linux/arch/x86/kernel/ldt.c

295 lines
6.4 KiB
C
Raw Normal View History

/*
* Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
* Copyright (C) 2002 Andi Kleen
*
* This handles calls from both 32bit and 64bit mode.
*/
#include <linux/errno.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <asm/ldt.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
/* context.lock is held for us, so we don't need any locking. */
static void flush_ldt(void *current_mm)
{
mm_context_t *pc;
if (current->active_mm != current_mm)
return;
pc = &current->active_mm->context;
set_ldt(pc->ldt->entries, pc->ldt->size);
}
/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
static struct ldt_struct *alloc_ldt_struct(int size)
{
struct ldt_struct *new_ldt;
int alloc_size;
if (size > LDT_ENTRIES)
return NULL;
new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
if (!new_ldt)
return NULL;
BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
alloc_size = size * LDT_ENTRY_SIZE;
/*
* Xen is very picky: it requires a page-aligned LDT that has no
* trailing nonzero bytes in any page that contains LDT descriptors.
* Keep it simple: zero the whole allocation and never allocate less
* than PAGE_SIZE.
*/
if (alloc_size > PAGE_SIZE)
new_ldt->entries = vzalloc(alloc_size);
else
new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL);
if (!new_ldt->entries) {
kfree(new_ldt);
return NULL;
}
new_ldt->size = size;
return new_ldt;
}
/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
paravirt_alloc_ldt(ldt->entries, ldt->size);
}
/* context.lock is held */
static void install_ldt(struct mm_struct *current_mm,
struct ldt_struct *ldt)
{
/* Synchronizes with lockless_dereference in load_mm_ldt. */
smp_store_release(&current_mm->context.ldt, ldt);
/* Activate the LDT for all CPUs using current_mm. */
on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
}
static void free_ldt_struct(struct ldt_struct *ldt)
{
if (likely(!ldt))
return;
paravirt_free_ldt(ldt->entries, ldt->size);
if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
vfree(ldt->entries);
else
free_page((unsigned long)ldt->entries);
kfree(ldt);
}
/*
* we do not have to muck with descriptors here, that is
* done in switch_mm() as needed.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
struct ldt_struct *new_ldt;
struct mm_struct *old_mm;
int retval = 0;
mutex_init(&mm->context.lock);
old_mm = current->mm;
if (!old_mm) {
mm->context.ldt = NULL;
return 0;
}
mutex_lock(&old_mm->context.lock);
if (!old_mm->context.ldt) {
mm->context.ldt = NULL;
goto out_unlock;
}
new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
if (!new_ldt) {
retval = -ENOMEM;
goto out_unlock;
}
memcpy(new_ldt->entries, old_mm->context.ldt->entries,
new_ldt->size * LDT_ENTRY_SIZE);
finalize_ldt_struct(new_ldt);
mm->context.ldt = new_ldt;
out_unlock:
mutex_unlock(&old_mm->context.lock);
return retval;
}
/*
* No need to lock the MM as we are the last user
*
* 64bit: Don't touch the LDT register - we're already in the next thread.
*/
void destroy_context(struct mm_struct *mm)
{
free_ldt_struct(mm->context.ldt);
mm->context.ldt = NULL;
}
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
int retval;
unsigned long size;
struct mm_struct *mm = current->mm;
mutex_lock(&mm->context.lock);
if (!mm->context.ldt) {
retval = 0;
goto out_unlock;
}
if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
size = mm->context.ldt->size * LDT_ENTRY_SIZE;
if (size > bytecount)
size = bytecount;
if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
retval = -EFAULT;
goto out_unlock;
}
if (size != bytecount) {
/* Zero-fill the rest and pretend we read bytecount bytes. */
if (clear_user(ptr + size, bytecount - size)) {
retval = -EFAULT;
goto out_unlock;
}
}
retval = bytecount;
out_unlock:
mutex_unlock(&mm->context.lock);
return retval;
}
static int read_default_ldt(void __user *ptr, unsigned long bytecount)
{
/* CHECKME: Can we use _one_ random number ? */
#ifdef CONFIG_X86_32
unsigned long size = 5 * sizeof(struct desc_struct);
#else
unsigned long size = 128;
#endif
if (bytecount > size)
bytecount = size;
if (clear_user(ptr, bytecount))
return -EFAULT;
return bytecount;
}
static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
{
struct mm_struct *mm = current->mm;
struct desc_struct ldt;
int error;
struct user_desc ldt_info;
int oldsize, newsize;
struct ldt_struct *new_ldt, *old_ldt;
error = -EINVAL;
if (bytecount != sizeof(ldt_info))
goto out;
error = -EFAULT;
if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
goto out;
error = -EINVAL;
if (ldt_info.entry_number >= LDT_ENTRIES)
goto out;
if (ldt_info.contents == 3) {
if (oldmode)
goto out;
if (ldt_info.seg_not_present == 0)
goto out;
}
if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
LDT_empty(&ldt_info)) {
/* The user wants to clear the entry. */
memset(&ldt, 0, sizeof(ldt));
} else {
if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
error = -EINVAL;
goto out;
}
fill_ldt(&ldt, &ldt_info);
if (oldmode)
ldt.avl = 0;
}
mutex_lock(&mm->context.lock);
old_ldt = mm->context.ldt;
oldsize = old_ldt ? old_ldt->size : 0;
newsize = max((int)(ldt_info.entry_number + 1), oldsize);
error = -ENOMEM;
new_ldt = alloc_ldt_struct(newsize);
if (!new_ldt)
goto out_unlock;
if (old_ldt)
memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
new_ldt->entries[ldt_info.entry_number] = ldt;
finalize_ldt_struct(new_ldt);
install_ldt(mm, new_ldt);
free_ldt_struct(old_ldt);
error = 0;
out_unlock:
mutex_unlock(&mm->context.lock);
out:
return error;
}
asmlinkage int sys_modify_ldt(int func, void __user *ptr,
unsigned long bytecount)
{
int ret = -ENOSYS;
switch (func) {
case 0:
ret = read_ldt(ptr, bytecount);
break;
case 1:
ret = write_ldt(ptr, bytecount, 1);
break;
case 2:
ret = read_default_ldt(ptr, bytecount);
break;
case 0x11:
ret = write_ldt(ptr, bytecount, 0);
break;
}
return ret;
}