mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-25 02:09:42 +00:00
![Andrea Arcangeli](/assets/img/avatar_default.png)
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>
319 lines
7.5 KiB
C
319 lines
7.5 KiB
C
/*
|
|
* mm/mprotect.c
|
|
*
|
|
* (C) Copyright 1994 Linus Torvalds
|
|
* (C) Copyright 2002 Christoph Hellwig
|
|
*
|
|
* Address space accounting code <alan@redhat.com>
|
|
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/shm.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/security.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/personality.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#ifndef pgprot_modify
|
|
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
|
|
{
|
|
return newprot;
|
|
}
|
|
#endif
|
|
|
|
static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pte_t *pte, oldpte;
|
|
spinlock_t *ptl;
|
|
|
|
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
|
|
arch_enter_lazy_mmu_mode();
|
|
do {
|
|
oldpte = *pte;
|
|
if (pte_present(oldpte)) {
|
|
pte_t ptent;
|
|
|
|
ptent = ptep_modify_prot_start(mm, addr, pte);
|
|
ptent = pte_modify(ptent, newprot);
|
|
|
|
/*
|
|
* Avoid taking write faults for pages we know to be
|
|
* dirty.
|
|
*/
|
|
if (dirty_accountable && pte_dirty(ptent))
|
|
ptent = pte_mkwrite(ptent);
|
|
|
|
ptep_modify_prot_commit(mm, addr, pte, ptent);
|
|
#ifdef CONFIG_MIGRATION
|
|
} else if (!pte_file(oldpte)) {
|
|
swp_entry_t entry = pte_to_swp_entry(oldpte);
|
|
|
|
if (is_write_migration_entry(entry)) {
|
|
/*
|
|
* A protection check is difficult so
|
|
* just be safe and disable write
|
|
*/
|
|
make_migration_entry_read(&entry);
|
|
set_pte_at(mm, addr, pte,
|
|
swp_entry_to_pte(entry));
|
|
}
|
|
#endif
|
|
}
|
|
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
arch_leave_lazy_mmu_mode();
|
|
pte_unmap_unlock(pte - 1, ptl);
|
|
}
|
|
|
|
static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
continue;
|
|
change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);
|
|
} while (pmd++, addr = next, addr != end);
|
|
}
|
|
|
|
static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (pud_none_or_clear_bad(pud))
|
|
continue;
|
|
change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable);
|
|
} while (pud++, addr = next, addr != end);
|
|
}
|
|
|
|
static void change_protection(struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
int dirty_accountable)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
unsigned long start = addr;
|
|
|
|
BUG_ON(addr >= end);
|
|
pgd = pgd_offset(mm, addr);
|
|
flush_cache_range(vma, addr, end);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
continue;
|
|
change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
|
|
} while (pgd++, addr = next, addr != end);
|
|
flush_tlb_range(vma, start, end);
|
|
}
|
|
|
|
int
|
|
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
|
|
unsigned long start, unsigned long end, unsigned long newflags)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
unsigned long oldflags = vma->vm_flags;
|
|
long nrpages = (end - start) >> PAGE_SHIFT;
|
|
unsigned long charged = 0;
|
|
pgoff_t pgoff;
|
|
int error;
|
|
int dirty_accountable = 0;
|
|
|
|
if (newflags == oldflags) {
|
|
*pprev = vma;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* If we make a private mapping writable we increase our commit;
|
|
* but (without finer accounting) cannot reduce our commit if we
|
|
* make it unwritable again.
|
|
*/
|
|
if (newflags & VM_WRITE) {
|
|
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
|
|
VM_SHARED|VM_NORESERVE))) {
|
|
charged = nrpages;
|
|
if (security_vm_enough_memory(charged))
|
|
return -ENOMEM;
|
|
newflags |= VM_ACCOUNT;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* First try to merge with previous and/or next vma.
|
|
*/
|
|
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
|
|
*pprev = vma_merge(mm, *pprev, start, end, newflags,
|
|
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
|
|
if (*pprev) {
|
|
vma = *pprev;
|
|
goto success;
|
|
}
|
|
|
|
*pprev = vma;
|
|
|
|
if (start != vma->vm_start) {
|
|
error = split_vma(mm, vma, start, 1);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
if (end != vma->vm_end) {
|
|
error = split_vma(mm, vma, end, 0);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
success:
|
|
/*
|
|
* vm_flags and vm_page_prot are protected by the mmap_sem
|
|
* held in write mode.
|
|
*/
|
|
vma->vm_flags = newflags;
|
|
vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
|
|
vm_get_page_prot(newflags));
|
|
|
|
if (vma_wants_writenotify(vma)) {
|
|
vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
|
|
dirty_accountable = 1;
|
|
}
|
|
|
|
mmu_notifier_invalidate_range_start(mm, start, end);
|
|
if (is_vm_hugetlb_page(vma))
|
|
hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
|
|
else
|
|
change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
|
|
mmu_notifier_invalidate_range_end(mm, start, end);
|
|
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
|
|
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
|
|
return 0;
|
|
|
|
fail:
|
|
vm_unacct_memory(charged);
|
|
return error;
|
|
}
|
|
|
|
asmlinkage long
|
|
sys_mprotect(unsigned long start, size_t len, unsigned long prot)
|
|
{
|
|
unsigned long vm_flags, nstart, end, tmp, reqprot;
|
|
struct vm_area_struct *vma, *prev;
|
|
int error = -EINVAL;
|
|
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
|
|
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
|
|
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
|
|
return -EINVAL;
|
|
|
|
if (start & ~PAGE_MASK)
|
|
return -EINVAL;
|
|
if (!len)
|
|
return 0;
|
|
len = PAGE_ALIGN(len);
|
|
end = start + len;
|
|
if (end <= start)
|
|
return -ENOMEM;
|
|
if (!arch_validate_prot(prot))
|
|
return -EINVAL;
|
|
|
|
reqprot = prot;
|
|
/*
|
|
* Does the application expect PROT_READ to imply PROT_EXEC:
|
|
*/
|
|
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
|
|
prot |= PROT_EXEC;
|
|
|
|
vm_flags = calc_vm_prot_bits(prot);
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
vma = find_vma_prev(current->mm, start, &prev);
|
|
error = -ENOMEM;
|
|
if (!vma)
|
|
goto out;
|
|
if (unlikely(grows & PROT_GROWSDOWN)) {
|
|
if (vma->vm_start >= end)
|
|
goto out;
|
|
start = vma->vm_start;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto out;
|
|
}
|
|
else {
|
|
if (vma->vm_start > start)
|
|
goto out;
|
|
if (unlikely(grows & PROT_GROWSUP)) {
|
|
end = vma->vm_end;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSUP))
|
|
goto out;
|
|
}
|
|
}
|
|
if (start > vma->vm_start)
|
|
prev = vma;
|
|
|
|
for (nstart = start ; ; ) {
|
|
unsigned long newflags;
|
|
|
|
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
|
|
|
|
newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
|
|
|
|
/* newflags >> 4 shift VM_MAY% in place of VM_% */
|
|
if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
|
|
error = -EACCES;
|
|
goto out;
|
|
}
|
|
|
|
error = security_file_mprotect(vma, reqprot, prot);
|
|
if (error)
|
|
goto out;
|
|
|
|
tmp = vma->vm_end;
|
|
if (tmp > end)
|
|
tmp = end;
|
|
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
|
|
if (error)
|
|
goto out;
|
|
nstart = tmp;
|
|
|
|
if (nstart < prev->vm_end)
|
|
nstart = prev->vm_end;
|
|
if (nstart >= end)
|
|
goto out;
|
|
|
|
vma = prev->vm_next;
|
|
if (!vma || vma->vm_start != nstart) {
|
|
error = -ENOMEM;
|
|
goto out;
|
|
}
|
|
}
|
|
out:
|
|
up_write(¤t->mm->mmap_sem);
|
|
return error;
|
|
}
|