2008-12-25 20:38:36 +08:00
|
|
|
/*
|
|
|
|
* vdso setup for s390
|
|
|
|
*
|
|
|
|
* Copyright IBM Corp. 2008
|
|
|
|
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License (version 2 only)
|
|
|
|
* as published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/unistd.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/user.h>
|
|
|
|
#include <linux/elf.h>
|
|
|
|
#include <linux/security.h>
|
|
|
|
#include <linux/bootmem.h>
|
2009-06-12 16:26:25 +08:00
|
|
|
#include <linux/compat.h>
|
2010-02-27 05:37:43 +08:00
|
|
|
#include <asm/asm-offsets.h>
|
2008-12-25 20:38:36 +08:00
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/processor.h>
|
|
|
|
#include <asm/mmu.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/sections.h>
|
|
|
|
#include <asm/vdso.h>
|
2012-03-29 01:30:02 +08:00
|
|
|
#include <asm/facility.h>
|
2008-12-25 20:38:36 +08:00
|
|
|
|
|
|
|
#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
|
|
|
|
extern char vdso32_start, vdso32_end;
|
|
|
|
static void *vdso32_kbase = &vdso32_start;
|
|
|
|
static unsigned int vdso32_pages;
|
|
|
|
static struct page **vdso32_pagelist;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_64BIT
|
|
|
|
extern char vdso64_start, vdso64_end;
|
|
|
|
static void *vdso64_kbase = &vdso64_start;
|
|
|
|
static unsigned int vdso64_pages;
|
|
|
|
static struct page **vdso64_pagelist;
|
|
|
|
#endif /* CONFIG_64BIT */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Should the kernel map a VDSO page into processes and pass its
|
|
|
|
* address down to glibc upon exec()?
|
|
|
|
*/
|
|
|
|
unsigned int __read_mostly vdso_enabled = 1;
|
|
|
|
|
|
|
|
static int __init vdso_setup(char *s)
|
|
|
|
{
|
2009-06-12 16:26:20 +08:00
|
|
|
unsigned long val;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
rc = 0;
|
|
|
|
if (strncmp(s, "on", 3) == 0)
|
|
|
|
vdso_enabled = 1;
|
|
|
|
else if (strncmp(s, "off", 4) == 0)
|
|
|
|
vdso_enabled = 0;
|
|
|
|
else {
|
2013-07-22 12:43:57 +08:00
|
|
|
rc = kstrtoul(s, 0, &val);
|
2009-06-12 16:26:20 +08:00
|
|
|
vdso_enabled = rc ? 0 : !!val;
|
|
|
|
}
|
|
|
|
return !rc;
|
2008-12-25 20:38:36 +08:00
|
|
|
}
|
|
|
|
__setup("vdso=", vdso_setup);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The vdso data page
|
|
|
|
*/
|
|
|
|
static union {
|
|
|
|
struct vdso_data data;
|
|
|
|
u8 page[PAGE_SIZE];
|
2009-09-21 06:14:15 +08:00
|
|
|
} vdso_data_store __page_aligned_data;
|
2008-12-25 20:38:36 +08:00
|
|
|
struct vdso_data *vdso_data = &vdso_data_store.data;
|
|
|
|
|
2008-12-31 22:11:42 +08:00
|
|
|
/*
|
|
|
|
* Setup vdso data page.
|
|
|
|
*/
|
|
|
|
static void vdso_init_data(struct vdso_data *vd)
|
|
|
|
{
|
2013-09-24 15:14:56 +08:00
|
|
|
vd->ectg_available = test_facility(31);
|
2008-12-31 22:11:42 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_64BIT
|
|
|
|
/*
|
|
|
|
* Allocate/free per cpu vdso data.
|
|
|
|
*/
|
|
|
|
#define SEGMENT_ORDER 2
|
|
|
|
|
2012-03-11 23:59:26 +08:00
|
|
|
int vdso_alloc_per_cpu(struct _lowcore *lowcore)
|
2008-12-31 22:11:42 +08:00
|
|
|
{
|
|
|
|
unsigned long segment_table, page_table, page_frame;
|
|
|
|
u32 *psal, *aste;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
lowcore->vdso_per_cpu_data = __LC_PASTE;
|
|
|
|
|
2013-09-24 15:14:56 +08:00
|
|
|
if (!vdso_enabled)
|
2008-12-31 22:11:42 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
|
|
|
|
page_table = get_zeroed_page(GFP_KERNEL | GFP_DMA);
|
|
|
|
page_frame = get_zeroed_page(GFP_KERNEL);
|
|
|
|
if (!segment_table || !page_table || !page_frame)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
|
|
|
|
PAGE_SIZE << SEGMENT_ORDER);
|
2013-07-24 02:57:57 +08:00
|
|
|
clear_table((unsigned long *) page_table, _PAGE_INVALID,
|
2008-12-31 22:11:42 +08:00
|
|
|
256*sizeof(unsigned long));
|
|
|
|
|
|
|
|
*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
|
2013-07-24 02:57:57 +08:00
|
|
|
*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
|
2008-12-31 22:11:42 +08:00
|
|
|
|
|
|
|
psal = (u32 *) (page_table + 256*sizeof(unsigned long));
|
|
|
|
aste = psal + 32;
|
|
|
|
|
|
|
|
for (i = 4; i < 32; i += 4)
|
|
|
|
psal[i] = 0x80000000;
|
|
|
|
|
|
|
|
lowcore->paste[4] = (u32)(addr_t) psal;
|
2013-11-30 19:57:13 +08:00
|
|
|
psal[0] = 0x02000000;
|
2008-12-31 22:11:42 +08:00
|
|
|
psal[2] = (u32)(addr_t) aste;
|
|
|
|
*(unsigned long *) (aste + 2) = segment_table +
|
|
|
|
_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
|
|
|
|
aste[4] = (u32)(addr_t) psal;
|
|
|
|
lowcore->vdso_per_cpu_data = page_frame;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
free_page(page_frame);
|
|
|
|
free_page(page_table);
|
|
|
|
free_pages(segment_table, SEGMENT_ORDER);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
2012-03-11 23:59:26 +08:00
|
|
|
void vdso_free_per_cpu(struct _lowcore *lowcore)
|
2008-12-31 22:11:42 +08:00
|
|
|
{
|
|
|
|
unsigned long segment_table, page_table, page_frame;
|
|
|
|
u32 *psal, *aste;
|
|
|
|
|
2013-09-24 15:14:56 +08:00
|
|
|
if (!vdso_enabled)
|
2008-12-31 22:11:42 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
psal = (u32 *)(addr_t) lowcore->paste[4];
|
|
|
|
aste = (u32 *)(addr_t) psal[2];
|
|
|
|
segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK;
|
|
|
|
page_table = *(unsigned long *) segment_table;
|
|
|
|
page_frame = *(unsigned long *) page_table;
|
|
|
|
|
|
|
|
free_page(page_frame);
|
|
|
|
free_page(page_table);
|
|
|
|
free_pages(segment_table, SEGMENT_ORDER);
|
|
|
|
}
|
|
|
|
|
2012-03-11 23:59:26 +08:00
|
|
|
static void vdso_init_cr5(void)
|
2008-12-31 22:11:42 +08:00
|
|
|
{
|
|
|
|
unsigned long cr5;
|
|
|
|
|
2013-09-24 15:14:56 +08:00
|
|
|
if (!vdso_enabled)
|
2012-03-11 23:59:26 +08:00
|
|
|
return;
|
2008-12-31 22:11:42 +08:00
|
|
|
cr5 = offsetof(struct _lowcore, paste);
|
|
|
|
__ctl_load(cr5, 5, 5);
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_64BIT */
|
|
|
|
|
2008-12-25 20:38:36 +08:00
|
|
|
/*
|
|
|
|
* This is called from binfmt_elf, we create the special vma for the
|
|
|
|
* vDSO and insert it into the mm struct tree
|
|
|
|
*/
|
|
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
struct page **vdso_pagelist;
|
|
|
|
unsigned long vdso_pages;
|
|
|
|
unsigned long vdso_base;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (!vdso_enabled)
|
|
|
|
return 0;
|
|
|
|
/*
|
|
|
|
* Only map the vdso for dynamically linked elf binaries.
|
|
|
|
*/
|
|
|
|
if (!uses_interp)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
#ifdef CONFIG_64BIT
|
|
|
|
vdso_pagelist = vdso64_pagelist;
|
|
|
|
vdso_pages = vdso64_pages;
|
|
|
|
#ifdef CONFIG_COMPAT
|
2009-06-12 16:26:25 +08:00
|
|
|
if (is_compat_task()) {
|
2008-12-25 20:38:36 +08:00
|
|
|
vdso_pagelist = vdso32_pagelist;
|
|
|
|
vdso_pages = vdso32_pages;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
#else
|
|
|
|
vdso_pagelist = vdso32_pagelist;
|
|
|
|
vdso_pages = vdso32_pages;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* vDSO has a problem and was disabled, just don't "enable" it for
|
|
|
|
* the process
|
|
|
|
*/
|
|
|
|
if (vdso_pages == 0)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
current->mm->context.vdso_base = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pick a base address for the vDSO in process space. We try to put
|
|
|
|
* it at vdso_base which is the "natural" base for it, but we might
|
|
|
|
* fail and end up putting it elsewhere.
|
|
|
|
*/
|
|
|
|
down_write(&mm->mmap_sem);
|
2011-01-12 16:55:24 +08:00
|
|
|
vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
|
2008-12-25 20:38:36 +08:00
|
|
|
if (IS_ERR_VALUE(vdso_base)) {
|
|
|
|
rc = vdso_base;
|
|
|
|
goto out_up;
|
|
|
|
}
|
|
|
|
|
2009-10-06 16:34:08 +08:00
|
|
|
/*
|
|
|
|
* Put vDSO base into mm struct. We need to do this before calling
|
|
|
|
* install_special_mapping or the perf counter mmap tracking code
|
|
|
|
* will fail to recognise it as a vDSO (since arch_vma_name fails).
|
|
|
|
*/
|
|
|
|
current->mm->context.vdso_base = vdso_base;
|
|
|
|
|
2008-12-25 20:38:36 +08:00
|
|
|
/*
|
|
|
|
* our vma flags don't have VM_WRITE so by default, the process
|
|
|
|
* isn't allowed to write those pages.
|
|
|
|
* gdb can break that with ptrace interface, and thus trigger COW
|
|
|
|
* on those pages but it's then your responsibility to never do that
|
|
|
|
* 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
|
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/<pid>/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 <jbaron@redhat.com>
Acked-by: Roland McGrath <roland@hack.frob.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Avi Kivity <avi@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:51 +08:00
|
|
|
* pages though.
|
2008-12-25 20:38:36 +08:00
|
|
|
*/
|
|
|
|
rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
|
|
|
|
VM_READ|VM_EXEC|
|
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/<pid>/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 <jbaron@redhat.com>
Acked-by: Roland McGrath <roland@hack.frob.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Avi Kivity <avi@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:51 +08:00
|
|
|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
|
2008-12-25 20:38:36 +08:00
|
|
|
vdso_pagelist);
|
|
|
|
if (rc)
|
2009-10-06 16:34:08 +08:00
|
|
|
current->mm->context.vdso_base = 0;
|
2008-12-25 20:38:36 +08:00
|
|
|
out_up:
|
|
|
|
up_write(&mm->mmap_sem);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
const char *arch_vma_name(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
|
|
|
|
return "[vdso]";
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init vdso_init(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2008-12-31 22:11:42 +08:00
|
|
|
if (!vdso_enabled)
|
|
|
|
return 0;
|
|
|
|
vdso_init_data(vdso_data);
|
2008-12-25 20:38:36 +08:00
|
|
|
#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
|
|
|
|
/* Calculate the size of the 32 bit vDSO */
|
|
|
|
vdso32_pages = ((&vdso32_end - &vdso32_start
|
|
|
|
+ PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
|
|
|
|
|
|
|
|
/* Make sure pages are in the correct state */
|
|
|
|
vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1),
|
|
|
|
GFP_KERNEL);
|
|
|
|
BUG_ON(vdso32_pagelist == NULL);
|
|
|
|
for (i = 0; i < vdso32_pages - 1; i++) {
|
|
|
|
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
|
|
|
|
ClearPageReserved(pg);
|
|
|
|
get_page(pg);
|
|
|
|
vdso32_pagelist[i] = pg;
|
|
|
|
}
|
|
|
|
vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data);
|
|
|
|
vdso32_pagelist[vdso32_pages] = NULL;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_64BIT
|
|
|
|
/* Calculate the size of the 64 bit vDSO */
|
|
|
|
vdso64_pages = ((&vdso64_end - &vdso64_start
|
|
|
|
+ PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
|
|
|
|
|
|
|
|
/* Make sure pages are in the correct state */
|
|
|
|
vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 1),
|
|
|
|
GFP_KERNEL);
|
|
|
|
BUG_ON(vdso64_pagelist == NULL);
|
|
|
|
for (i = 0; i < vdso64_pages - 1; i++) {
|
|
|
|
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
|
|
|
|
ClearPageReserved(pg);
|
|
|
|
get_page(pg);
|
|
|
|
vdso64_pagelist[i] = pg;
|
|
|
|
}
|
|
|
|
vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
|
|
|
|
vdso64_pagelist[vdso64_pages] = NULL;
|
2012-03-11 23:59:26 +08:00
|
|
|
if (vdso_alloc_per_cpu(&S390_lowcore))
|
2009-01-09 19:14:54 +08:00
|
|
|
BUG();
|
2008-12-31 22:11:42 +08:00
|
|
|
vdso_init_cr5();
|
2008-12-25 20:38:36 +08:00
|
|
|
#endif /* CONFIG_64BIT */
|
|
|
|
|
|
|
|
get_page(virt_to_page(vdso_data));
|
|
|
|
|
|
|
|
smp_wmb();
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2012-03-11 23:59:26 +08:00
|
|
|
early_initcall(vdso_init);
|
2008-12-25 20:38:36 +08:00
|
|
|
|
2011-03-14 03:49:17 +08:00
|
|
|
int in_gate_area_no_mm(unsigned long addr)
|
2008-12-25 20:38:36 +08:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-03-14 03:49:16 +08:00
|
|
|
int in_gate_area(struct mm_struct *mm, unsigned long addr)
|
2008-12-25 20:38:36 +08:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-03-14 03:49:15 +08:00
|
|
|
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
|
2008-12-25 20:38:36 +08:00
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|