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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e3aca3b7-4f38-410d-91d6-5a2521dedb6c@oracle.com>
Date: Tue, 12 Aug 2025 10:12:14 -0700
From: Anthony Yznaga <anthony.yznaga@...cle.com>
To: Yongting Lin <linyongting@...edance.com>
Cc: akpm@...ux-foundation.org, andreyknvl@...il.com, arnd@...db.de,
        brauner@...nel.org, catalin.marinas@....com, dave.hansen@...el.com,
        david@...hat.com, ebiederm@...ssion.com, khalid@...nel.org,
        linux-arch@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, luto@...nel.org, markhemm@...glemail.com,
        maz@...nel.org, mhiramat@...nel.org, neilb@...e.de, pcc@...gle.com,
        rostedt@...dmis.org, vasily.averin@...ux.dev, viro@...iv.linux.org.uk,
        willy@...radead.org, xhao@...ux.alibaba.com
Subject: Re: [PATCH v2 13/20] x86/mm: enable page table sharing



On 8/12/25 6:46 AM, Yongting Lin wrote:
> Hi,
> 
> On 4/4/25 10:18 AM, Anthony Yznaga wrote:
>> Enable x86 support for handling page faults in an mshare region by
>> redirecting page faults to operate on the mshare mm_struct and vmas
>> contained in it.
>> Some permissions checks are done using vma flags in architecture-specfic
>> fault handling code so the actual vma needed to complete the handling
>> is acquired before calling handle_mm_fault(). Because of this an
>> ARCH_SUPPORTS_MSHARE config option is added.
>>
>> Signed-off-by: Anthony Yznaga <anthony.yznaga@...cle.com>
>> ---
>>   arch/Kconfig        |  3 +++
>>   arch/x86/Kconfig    |  1 +
>>   arch/x86/mm/fault.c | 37 ++++++++++++++++++++++++++++++++++++-
>>   mm/Kconfig          |  2 +-
>>   4 files changed, 41 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/Kconfig b/arch/Kconfig
>> index 9f6eb09ef12d..2e000fefe9b3 100644
>> --- a/arch/Kconfig
>> +++ b/arch/Kconfig
>> @@ -1652,6 +1652,9 @@ config HAVE_ARCH_PFN_VALID
>>   config ARCH_SUPPORTS_DEBUG_PAGEALLOC
>>   	bool
>>   
>> +config ARCH_SUPPORTS_MSHARE
>> +	bool
>> +
>>   config ARCH_SUPPORTS_PAGE_TABLE_CHECK
>>   	bool
>>   
>> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
>> index 1502fd0c3c06..1f1779decb44 100644
>> --- a/arch/x86/Kconfig
>> +++ b/arch/x86/Kconfig
>> @@ -125,6 +125,7 @@ config X86
>>   	select ARCH_SUPPORTS_ACPI
>>   	select ARCH_SUPPORTS_ATOMIC_RMW
>>   	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
>> +	select ARCH_SUPPORTS_MSHARE		if X86_64
>>   	select ARCH_SUPPORTS_PAGE_TABLE_CHECK	if X86_64
>>   	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
>>   	select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP	if NR_CPUS <= 4096
>> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
>> index 296d294142c8..49659d2f9316 100644
>> --- a/arch/x86/mm/fault.c
>> +++ b/arch/x86/mm/fault.c
>> @@ -1216,6 +1216,8 @@ void do_user_addr_fault(struct pt_regs *regs,
>>   	struct mm_struct *mm;
>>   	vm_fault_t fault;
>>   	unsigned int flags = FAULT_FLAG_DEFAULT;
>> +	bool is_shared_vma;
>> +	unsigned long addr;
>>   
>>   	tsk = current;
>>   	mm = tsk->mm;
>> @@ -1329,6 +1331,12 @@ void do_user_addr_fault(struct pt_regs *regs,
>>   	if (!vma)
>>   		goto lock_mmap;
>>   
>> +	/* mshare does not support per-VMA locks yet */
>> +	if (vma_is_mshare(vma)) {
>> +		vma_end_read(vma);
>> +		goto lock_mmap;
>> +	}
>> +
>>   	if (unlikely(access_error(error_code, vma))) {
>>   		bad_area_access_error(regs, error_code, address, NULL, vma);
>>   		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
>> @@ -1357,17 +1365,38 @@ void do_user_addr_fault(struct pt_regs *regs,
>>   lock_mmap:
>>   
>>   retry:
>> +	addr = address;
>> +	is_shared_vma = false;
>>   	vma = lock_mm_and_find_vma(mm, address, regs);
>>   	if (unlikely(!vma)) {
>>   		bad_area_nosemaphore(regs, error_code, address);
>>   		return;
>>   	}
>>   
>> +	if (unlikely(vma_is_mshare(vma))) {
>> +		fault = find_shared_vma(&vma, &addr);
>> +
>> +		if (fault) {
>> +			mmap_read_unlock(mm);
>> +			goto done;
>> +		}
>> +
>> +		if (!vma) {
>> +			mmap_read_unlock(mm);
>> +			bad_area_nosemaphore(regs, error_code, address);
>> +			return;
>> +		}
>> +
>> +		is_shared_vma = true;
>> +	}
>> +
>>   	/*
>>   	 * Ok, we have a good vm_area for this memory access, so
>>   	 * we can handle it..
>>   	 */
>>   	if (unlikely(access_error(error_code, vma))) {
>> +		if (unlikely(is_shared_vma))
>> +			mmap_read_unlock(vma->vm_mm);
>>   		bad_area_access_error(regs, error_code, address, mm, vma);
>>   		return;
>>   	}
>> @@ -1385,7 +1414,11 @@ void do_user_addr_fault(struct pt_regs *regs,
>>   	 * userland). The return to userland is identified whenever
>>   	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
>>   	 */
>> -	fault = handle_mm_fault(vma, address, flags, regs);
>> +	fault = handle_mm_fault(vma, addr, flags, regs);
>> +
>> +	if (unlikely(is_shared_vma) && ((fault & VM_FAULT_COMPLETED) ||
>> +	    (fault & VM_FAULT_RETRY) || fault_signal_pending(fault, regs)))
>> +		mmap_read_unlock(mm);
> 
> I was backporting these patches of mshare to 5.15 kernel and trying to do some
> basic tests. Then found a potential issue.
> 
> Reaching here means find_shared_vma function has been executed successfully
> and host_mm->mmap_lock has got locked.
> 
> When returned fault variable has VM_FAULT_COMPLETED or VM_FAULT_RETRY flags,
> or fault_signal_pending(fault, regs) takes true, there is not chance to release
> locks of both mm and host_mm(i.e. vma->vm_mm) in the following Snippet of Code.

If VM_FAULT_COMPLETED or VM_FAULT_RETRY are returned then the 
host_mm->mmap_lock will already have been released. See 
fault_dirty_shared_page(), filemap_fault(), and other callers of 
maybe_unlock_mmap_for_io(). I will add a comment to help make this 
clearer. I also realized that fault_signal_pending() does not need to be 
called here because it can only return true if VM_FAULT_RETRY is set so 
I'll change that, too.

The checks in a 5.15 kernel will be different. You probably want 
something like:

         if (unlikely(is_shared_vma) && ((fault & VM_FAULT_RETRY) &&
             (flags & FAULT_FLAG_ALLOW_RETRY)) || 
fault_signal_pending(fault, regs))
                 mmap_read_unlock(mm);

Anthony

> 
> As a result, needs to release vma->vm_mm.mmap_lock as well.
> 
> So it is supposed to be like below:
> 
> -	fault = handle_mm_fault(vma, address, flags, regs);
> +	fault = handle_mm_fault(vma, addr, flags, regs);
> +
> +	if (unlikely(is_shared_vma) && ((fault & VM_FAULT_COMPLETED) ||
> +	    (fault & VM_FAULT_RETRY) || fault_signal_pending(fault, regs))) {
> +		mmap_read_unlock(vma->vm_mm);
> +		mmap_read_unlock(mm);
> +	}
> 
>>   
>>   	if (fault_signal_pending(fault, regs)) {
>>   		/*
>> @@ -1413,6 +1446,8 @@ void do_user_addr_fault(struct pt_regs *regs,
>>   		goto retry;
>>   	}
>>   
>> +	if (unlikely(is_shared_vma))
>> +		mmap_read_unlock(vma->vm_mm);
>>   	mmap_read_unlock(mm);
>>   done:
>>   	if (likely(!(fault & VM_FAULT_ERROR)))
>> diff --git a/mm/Kconfig b/mm/Kconfig
>> index e6c90db83d01..8a5a159457f2 100644
>> --- a/mm/Kconfig
>> +++ b/mm/Kconfig
>> @@ -1344,7 +1344,7 @@ config PT_RECLAIM
>>   
>>   config MSHARE
>>   	bool "Mshare"
>> -	depends on MMU
>> +	depends on MMU && ARCH_SUPPORTS_MSHARE
>>   	help
>>   	  Enable msharefs: A ram-based filesystem that allows multiple
>>   	  processes to share page table entries for shared pages. A file
> 
> Yongting Lin.


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ