linux/mm/filemap_xip.c
Andrea Arcangeli cddb8a5c14 mmu-notifiers: core
With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages.
 There are secondary MMUs (with secondary sptes and secondary tlbs) too.
sptes in the kvm case are shadow pagetables, but when I say spte in
mmu-notifier context, I mean "secondary pte".  In GRU case there's no
actual secondary pte and there's only a secondary tlb because the GRU
secondary MMU has no knowledge about sptes and every secondary tlb miss
event in the MMU always generates a page fault that has to be resolved by
the CPU (this is not the case of KVM where the a secondary tlb miss will
walk sptes in hardware and it will refill the secondary tlb transparently
to software if the corresponding spte is present).  The same way
zap_page_range has to invalidate the pte before freeing the page, the spte
(and secondary tlb) must also be invalidated before any page is freed and
reused.

Currently we take a page_count pin on every page mapped by sptes, but that
means the pages can't be swapped whenever they're mapped by any spte
because they're part of the guest working set.  Furthermore a spte unmap
event can immediately lead to a page to be freed when the pin is released
(so requiring the same complex and relatively slow tlb_gather smp safe
logic we have in zap_page_range and that can be avoided completely if the
spte unmap event doesn't require an unpin of the page previously mapped in
the secondary MMU).

The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know
when the VM is swapping or freeing or doing anything on the primary MMU so
that the secondary MMU code can drop sptes before the pages are freed,
avoiding all page pinning and allowing 100% reliable swapping of guest
physical address space.  Furthermore it avoids the code that teardown the
mappings of the secondary MMU, to implement a logic like tlb_gather in
zap_page_range that would require many IPI to flush other cpu tlbs, for
each fixed number of spte unmapped.

To make an example: if what happens on the primary MMU is a protection
downgrade (from writeable to wrprotect) the secondary MMU mappings will be
invalidated, and the next secondary-mmu-page-fault will call
get_user_pages and trigger a do_wp_page through get_user_pages if it
called get_user_pages with write=1, and it'll re-establishing an updated
spte or secondary-tlb-mapping on the copied page.  Or it will setup a
readonly spte or readonly tlb mapping if it's a guest-read, if it calls
get_user_pages with write=0.  This is just an example.

This allows to map any page pointed by any pte (and in turn visible in the
primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an
full MMU with both sptes and secondary-tlb like the shadow-pagetable layer
with kvm), or a remote DMA in software like XPMEM (hence needing of
schedule in XPMEM code to send the invalidate to the remote node, while no
need to schedule in kvm/gru as it's an immediate event like invalidating
primary-mmu pte).

At least for KVM without this patch it's impossible to swap guests
reliably.  And having this feature and removing the page pin allows
several other optimizations that simplify life considerably.

Dependencies:

1) mm_take_all_locks() to register the mmu notifier when the whole VM
   isn't doing anything with "mm".  This allows mmu notifier users to keep
   track if the VM is in the middle of the invalidate_range_begin/end
   critical section with an atomic counter incraese in range_begin and
   decreased in range_end.  No secondary MMU page fault is allowed to map
   any spte or secondary tlb reference, while the VM is in the middle of
   range_begin/end as any page returned by get_user_pages in that critical
   section could later immediately be freed without any further
   ->invalidate_page notification (invalidate_range_begin/end works on
   ranges and ->invalidate_page isn't called immediately before freeing
   the page).  To stop all page freeing and pagetable overwrites the
   mmap_sem must be taken in write mode and all other anon_vma/i_mmap
   locks must be taken too.

2) It'd be a waste to add branches in the VM if nobody could possibly
   run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if
   CONFIG_KVM=m/y.  In the current kernel kvm won't yet take advantage of
   mmu notifiers, but this already allows to compile a KVM external module
   against a kernel with mmu notifiers enabled and from the next pull from
   kvm.git we'll start using them.  And GRU/XPMEM will also be able to
   continue the development by enabling KVM=m in their config, until they
   submit all GRU/XPMEM GPLv2 code to the mainline kernel.  Then they can
   also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n).
   This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM
   are all =n.

The mmu_notifier_register call can fail because mm_take_all_locks may be
interrupted by a signal and return -EINTR.  Because mmu_notifier_reigster
is used when a driver startup, a failure can be gracefully handled.  Here
an example of the change applied to kvm to register the mmu notifiers.
Usually when a driver startups other allocations are required anyway and
-ENOMEM failure paths exists already.

 struct  kvm *kvm_arch_create_vm(void)
 {
        struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+       int err;

        if (!kvm)
                return ERR_PTR(-ENOMEM);

        INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);

+       kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops;
+       err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm);
+       if (err) {
+               kfree(kvm);
+               return ERR_PTR(err);
+       }
+
        return kvm;
 }

mmu_notifier_unregister returns void and it's reliable.

The patch also adds a few needed but missing includes that would prevent
kernel to compile after these changes on non-x86 archs (x86 didn't need
them by luck).

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix mm/filemap_xip.c build]
[akpm@linux-foundation.org: fix mm/mmu_notifier.c build]
Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Kanoj Sarcar <kanojsarcar@yahoo.com>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Chris Wright <chrisw@redhat.com>
Cc: Marcelo Tosatti <marcelo@kvack.org>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Izik Eidus <izike@qumranet.com>
Cc: Anthony Liguori <aliguori@us.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-28 16:30:21 -07:00

440 lines
10 KiB
C

/*
* linux/mm/filemap_xip.c
*
* Copyright (C) 2005 IBM Corporation
* Author: Carsten Otte <cotte@de.ibm.com>
*
* derived from linux/mm/filemap.c - Copyright (C) Linus Torvalds
*
*/
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/uio.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/sched.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
/*
* We do use our own empty page to avoid interference with other users
* of ZERO_PAGE(), such as /dev/zero
*/
static struct page *__xip_sparse_page;
static struct page *xip_sparse_page(void)
{
if (!__xip_sparse_page) {
struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
if (page) {
static DEFINE_SPINLOCK(xip_alloc_lock);
spin_lock(&xip_alloc_lock);
if (!__xip_sparse_page)
__xip_sparse_page = page;
else
__free_page(page);
spin_unlock(&xip_alloc_lock);
}
}
return __xip_sparse_page;
}
/*
* This is a file read routine for execute in place files, and uses
* the mapping->a_ops->get_xip_mem() function for the actual low-level
* stuff.
*
* Note the struct file* is not used at all. It may be NULL.
*/
static ssize_t
do_xip_mapping_read(struct address_space *mapping,
struct file_ra_state *_ra,
struct file *filp,
char __user *buf,
size_t len,
loff_t *ppos)
{
struct inode *inode = mapping->host;
pgoff_t index, end_index;
unsigned long offset;
loff_t isize, pos;
size_t copied = 0, error = 0;
BUG_ON(!mapping->a_ops->get_xip_mem);
pos = *ppos;
index = pos >> PAGE_CACHE_SHIFT;
offset = pos & ~PAGE_CACHE_MASK;
isize = i_size_read(inode);
if (!isize)
goto out;
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
do {
unsigned long nr, left;
void *xip_mem;
unsigned long xip_pfn;
int zero = 0;
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (nr <= offset) {
goto out;
}
}
nr = nr - offset;
if (nr > len)
nr = len;
error = mapping->a_ops->get_xip_mem(mapping, index, 0,
&xip_mem, &xip_pfn);
if (unlikely(error)) {
if (error == -ENODATA) {
/* sparse */
zero = 1;
} else
goto out;
}
/* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
/* address based flush */ ;
/*
* Ok, we have the mem, so now we can copy it to user space...
*
* The actor routine returns how many bytes were actually used..
* NOTE! This may not be the same as how much of a user buffer
* we filled up (we may be padding etc), so we can only update
* "pos" here (the actor routine has to update the user buffer
* pointers and the remaining count).
*/
if (!zero)
left = __copy_to_user(buf+copied, xip_mem+offset, nr);
else
left = __clear_user(buf + copied, nr);
if (left) {
error = -EFAULT;
goto out;
}
copied += (nr - left);
offset += (nr - left);
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
} while (copied < len);
out:
*ppos = pos + copied;
if (filp)
file_accessed(filp);
return (copied ? copied : error);
}
ssize_t
xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
if (!access_ok(VERIFY_WRITE, buf, len))
return -EFAULT;
return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
buf, len, ppos);
}
EXPORT_SYMBOL_GPL(xip_file_read);
/*
* __xip_unmap is invoked from xip_unmap and
* xip_write
*
* This function walks all vmas of the address_space and unmaps the
* __xip_sparse_page when found at pgoff.
*/
static void
__xip_unmap (struct address_space * mapping,
unsigned long pgoff)
{
struct vm_area_struct *vma;
struct mm_struct *mm;
struct prio_tree_iter iter;
unsigned long address;
pte_t *pte;
pte_t pteval;
spinlock_t *ptl;
struct page *page;
page = __xip_sparse_page;
if (!page)
return;
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
mm = vma->vm_mm;
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
pte = page_check_address(page, mm, address, &ptl);
if (pte) {
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
pteval = ptep_clear_flush_notify(vma, address, pte);
page_remove_rmap(page, vma);
dec_mm_counter(mm, file_rss);
BUG_ON(pte_dirty(pteval));
pte_unmap_unlock(pte, ptl);
page_cache_release(page);
}
}
spin_unlock(&mapping->i_mmap_lock);
}
/*
* xip_fault() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* This function is derived from filemap_fault, but used for execute in place
*/
static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
pgoff_t size;
void *xip_mem;
unsigned long xip_pfn;
struct page *page;
int error;
/* XXX: are VM_FAULT_ codes OK? */
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
&xip_mem, &xip_pfn);
if (likely(!error))
goto found;
if (error != -ENODATA)
return VM_FAULT_OOM;
/* sparse block */
if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
(vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) &&
(!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
int err;
/* maybe shared writable, allocate new block */
error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
&xip_mem, &xip_pfn);
if (error)
return VM_FAULT_SIGBUS;
/* unmap sparse mappings at pgoff from all other vmas */
__xip_unmap(mapping, vmf->pgoff);
found:
err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
xip_pfn);
if (err == -ENOMEM)
return VM_FAULT_OOM;
BUG_ON(err);
return VM_FAULT_NOPAGE;
} else {
/* not shared and writable, use xip_sparse_page() */
page = xip_sparse_page();
if (!page)
return VM_FAULT_OOM;
page_cache_get(page);
vmf->page = page;
return 0;
}
}
static struct vm_operations_struct xip_file_vm_ops = {
.fault = xip_file_fault,
};
int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
{
BUG_ON(!file->f_mapping->a_ops->get_xip_mem);
file_accessed(file);
vma->vm_ops = &xip_file_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP;
return 0;
}
EXPORT_SYMBOL_GPL(xip_file_mmap);
static ssize_t
__xip_file_write(struct file *filp, const char __user *buf,
size_t count, loff_t pos, loff_t *ppos)
{
struct address_space * mapping = filp->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
struct inode *inode = mapping->host;
long status = 0;
size_t bytes;
ssize_t written = 0;
BUG_ON(!mapping->a_ops->get_xip_mem);
do {
unsigned long index;
unsigned long offset;
size_t copied;
void *xip_mem;
unsigned long xip_pfn;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
index = pos >> PAGE_CACHE_SHIFT;
bytes = PAGE_CACHE_SIZE - offset;
if (bytes > count)
bytes = count;
status = a_ops->get_xip_mem(mapping, index, 0,
&xip_mem, &xip_pfn);
if (status == -ENODATA) {
/* we allocate a new page unmap it */
status = a_ops->get_xip_mem(mapping, index, 1,
&xip_mem, &xip_pfn);
if (!status)
/* unmap page at pgoff from all other vmas */
__xip_unmap(mapping, index);
}
if (status)
break;
copied = bytes -
__copy_from_user_nocache(xip_mem + offset, buf, bytes);
if (likely(copied > 0)) {
status = copied;
if (status >= 0) {
written += status;
count -= status;
pos += status;
buf += status;
}
}
if (unlikely(copied != bytes))
if (status >= 0)
status = -EFAULT;
if (status < 0)
break;
} while (count);
*ppos = pos;
/*
* No need to use i_size_read() here, the i_size
* cannot change under us because we hold i_mutex.
*/
if (pos > inode->i_size) {
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
return written ? written : status;
}
ssize_t
xip_file_write(struct file *filp, const char __user *buf, size_t len,
loff_t *ppos)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
size_t count;
loff_t pos;
ssize_t ret;
mutex_lock(&inode->i_mutex);
if (!access_ok(VERIFY_READ, buf, len)) {
ret=-EFAULT;
goto out_up;
}
pos = *ppos;
count = len;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
if (ret)
goto out_backing;
if (count == 0)
goto out_backing;
ret = file_remove_suid(filp);
if (ret)
goto out_backing;
file_update_time(filp);
ret = __xip_file_write (filp, buf, count, pos, ppos);
out_backing:
current->backing_dev_info = NULL;
out_up:
mutex_unlock(&inode->i_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(xip_file_write);
/*
* truncate a page used for execute in place
* functionality is analog to block_truncate_page but does use get_xip_mem
* to get the page instead of page cache
*/
int
xip_truncate_page(struct address_space *mapping, loff_t from)
{
pgoff_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize;
unsigned length;
void *xip_mem;
unsigned long xip_pfn;
int err;
BUG_ON(!mapping->a_ops->get_xip_mem);
blocksize = 1 << mapping->host->i_blkbits;
length = offset & (blocksize - 1);
/* Block boundary? Nothing to do */
if (!length)
return 0;
length = blocksize - length;
err = mapping->a_ops->get_xip_mem(mapping, index, 0,
&xip_mem, &xip_pfn);
if (unlikely(err)) {
if (err == -ENODATA)
/* Hole? No need to truncate */
return 0;
else
return err;
}
memset(xip_mem + offset, 0, length);
return 0;
}
EXPORT_SYMBOL_GPL(xip_truncate_page);