linux/arch/s390/kernel/vdso.c

325 lines
8.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* vdso setup for s390
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
*/
#include <linux/init.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>
#include <linux/compat.h>
#include <asm/asm-offsets.h>
#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>
#include <asm/facility.h>
#ifdef 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
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
static unsigned int vdso64_pages;
static struct page **vdso64_pagelist;
/*
* 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 vdso_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page **vdso_pagelist;
unsigned long vdso_pages;
vdso_pagelist = vdso64_pagelist;
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
if (is_compat_task()) {
vdso_pagelist = vdso32_pagelist;
vdso_pages = vdso32_pages;
}
#endif
if (vmf->pgoff >= vdso_pages)
return VM_FAULT_SIGBUS;
vmf->page = vdso_pagelist[vmf->pgoff];
get_page(vmf->page);
return 0;
}
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *vma)
{
unsigned long vdso_pages;
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
if (is_compat_task())
vdso_pages = vdso32_pages;
#endif
if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start)
return -EINVAL;
if (WARN_ON_ONCE(current->mm != vma->vm_mm))
return -EFAULT;
current->mm->context.vdso_base = vma->vm_start;
return 0;
}
static const struct vm_special_mapping vdso_mapping = {
.name = "[vdso]",
.fault = vdso_fault,
.mremap = vdso_mremap,
};
static int __init vdso_setup(char *s)
{
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 {
rc = kstrtoul(s, 0, &val);
vdso_enabled = rc ? 0 : !!val;
}
return !rc;
}
__setup("vdso=", vdso_setup);
/*
* The vdso data page
*/
static union {
struct vdso_data data;
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
struct vdso_data *vdso_data = &vdso_data_store.data;
/*
* Setup vdso data page.
*/
static void __init vdso_init_data(struct vdso_data *vd)
{
vd->ectg_available = test_facility(31);
}
/*
* Allocate/free per cpu vdso data.
*/
#define SEGMENT_ORDER 2
/*
* The initial vdso_data structure for the boot CPU. Eventually
* it is replaced with a properly allocated structure in vdso_init.
* This is necessary because a valid S390_lowcore.vdso_per_cpu_data
* pointer is required to be able to return from an interrupt or
* program check. See the exit paths in entry.S.
*/
struct vdso_data boot_vdso_data __initdata;
void __init vdso_alloc_boot_cpu(struct lowcore *lowcore)
{
lowcore->vdso_per_cpu_data = (unsigned long) &boot_vdso_data;
}
int vdso_alloc_per_cpu(struct lowcore *lowcore)
{
unsigned long segment_table, page_table, page_frame;
struct vdso_per_cpu_data *vd;
segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
s390: remove all code using the access register mode The vdso code for the getcpu() and the clock_gettime() call use the access register mode to access the per-CPU vdso data page with the current code. An alternative to the complicated AR mode is to use the secondary space mode. This makes the vdso faster and quite a bit simpler. The downside is that the uaccess code has to be changed quite a bit. Which instructions are used depends on the machine and what kind of uaccess operation is requested. The instruction dictates which ASCE value needs to be loaded into %cr1 and %cr7. The different cases: * User copy with MVCOS for z10 and newer machines The MVCOS instruction can copy between the primary space (aka user) and the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already loaded in %cr1. * User copy with MVCP/MVCS for older machines To be able to execute the MVCP/MVCS instructions the kernel needs to switch to primary mode. The control register %cr1 has to be set to the kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent on set_fs(KERNEL_DS) vs set_fs(USER_DS). * Data access in the user address space for strnlen / futex To use "normal" instruction with data from the user address space the secondary space mode is used. The kernel needs to switch to primary mode, %cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the kernel ASCE, dependent on set_fs. To load a new value into %cr1 or %cr7 is an expensive operation, the kernel tries to be lazy about it. E.g. for multiple user copies in a row with MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is done only once. On return to user space a CPU bit is checked that loads the vdso ASCE again. To enable and disable the data access via the secondary space two new functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact that a context is in secondary space uaccess mode is stored in the mm_segment_t value for the task. The code of an interrupt may use set_fs as long as it returns to the previous state it got with get_fs with another call to set_fs. The code in finish_arch_post_lock_switch simply has to do a set_fs with the current mm_segment_t value for the task. For CPUs with MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode, lazy | user | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | For CPUs without MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode lazy | kernel | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | The lines with "lazy" refer to the state after a copy via the secondary space with a delayed reload of %cr1 and %cr7. There are three hardware address spaces that can cause a DAT exception, primary, secondary and home space. The exception can be related to four different fault types: user space fault, vdso fault, kernel fault, and the gmap faults. Dependent on the set_fs state and normal vs. sacf mode there are a number of fault combinations: 1) user address space fault via the primary ASCE 2) gmap address space fault via the primary ASCE 3) kernel address space fault via the primary ASCE for machines with MVCOS and set_fs(KERNEL_DS) 4) vdso address space faults via the secondary ASCE with an invalid address while running in secondary space in problem state 5) user address space fault via the secondary ASCE for user-copy based on the secondary space mode, e.g. futex_ops or strnlen_user 6) kernel address space fault via the secondary ASCE for user-copy with secondary space mode with set_fs(KERNEL_DS) 7) kernel address space fault via the primary ASCE for user-copy with secondary space mode with set_fs(USER_DS) on machines without MVCOS. 8) kernel address space fault via the home space ASCE Replace user_space_fault() with a new function get_fault_type() that can distinguish all four different fault types. With these changes the futex atomic ops from the kernel and the strnlen_user will get a little bit slower, as well as the old style uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as fast as before. On the positive side, the user space vdso code is a lot faster and Linux ceases to use the complicated AR mode. Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 18:08:22 +08:00
page_table = get_zeroed_page(GFP_KERNEL);
page_frame = get_zeroed_page(GFP_KERNEL);
if (!segment_table || !page_table || !page_frame)
goto out;
arch_set_page_dat(virt_to_page(segment_table), SEGMENT_ORDER);
arch_set_page_dat(virt_to_page(page_table), 0);
/* Initialize per-cpu vdso data page */
vd = (struct vdso_per_cpu_data *) page_frame;
vd->cpu_nr = lowcore->cpu_nr;
vd->node_id = cpu_to_node(vd->cpu_nr);
s390: remove all code using the access register mode The vdso code for the getcpu() and the clock_gettime() call use the access register mode to access the per-CPU vdso data page with the current code. An alternative to the complicated AR mode is to use the secondary space mode. This makes the vdso faster and quite a bit simpler. The downside is that the uaccess code has to be changed quite a bit. Which instructions are used depends on the machine and what kind of uaccess operation is requested. The instruction dictates which ASCE value needs to be loaded into %cr1 and %cr7. The different cases: * User copy with MVCOS for z10 and newer machines The MVCOS instruction can copy between the primary space (aka user) and the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already loaded in %cr1. * User copy with MVCP/MVCS for older machines To be able to execute the MVCP/MVCS instructions the kernel needs to switch to primary mode. The control register %cr1 has to be set to the kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent on set_fs(KERNEL_DS) vs set_fs(USER_DS). * Data access in the user address space for strnlen / futex To use "normal" instruction with data from the user address space the secondary space mode is used. The kernel needs to switch to primary mode, %cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the kernel ASCE, dependent on set_fs. To load a new value into %cr1 or %cr7 is an expensive operation, the kernel tries to be lazy about it. E.g. for multiple user copies in a row with MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is done only once. On return to user space a CPU bit is checked that loads the vdso ASCE again. To enable and disable the data access via the secondary space two new functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact that a context is in secondary space uaccess mode is stored in the mm_segment_t value for the task. The code of an interrupt may use set_fs as long as it returns to the previous state it got with get_fs with another call to set_fs. The code in finish_arch_post_lock_switch simply has to do a set_fs with the current mm_segment_t value for the task. For CPUs with MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode, lazy | user | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | For CPUs without MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode lazy | kernel | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | The lines with "lazy" refer to the state after a copy via the secondary space with a delayed reload of %cr1 and %cr7. There are three hardware address spaces that can cause a DAT exception, primary, secondary and home space. The exception can be related to four different fault types: user space fault, vdso fault, kernel fault, and the gmap faults. Dependent on the set_fs state and normal vs. sacf mode there are a number of fault combinations: 1) user address space fault via the primary ASCE 2) gmap address space fault via the primary ASCE 3) kernel address space fault via the primary ASCE for machines with MVCOS and set_fs(KERNEL_DS) 4) vdso address space faults via the secondary ASCE with an invalid address while running in secondary space in problem state 5) user address space fault via the secondary ASCE for user-copy based on the secondary space mode, e.g. futex_ops or strnlen_user 6) kernel address space fault via the secondary ASCE for user-copy with secondary space mode with set_fs(KERNEL_DS) 7) kernel address space fault via the primary ASCE for user-copy with secondary space mode with set_fs(USER_DS) on machines without MVCOS. 8) kernel address space fault via the home space ASCE Replace user_space_fault() with a new function get_fault_type() that can distinguish all four different fault types. With these changes the futex atomic ops from the kernel and the strnlen_user will get a little bit slower, as well as the old style uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as fast as before. On the positive side, the user space vdso code is a lot faster and Linux ceases to use the complicated AR mode. Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 18:08:22 +08:00
/* Set up page table for the vdso address space */
memset64((u64 *)segment_table, _SEGMENT_ENTRY_EMPTY, _CRST_ENTRIES);
memset64((u64 *)page_table, _PAGE_INVALID, PTRS_PER_PTE);
*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
s390: remove all code using the access register mode The vdso code for the getcpu() and the clock_gettime() call use the access register mode to access the per-CPU vdso data page with the current code. An alternative to the complicated AR mode is to use the secondary space mode. This makes the vdso faster and quite a bit simpler. The downside is that the uaccess code has to be changed quite a bit. Which instructions are used depends on the machine and what kind of uaccess operation is requested. The instruction dictates which ASCE value needs to be loaded into %cr1 and %cr7. The different cases: * User copy with MVCOS for z10 and newer machines The MVCOS instruction can copy between the primary space (aka user) and the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already loaded in %cr1. * User copy with MVCP/MVCS for older machines To be able to execute the MVCP/MVCS instructions the kernel needs to switch to primary mode. The control register %cr1 has to be set to the kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent on set_fs(KERNEL_DS) vs set_fs(USER_DS). * Data access in the user address space for strnlen / futex To use "normal" instruction with data from the user address space the secondary space mode is used. The kernel needs to switch to primary mode, %cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the kernel ASCE, dependent on set_fs. To load a new value into %cr1 or %cr7 is an expensive operation, the kernel tries to be lazy about it. E.g. for multiple user copies in a row with MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is done only once. On return to user space a CPU bit is checked that loads the vdso ASCE again. To enable and disable the data access via the secondary space two new functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact that a context is in secondary space uaccess mode is stored in the mm_segment_t value for the task. The code of an interrupt may use set_fs as long as it returns to the previous state it got with get_fs with another call to set_fs. The code in finish_arch_post_lock_switch simply has to do a set_fs with the current mm_segment_t value for the task. For CPUs with MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode, lazy | user | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | For CPUs without MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode lazy | kernel | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | The lines with "lazy" refer to the state after a copy via the secondary space with a delayed reload of %cr1 and %cr7. There are three hardware address spaces that can cause a DAT exception, primary, secondary and home space. The exception can be related to four different fault types: user space fault, vdso fault, kernel fault, and the gmap faults. Dependent on the set_fs state and normal vs. sacf mode there are a number of fault combinations: 1) user address space fault via the primary ASCE 2) gmap address space fault via the primary ASCE 3) kernel address space fault via the primary ASCE for machines with MVCOS and set_fs(KERNEL_DS) 4) vdso address space faults via the secondary ASCE with an invalid address while running in secondary space in problem state 5) user address space fault via the secondary ASCE for user-copy based on the secondary space mode, e.g. futex_ops or strnlen_user 6) kernel address space fault via the secondary ASCE for user-copy with secondary space mode with set_fs(KERNEL_DS) 7) kernel address space fault via the primary ASCE for user-copy with secondary space mode with set_fs(USER_DS) on machines without MVCOS. 8) kernel address space fault via the home space ASCE Replace user_space_fault() with a new function get_fault_type() that can distinguish all four different fault types. With these changes the futex atomic ops from the kernel and the strnlen_user will get a little bit slower, as well as the old style uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as fast as before. On the positive side, the user space vdso code is a lot faster and Linux ceases to use the complicated AR mode. Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 18:08:22 +08:00
lowcore->vdso_asce = segment_table +
_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
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;
}
void vdso_free_per_cpu(struct lowcore *lowcore)
{
unsigned long segment_table, page_table, page_frame;
s390: remove all code using the access register mode The vdso code for the getcpu() and the clock_gettime() call use the access register mode to access the per-CPU vdso data page with the current code. An alternative to the complicated AR mode is to use the secondary space mode. This makes the vdso faster and quite a bit simpler. The downside is that the uaccess code has to be changed quite a bit. Which instructions are used depends on the machine and what kind of uaccess operation is requested. The instruction dictates which ASCE value needs to be loaded into %cr1 and %cr7. The different cases: * User copy with MVCOS for z10 and newer machines The MVCOS instruction can copy between the primary space (aka user) and the home space (aka kernel) directly. For set_fs(KERNEL_DS) the kernel ASCE is loaded into %cr1. For set_fs(USER_DS) the user space is already loaded in %cr1. * User copy with MVCP/MVCS for older machines To be able to execute the MVCP/MVCS instructions the kernel needs to switch to primary mode. The control register %cr1 has to be set to the kernel ASCE and %cr7 to either the kernel ASCE or the user ASCE dependent on set_fs(KERNEL_DS) vs set_fs(USER_DS). * Data access in the user address space for strnlen / futex To use "normal" instruction with data from the user address space the secondary space mode is used. The kernel needs to switch to primary mode, %cr1 has to contain the kernel ASCE and %cr7 either the user ASCE or the kernel ASCE, dependent on set_fs. To load a new value into %cr1 or %cr7 is an expensive operation, the kernel tries to be lazy about it. E.g. for multiple user copies in a row with MVCP/MVCS the replacement of the vdso ASCE in %cr7 with the user ASCE is done only once. On return to user space a CPU bit is checked that loads the vdso ASCE again. To enable and disable the data access via the secondary space two new functions are added, enable_sacf_uaccess and disable_sacf_uaccess. The fact that a context is in secondary space uaccess mode is stored in the mm_segment_t value for the task. The code of an interrupt may use set_fs as long as it returns to the previous state it got with get_fs with another call to set_fs. The code in finish_arch_post_lock_switch simply has to do a set_fs with the current mm_segment_t value for the task. For CPUs with MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode, lazy | user | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | For CPUs without MVCOS: CPU running in | %cr1 ASCE | %cr7 ASCE | --------------------------------------|-----------|-----------| user space | user | vdso | kernel, USER_DS, normal-mode | user | vdso | kernel, USER_DS, normal-mode lazy | kernel | user | kernel, USER_DS, sacf-mode | kernel | user | kernel, KERNEL_DS, normal-mode | kernel | vdso | kernel, KERNEL_DS, normal-mode, lazy | kernel | kernel | kernel, KERNEL_DS, sacf-mode | kernel | kernel | The lines with "lazy" refer to the state after a copy via the secondary space with a delayed reload of %cr1 and %cr7. There are three hardware address spaces that can cause a DAT exception, primary, secondary and home space. The exception can be related to four different fault types: user space fault, vdso fault, kernel fault, and the gmap faults. Dependent on the set_fs state and normal vs. sacf mode there are a number of fault combinations: 1) user address space fault via the primary ASCE 2) gmap address space fault via the primary ASCE 3) kernel address space fault via the primary ASCE for machines with MVCOS and set_fs(KERNEL_DS) 4) vdso address space faults via the secondary ASCE with an invalid address while running in secondary space in problem state 5) user address space fault via the secondary ASCE for user-copy based on the secondary space mode, e.g. futex_ops or strnlen_user 6) kernel address space fault via the secondary ASCE for user-copy with secondary space mode with set_fs(KERNEL_DS) 7) kernel address space fault via the primary ASCE for user-copy with secondary space mode with set_fs(USER_DS) on machines without MVCOS. 8) kernel address space fault via the home space ASCE Replace user_space_fault() with a new function get_fault_type() that can distinguish all four different fault types. With these changes the futex atomic ops from the kernel and the strnlen_user will get a little bit slower, as well as the old style uaccess with MVCP/MVCS. All user accesses based on MVCOS will be as fast as before. On the positive side, the user space vdso code is a lot faster and Linux ceases to use the complicated AR mode. Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2017-08-22 18:08:22 +08:00
segment_table = lowcore->vdso_asce & 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);
}
/*
* 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 vm_area_struct *vma;
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;
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
if (is_compat_task())
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;
/*
* 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.
*/
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
if (IS_ERR_VALUE(vdso_base)) {
rc = vdso_base;
goto out_up;
}
/*
* 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.
*/
vma = _install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&vdso_mapping);
if (IS_ERR(vma)) {
rc = PTR_ERR(vma);
goto out_up;
}
current->mm->context.vdso_base = vdso_base;
rc = 0;
out_up:
up_write(&mm->mmap_sem);
return rc;
}
static int __init vdso_init(void)
{
int i;
vdso_init_data(vdso_data);
#ifdef 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 */
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
vdso32_pagelist = kcalloc(vdso32_pages + 1, sizeof(struct page *),
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
/* 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 */
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
vdso64_pagelist = kcalloc(vdso64_pages + 1, sizeof(struct page *),
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;
if (vdso_alloc_per_cpu(&S390_lowcore))
BUG();
get_page(virt_to_page(vdso_data));
return 0;
}
early_initcall(vdso_init);