | 1 + mm/madvise.c | 8 ++++++++ 8 files changed, 32 insertions(+) (limited to 'fs/binfmt_elf.c') diff --git a/arch/alpha/include/asm/mman.h b/arch/alpha/include/asm/mman.h index 72db984f8781..cbeb3616a28e 100644 --- a/arch/alpha/include/asm/mman.h +++ b/arch/alpha/include/asm/mman.h @@ -56,6 +56,10 @@ #define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ #define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/include/asm/mman.h b/arch/mips/include/asm/mman.h index 785b4ea4ec3f..46d3da0d4b92 100644 --- a/arch/mips/include/asm/mman.h +++ b/arch/mips/include/asm/mman.h @@ -80,6 +80,10 @@ #define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ #define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h index f5b7bf5fba68..12219ebce869 100644 --- a/arch/parisc/include/asm/mman.h +++ b/arch/parisc/include/asm/mman.h @@ -62,6 +62,10 @@ #define MADV_HUGEPAGE 67 /* Worth backing with hugepages */ #define MADV_NOHUGEPAGE 68 /* Not worth backing with hugepages */ +#define MADV_DONTDUMP 69 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 70 /* Clear the MADV_NODUMP flag */ + /* compatibility flags */ #define MAP_FILE 0 #define MAP_VARIABLE 0 diff --git a/arch/xtensa/include/asm/mman.h b/arch/xtensa/include/asm/mman.h index 30789010733d..25bc6c1309c3 100644 --- a/arch/xtensa/include/asm/mman.h +++ b/arch/xtensa/include/asm/mman.h @@ -86,6 +86,10 @@ #define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ #define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ + /* compatibility flags */ #define MAP_FILE 0 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)) diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index 787abbb6d867..d030d2c2647a 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_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 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 2de2ddba51d4..a6fabdfd34c5 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 f5ab745672b7..1ccbba5b6674 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_DONTDUMP: + new_flags |= VM_NODUMP; + break; + case MADV_DODUMP: + 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_DONTDUMP: + case MADV_DODUMP: return 1; default: -- 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 --- drivers/misc/sgi-gru/gru_instructions.h | 1 + drivers/staging/crystalhd/bc_dts_defs.h | 2 ++ fs/binfmt_elf.c | 1 + fs/binfmt_elf_fdpic.c | 1 + fs/exec.c | 1 + include/asm-generic/bitops/atomic.h | 2 +- include/linux/llist.h | 3 +-- include/linux/mtd/map.h | 1 + include/linux/spinlock.h | 1 + kernel/sched/core.c | 1 + 10 files changed, 11 insertions(+), 3 deletions(-) (limited to 'fs/binfmt_elf.c') diff --git a/drivers/misc/sgi-gru/gru_instructions.h b/drivers/misc/sgi-gru/gru_instructions.h index d95587cc794c..04d5170ac149 100644 --- a/drivers/misc/sgi-gru/gru_instructions.h +++ b/drivers/misc/sgi-gru/gru_instructions.h @@ -40,6 +40,7 @@ extern void gru_wait_abort_proc(void *cb); *((volatile unsigned long *)(p)) = v; /* force st.rel */ \ } while (0) #elif defined(CONFIG_X86_64) +#include #define __flush_cache(p) clflush(p) #define gru_ordered_store_ulong(p, v) \ do { \ diff --git a/drivers/staging/crystalhd/bc_dts_defs.h b/drivers/staging/crystalhd/bc_dts_defs.h index 8cd51a7aad8e..647e116e10de 100644 --- a/drivers/staging/crystalhd/bc_dts_defs.h +++ b/drivers/staging/crystalhd/bc_dts_defs.h @@ -26,6 +26,8 @@ #ifndef _BC_DTS_DEFS_H_ #define _BC_DTS_DEFS_H_ +#include + /* BIT Mask */ #define BC_BIT(_x) (1 << (_x)) 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 *); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index c64bf5ee2df4..9bd5612a8224 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -39,6 +39,7 @@ #include #include #include +#include typedef char *elf_caddr_t; diff --git a/fs/exec.c b/fs/exec.c index 23559c227d9c..c8b63d14da85 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -59,6 +59,7 @@ #include #include #include +#include #include #include "internal.h" diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index ecc44a8e2b44..9ae6c34dc191 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -2,7 +2,7 @@ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ #include -#include +#include #ifdef CONFIG_SMP #include diff --git a/include/linux/llist.h b/include/linux/llist.h index 801b44b07aac..a5199f6d0e82 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -56,8 +56,7 @@ */ #include -#include -#include +#include struct llist_head { struct llist_node *first; diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 94e924e2ecd5..ade5c990f1f0 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -31,6 +31,7 @@ #include #include #include +#include #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 #define map_bankwidth(map) 1 diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 7df6c17b0281..fa0f93e4d86d 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -55,6 +55,7 @@ #include #include #include +#include #include diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 503d6426126d..157fb9b2b186 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3