| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <8bb04603-f55e-3c46-8f29-a183ba6ef47b@linux.vnet.ibm.com>
Date: Wed, 28 Mar 2018 18:57:21 +0200
From: Laurent Dufour <ldufour@...ux.vnet.ibm.com>
To: David Rientjes <rientjes@...gle.com>
Cc: paulmck@...ux.vnet.ibm.com, peterz@...radead.org,
akpm@...ux-foundation.org, kirill@...temov.name,
ak@...ux.intel.com, mhocko@...nel.org, dave@...olabs.net,
jack@...e.cz, Matthew Wilcox <willy@...radead.org>,
benh@...nel.crashing.org, mpe@...erman.id.au, paulus@...ba.org,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, hpa@...or.com,
Will Deacon <will.deacon@....com>,
Sergey Senozhatsky <sergey.senozhatsky@...il.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
kemi.wang@...el.com, sergey.senozhatsky.work@...il.com,
Daniel Jordan <daniel.m.jordan@...cle.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
haren@...ux.vnet.ibm.com, khandual@...ux.vnet.ibm.com,
npiggin@...il.com, bsingharora@...il.com,
Tim Chen <tim.c.chen@...ux.intel.com>,
linuxppc-dev@...ts.ozlabs.org, x86@...nel.org
Subject: Re: [PATCH v9 08/24] mm: Protect VMA modifications using VMA sequence
count
On 27/03/2018 23:45, David Rientjes wrote:
> On Tue, 13 Mar 2018, Laurent Dufour wrote:
>
>> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
>> index 65ae54659833..a2d9c87b7b0b 100644
>> --- a/fs/proc/task_mmu.c
>> +++ b/fs/proc/task_mmu.c
>> @@ -1136,8 +1136,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
>> goto out_mm;
>> }
>> for (vma = mm->mmap; vma; vma = vma->vm_next) {
>> - vma->vm_flags &= ~VM_SOFTDIRTY;
>> + vm_write_begin(vma);
>> + WRITE_ONCE(vma->vm_flags,
>> + vma->vm_flags & ~VM_SOFTDIRTY);
>> vma_set_page_prot(vma);
>> + vm_write_end(vma);
>> }
>> downgrade_write(&mm->mmap_sem);
>> break;
>> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
>> index cec550c8468f..b8212ba17695 100644
>> --- a/fs/userfaultfd.c
>> +++ b/fs/userfaultfd.c
>> @@ -659,8 +659,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
>>
>> octx = vma->vm_userfaultfd_ctx.ctx;
>> if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
>> + vm_write_begin(vma);
>> vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
>> - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
>> + WRITE_ONCE(vma->vm_flags,
>> + vma->vm_flags & ~(VM_UFFD_WP | VM_UFFD_MISSING));
>> + vm_write_end(vma);
>> return 0;
>> }
>>
>
> In several locations in this patch vm_write_begin(vma) ->
> vm_write_end(vma) is nesting things other than vma->vm_flags,
> vma->vm_policy, etc. I think it's better to do vm_write_end(vma) as soon
> as the members that the seqcount protects are modified. In other words,
> this isn't offering protection for vma->vm_userfaultfd_ctx. There are
> several examples of this in the patch.
That's true in this particular case, and I could change that to not include the
change to vm_userfaultfd_ctx.
This being said, I don't think this will have a major impact, but I'll make a
close review on this patch to be sure there is too large protected part of code.
>> @@ -885,8 +888,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
>> vma = prev;
>> else
>> prev = vma;
>> - vma->vm_flags = new_flags;
>> + vm_write_begin(vma);
>> + WRITE_ONCE(vma->vm_flags, new_flags);
>> vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
>> + vm_write_end(vma);
>> }
>> up_write(&mm->mmap_sem);
>> mmput(mm);
>> @@ -1434,8 +1439,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
>> * the next vma was merged into the current one and
>> * the current one has not been updated yet.
>> */
>> - vma->vm_flags = new_flags;
>> + vm_write_begin(vma);
>> + WRITE_ONCE(vma->vm_flags, new_flags);
>> vma->vm_userfaultfd_ctx.ctx = ctx;
>> + vm_write_end(vma);
>>
>> skip:
>> prev = vma;
>> @@ -1592,8 +1599,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
>> * the next vma was merged into the current one and
>> * the current one has not been updated yet.
>> */
>> - vma->vm_flags = new_flags;
>> + vm_write_begin(vma);
>> + WRITE_ONCE(vma->vm_flags, new_flags);
>> vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
>> + vm_write_end(vma);
>>
>> skip:
>> prev = vma;
>> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
>> index b7e2268dfc9a..32314e9e48dd 100644
>> --- a/mm/khugepaged.c
>> +++ b/mm/khugepaged.c
>> @@ -1006,6 +1006,7 @@ static void collapse_huge_page(struct mm_struct *mm,
>> if (mm_find_pmd(mm, address) != pmd)
>> goto out;
>>
>> + vm_write_begin(vma);
>> anon_vma_lock_write(vma->anon_vma);
>>
>> pte = pte_offset_map(pmd, address);
>> @@ -1041,6 +1042,7 @@ static void collapse_huge_page(struct mm_struct *mm,
>> pmd_populate(mm, pmd, pmd_pgtable(_pmd));
>> spin_unlock(pmd_ptl);
>> anon_vma_unlock_write(vma->anon_vma);
>> + vm_write_end(vma);
>> result = SCAN_FAIL;
>> goto out;
>> }
>> @@ -1075,6 +1077,7 @@ static void collapse_huge_page(struct mm_struct *mm,
>> set_pmd_at(mm, address, pmd, _pmd);
>> update_mmu_cache_pmd(vma, address, pmd);
>> spin_unlock(pmd_ptl);
>> + vm_write_end(vma);
>>
>> *hpage = NULL;
>>
>> diff --git a/mm/madvise.c b/mm/madvise.c
>> index 4d3c922ea1a1..e328f7ab5942 100644
>> --- a/mm/madvise.c
>> +++ b/mm/madvise.c
>> @@ -184,7 +184,9 @@ static long madvise_behavior(struct vm_area_struct *vma,
>> /*
>> * vm_flags is protected by the mmap_sem held in write mode.
>> */
>> - vma->vm_flags = new_flags;
>> + vm_write_begin(vma);
>> + WRITE_ONCE(vma->vm_flags, new_flags);
>> + vm_write_end(vma);
>> out:
>> return error;
>> }
>> @@ -450,9 +452,11 @@ static void madvise_free_page_range(struct mmu_gather *tlb,
>> .private = tlb,
>> };
>>
>> + vm_write_begin(vma);
>> tlb_start_vma(tlb, vma);
>> walk_page_range(addr, end, &free_walk);
>> tlb_end_vma(tlb, vma);
>> + vm_write_end(vma);
>> }
>>
>> static int madvise_free_single_vma(struct vm_area_struct *vma,
>> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
>> index e0e706f0b34e..2632c6f93b63 100644
>> --- a/mm/mempolicy.c
>> +++ b/mm/mempolicy.c
>> @@ -380,8 +380,11 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
>> struct vm_area_struct *vma;
>>
>> down_write(&mm->mmap_sem);
>> - for (vma = mm->mmap; vma; vma = vma->vm_next)
>> + for (vma = mm->mmap; vma; vma = vma->vm_next) {
>> + vm_write_begin(vma);
>> mpol_rebind_policy(vma->vm_policy, new);
>> + vm_write_end(vma);
>> + }
>> up_write(&mm->mmap_sem);
>> }
>>
>> @@ -554,9 +557,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
>> {
>> int nr_updated;
>>
>> + vm_write_begin(vma);
>> nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
>> if (nr_updated)
>> count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
>> + vm_write_end(vma);
>>
>> return nr_updated;
>> }
>> @@ -657,6 +662,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
>> if (IS_ERR(new))
>> return PTR_ERR(new);
>>
>> + vm_write_begin(vma);
>> if (vma->vm_ops && vma->vm_ops->set_policy) {
>> err = vma->vm_ops->set_policy(vma, new);
>> if (err)
>> @@ -664,11 +670,17 @@ static int vma_replace_policy(struct vm_area_struct *vma,
>> }
>>
>> old = vma->vm_policy;
>> - vma->vm_policy = new; /* protected by mmap_sem */
>> + /*
>> + * The speculative page fault handler access this field without
>> + * hodling the mmap_sem.
>> + */
>
> "The speculative page fault handler accesses this field without holding
> vma->vm_mm->mmap_sem"
Oops :/
>
>> + WRITE_ONCE(vma->vm_policy, new);
>> + vm_write_end(vma);
>> mpol_put(old);
>>
>> return 0;
>> err_out:
>> + vm_write_end(vma);
>> mpol_put(new);
>> return err;
>> }
>
> Wait, doesn't vma_dup_policy() also need to protect dst->vm_policy?
Indeed this is not necessary because vma_dup_policy() is called when dst is not
yet linked in the RB tree, so it can't be found by the speculative page fault
handler. This is not the case of vma_replace_policy, and this is why the
protection are needed here.
>
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -2121,7 +2121,9 @@ int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
>
> if (IS_ERR(pol))
> return PTR_ERR(pol);
> - dst->vm_policy = pol;
> + vm_write_begin(dst);
> + WRITE_ONCE(dst->vm_policy, pol);
> + vm_write_end(dst);
> return 0;
> }
Powered by blists - more mailing lists