Re: [PATCH v2] x86/sgx: Fix deadlock and race conditions between fork() and EPC reclaim

[Sean Christopherson <sean.j.christopherson@intel.com>]

On Fri, Apr 03, 2020 at 12:35:50PM +0300, Jarkko Sakkinen wrote:
> From: Sean Christopherson <sean.j.christopherson@intel.com>
> @@ -221,12 +224,16 @@ int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
>  		return ret;
>  	}
>  
> +	/*
> +	 * The page reclaimer uses list version for synchronization instead of
> +	 * synchronize_scru() because otherwise we could conflict with
> +	 * dup_mmap().
> +	 */
>  	spin_lock(&encl->mm_lock);
>  	list_add_rcu(&encl_mm->list, &encl->mm_list);

You dropped the smp_wmb().

> +	encl->mm_list_version++;
>  	spin_unlock(&encl->mm_lock);
>  
> -	synchronize_srcu(&encl->srcu);
> -
>  	return 0;
>  }
>  
> diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
> index 44b353aa8866..f0f72e591244 100644
> --- a/arch/x86/kernel/cpu/sgx/encl.h
> +++ b/arch/x86/kernel/cpu/sgx/encl.h
> @@ -74,6 +74,7 @@ struct sgx_encl {
>  	struct mutex lock;
>  	struct list_head mm_list;
>  	spinlock_t mm_lock;
> +	unsigned long mm_list_version;
>  	struct file *backing;
>  	struct kref refcount;
>  	struct srcu_struct srcu;
> diff --git a/arch/x86/kernel/cpu/sgx/reclaim.c b/arch/x86/kernel/cpu/sgx/reclaim.c
> index 39f0ddefbb79..5fb8bdfa6a1f 100644
> --- a/arch/x86/kernel/cpu/sgx/reclaim.c
> +++ b/arch/x86/kernel/cpu/sgx/reclaim.c
> @@ -184,28 +184,38 @@ static void sgx_reclaimer_block(struct sgx_epc_page *epc_page)
>  	struct sgx_encl_page *page = epc_page->owner;
>  	unsigned long addr = SGX_ENCL_PAGE_ADDR(page);
>  	struct sgx_encl *encl = page->encl;
> +	unsigned long mm_list_version;
>  	struct sgx_encl_mm *encl_mm;
>  	struct vm_area_struct *vma;
>  	int idx, ret;
>  
> -	idx = srcu_read_lock(&encl->srcu);
> +	do {
> +		mm_list_version = encl->mm_list_version;
>  
> -	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
> -		if (!mmget_not_zero(encl_mm->mm))
> -			continue;
> +		/* Fence reads as the CPU can reorder them. This guarantees
> +		 * that we don't access old list with a new version.

This comment is flat out wrong.  This has nothing to do the CPU reordering
things.  The smp_{r,w}mb() are nothing more than compiler barriers, and
even those go away when the kernel is built with SMP=0.

I don't mind gutting the other comments, but there is a well established
pattern form smb_wmb()/smp_rmb() pairs, I would strongly prefer to keep
the exact comment I submitted.

> +		 */
> +		smp_rmb();


>  
> -		down_read(&encl_mm->mm->mmap_sem);
> +		idx = srcu_read_lock(&encl->srcu);
>  
> -		ret = sgx_encl_find(encl_mm->mm, addr, &vma);
> -		if (!ret && encl == vma->vm_private_data)
> -			zap_vma_ptes(vma, addr, PAGE_SIZE);
> +		list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
> +			if (!mmget_not_zero(encl_mm->mm))
> +				continue;
>  
> -		up_read(&encl_mm->mm->mmap_sem);
> +			down_read(&encl_mm->mm->mmap_sem);
>  
> -		mmput_async(encl_mm->mm);
> -	}
> +			ret = sgx_encl_find(encl_mm->mm, addr, &vma);
> +			if (!ret && encl == vma->vm_private_data)
> +				zap_vma_ptes(vma, addr, PAGE_SIZE);
>  
> -	srcu_read_unlock(&encl->srcu, idx);
> +			up_read(&encl_mm->mm->mmap_sem);
> +
> +			mmput_async(encl_mm->mm);
> +		}
> +
> +		srcu_read_unlock(&encl->srcu, idx);
> +	} while (unlikely(encl->mm_list_version != mm_list_version));
>  
>  	mutex_lock(&encl->lock);
>  
> @@ -250,6 +260,11 @@ static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl)
>  	struct sgx_encl_mm *encl_mm;
>  	int idx;
>  
> +	/*
> +	 * Can race with sgx_encl_mm_add(), but ETRACK has already been
> +	 * executed, which means that the CPUs running in the new mm will enter
> +	 * into the enclave with a fresh epoch.
> +	 */
>  	cpumask_clear(cpumask);
>  
>  	idx = srcu_read_lock(&encl->srcu);
> -- 
> 2.25.1
>