2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
|
|
|
|
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
|
|
|
|
* Copyright (C) 2002 Andi Kleen
|
2008-01-30 19:30:13 +07:00
|
|
|
*
|
2005-04-17 05:20:36 +07:00
|
|
|
* 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 15:04:11 +07:00
|
|
|
#include <linux/gfp.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/vmalloc.h>
|
2008-12-31 18:12:20 +07:00
|
|
|
#include <linux/uaccess.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
#include <asm/system.h>
|
|
|
|
#include <asm/ldt.h>
|
|
|
|
#include <asm/desc.h>
|
2008-01-30 19:30:13 +07:00
|
|
|
#include <asm/mmu_context.h>
|
2008-07-21 23:04:13 +07:00
|
|
|
#include <asm/syscalls.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
#ifdef CONFIG_SMP
|
2008-05-12 20:44:39 +07:00
|
|
|
static void flush_ldt(void *current_mm)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2008-05-12 20:44:39 +07:00
|
|
|
if (current->active_mm == current_mm)
|
2008-01-30 19:30:13 +07:00
|
|
|
load_LDT(¤t->active_mm->context);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2008-01-30 19:30:13 +07:00
|
|
|
void *oldldt, *newldt;
|
|
|
|
int oldsize;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
if (mincount <= pc->size)
|
2005-04-17 05:20:36 +07:00
|
|
|
return 0;
|
|
|
|
oldsize = pc->size;
|
2008-02-04 22:48:03 +07:00
|
|
|
mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
|
|
|
|
(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
|
2008-01-30 19:30:13 +07:00
|
|
|
if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
|
|
|
|
newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
|
2005-04-17 05:20:36 +07:00
|
|
|
else
|
2008-01-30 19:33:14 +07:00
|
|
|
newldt = (void *)__get_free_page(GFP_KERNEL);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
if (!newldt)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (oldsize)
|
2008-01-30 19:30:13 +07:00
|
|
|
memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
|
2005-04-17 05:20:36 +07:00
|
|
|
oldldt = pc->ldt;
|
2008-01-30 19:30:13 +07:00
|
|
|
memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
|
|
|
|
(mincount - oldsize) * LDT_ENTRY_SIZE);
|
2008-01-30 19:30:14 +07:00
|
|
|
|
2008-07-24 04:21:18 +07:00
|
|
|
paravirt_alloc_ldt(newldt, mincount);
|
|
|
|
|
2008-01-30 19:30:14 +07:00
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
/* CHECKME: Do we really need this ? */
|
2005-04-17 05:20:36 +07:00
|
|
|
wmb();
|
2008-01-30 19:30:14 +07:00
|
|
|
#endif
|
2005-04-17 05:20:36 +07:00
|
|
|
pc->ldt = newldt;
|
|
|
|
wmb();
|
|
|
|
pc->size = mincount;
|
|
|
|
wmb();
|
2008-01-30 19:30:13 +07:00
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
if (reload) {
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
preempt_disable();
|
|
|
|
load_LDT(pc);
|
2009-09-24 22:34:51 +07:00
|
|
|
if (!cpumask_equal(mm_cpumask(current->mm),
|
|
|
|
cpumask_of(smp_processor_id())))
|
2008-07-16 02:55:59 +07:00
|
|
|
smp_call_function(flush_ldt, current->mm, 1);
|
2005-04-17 05:20:36 +07:00
|
|
|
preempt_enable();
|
|
|
|
#else
|
|
|
|
load_LDT(pc);
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
if (oldsize) {
|
2008-07-24 04:21:18 +07:00
|
|
|
paravirt_free_ldt(oldldt, oldsize);
|
2008-01-30 19:30:13 +07:00
|
|
|
if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
|
2005-04-17 05:20:36 +07:00
|
|
|
vfree(oldldt);
|
|
|
|
else
|
2008-01-30 19:33:14 +07:00
|
|
|
put_page(virt_to_page(oldldt));
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
|
|
|
|
{
|
|
|
|
int err = alloc_ldt(new, old->size, 0);
|
2008-07-24 04:21:18 +07:00
|
|
|
int i;
|
2008-01-30 19:30:13 +07:00
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
2008-07-24 04:21:18 +07:00
|
|
|
|
2008-12-31 18:12:20 +07:00
|
|
|
for (i = 0; i < old->size; i++)
|
2008-07-24 04:21:18 +07:00
|
|
|
write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
|
2005-04-17 05:20:36 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
{
|
2008-01-30 19:30:13 +07:00
|
|
|
struct mm_struct *old_mm;
|
2005-04-17 05:20:36 +07:00
|
|
|
int retval = 0;
|
|
|
|
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_init(&mm->context.lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
mm->context.size = 0;
|
|
|
|
old_mm = current->mm;
|
|
|
|
if (old_mm && old_mm->context.size > 0) {
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_lock(&old_mm->context.lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
retval = copy_ldt(&mm->context, &old_mm->context);
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_unlock(&old_mm->context.lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2008-01-30 19:30:14 +07:00
|
|
|
* 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.
|
2005-04-17 05:20:36 +07:00
|
|
|
*/
|
|
|
|
void destroy_context(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
if (mm->context.size) {
|
2008-01-30 19:30:14 +07:00
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
/* CHECKME: Can this ever happen ? */
|
|
|
|
if (mm == current->active_mm)
|
|
|
|
clear_LDT();
|
|
|
|
#endif
|
2008-07-24 04:21:18 +07:00
|
|
|
paravirt_free_ldt(mm->context.ldt, mm->context.size);
|
2008-01-30 19:30:13 +07:00
|
|
|
if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
|
2005-04-17 05:20:36 +07:00
|
|
|
vfree(mm->context.ldt);
|
|
|
|
else
|
2008-01-30 19:33:14 +07:00
|
|
|
put_page(virt_to_page(mm->context.ldt));
|
2005-04-17 05:20:36 +07:00
|
|
|
mm->context.size = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
static int read_ldt(void __user *ptr, unsigned long bytecount)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
unsigned long size;
|
2008-01-30 19:30:13 +07:00
|
|
|
struct mm_struct *mm = current->mm;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
if (!mm->context.size)
|
|
|
|
return 0;
|
2008-01-30 19:30:13 +07:00
|
|
|
if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
|
|
|
|
bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_lock(&mm->context.lock);
|
2008-01-30 19:30:13 +07:00
|
|
|
size = mm->context.size * LDT_ENTRY_SIZE;
|
2005-04-17 05:20:36 +07:00
|
|
|
if (size > bytecount)
|
|
|
|
size = bytecount;
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
if (copy_to_user(ptr, mm->context.ldt, size))
|
|
|
|
err = -EFAULT;
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_unlock(&mm->context.lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err < 0)
|
|
|
|
goto error_return;
|
|
|
|
if (size != bytecount) {
|
|
|
|
/* zero-fill the rest */
|
2008-01-30 19:30:13 +07:00
|
|
|
if (clear_user(ptr + size, bytecount - size) != 0) {
|
2005-04-17 05:20:36 +07:00
|
|
|
err = -EFAULT;
|
|
|
|
goto error_return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return bytecount;
|
|
|
|
error_return:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
static int read_default_ldt(void __user *ptr, unsigned long bytecount)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2008-01-30 19:30:14 +07:00
|
|
|
/* 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;
|
2005-04-17 05:20:36 +07:00
|
|
|
if (clear_user(ptr, bytecount))
|
|
|
|
return -EFAULT;
|
2008-01-30 19:30:13 +07:00
|
|
|
return bytecount;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2008-01-30 19:30:13 +07:00
|
|
|
struct mm_struct *mm = current->mm;
|
2008-01-30 19:31:13 +07:00
|
|
|
struct desc_struct ldt;
|
2005-04-17 05:20:36 +07:00
|
|
|
int error;
|
|
|
|
struct user_desc ldt_info;
|
|
|
|
|
|
|
|
error = -EINVAL;
|
|
|
|
if (bytecount != sizeof(ldt_info))
|
|
|
|
goto out;
|
2008-01-30 19:30:13 +07:00
|
|
|
error = -EFAULT;
|
2008-01-30 19:30:13 +07:00
|
|
|
if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
|
2005-04-17 05:20:36 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_lock(&mm->context.lock);
|
2008-01-30 19:30:13 +07:00
|
|
|
if (ldt_info.entry_number >= mm->context.size) {
|
2008-01-30 19:30:13 +07:00
|
|
|
error = alloc_ldt(¤t->mm->context,
|
|
|
|
ldt_info.entry_number + 1, 1);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
/* Allow LDTs to be cleared by the user. */
|
|
|
|
if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
|
2005-04-17 05:20:36 +07:00
|
|
|
if (oldmode || LDT_empty(&ldt_info)) {
|
2008-01-30 19:31:13 +07:00
|
|
|
memset(&ldt, 0, sizeof(ldt));
|
2005-04-17 05:20:36 +07:00
|
|
|
goto install;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-01-30 19:31:13 +07:00
|
|
|
fill_ldt(&ldt, &ldt_info);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (oldmode)
|
2008-01-30 19:31:13 +07:00
|
|
|
ldt.avl = 0;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/* Install the new entry ... */
|
|
|
|
install:
|
2008-01-30 19:31:13 +07:00
|
|
|
write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = 0;
|
|
|
|
|
|
|
|
out_unlock:
|
2007-10-17 23:04:41 +07:00
|
|
|
mutex_unlock(&mm->context.lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
out:
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2008-01-30 19:30:13 +07:00
|
|
|
asmlinkage int sys_modify_ldt(int func, void __user *ptr,
|
|
|
|
unsigned long bytecount)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
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;
|
|
|
|
}
|