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

[Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>]

On Mon, Mar 16, 2020 at 10:15:39PM -0700, Sean Christopherson wrote:
> Drop the synchronize_srcu() from sgx_encl_mm_add() and replace it with a
> mm_list versioning concept to avoid deadlock when adding a mm during
> dup_mmap()/fork(), and to ensure copied PTEs are zapped.
> 
> When dup_mmap() runs, it holds mmap_sem for write in both the old mm and
> new mm.  Invoking synchronize_srcu() while holding mmap_sem of a mm that
> is already attached to the enclave will deadlock if the reclaimer is in
> the process of walking mm_list, as the reclaimer will try to acquire
> mmap_sem (of the old mm) while holding encl->srcu for read.
> 
>  INFO: task ksgxswapd:181 blocked for more than 120 seconds.
>  ksgxswapd       D    0   181      2 0x80004000
>  Call Trace:
>   __schedule+0x2db/0x700
>   schedule+0x44/0xb0
>   rwsem_down_read_slowpath+0x370/0x470
>   down_read+0x95/0xa0
>   sgx_reclaim_pages+0x1d2/0x7d0
>   ksgxswapd+0x151/0x2e0
>   kthread+0x120/0x140
>   ret_from_fork+0x35/0x40
> 
>  INFO: task fork_consistenc:18824 blocked for more than 120 seconds.
>  fork_consistenc D    0 18824  18786 0x00004320
>  Call Trace:
>   __schedule+0x2db/0x700
>   schedule+0x44/0xb0
>   schedule_timeout+0x205/0x300
>   wait_for_completion+0xb7/0x140
>   __synchronize_srcu.part.22+0x81/0xb0
>   synchronize_srcu_expedited+0x27/0x30
>   synchronize_srcu+0x57/0xe0
>   sgx_encl_mm_add+0x12b/0x160
>   sgx_vma_open+0x22/0x40
>   dup_mm+0x521/0x580
>   copy_process+0x1a56/0x1b50
>   _do_fork+0x85/0x3a0
>   __x64_sys_clone+0x8e/0xb0
>   do_syscall_64+0x57/0x1b0
>   entry_SYSCALL_64_after_hwframe+0x44/0xa9
> 
> Furthermore, doing synchronize_srcu() in sgx_encl_mm_add() does not
> prevent the new mm from having stale PTEs pointing at the EPC page to be
> reclaimed.  dup_mmap() calls vm_ops->open()/sgx_encl_mm_add() _after_
> PTEs are copied to the new mm, i.e. blocking fork() until reclaim zaps
> the old mm is pointless as the stale PTEs have already been created in
> the new mm.
> 
> All other flows that walk mm_list can safely race with dup_mmap() or are
> protected by a different mechanism.  Add comments to all srcu readers
> that don't check the list version to document why its ok for the flow to
> ignore the version.
> 
> Note, synchronize_srcu() is still needed when removing a mm from an
> enclave, as the srcu readers must complete their walk before the mm can
> be freed.  Removing a mm is never done while holding mmap_sem.
> 
> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
> ---
>  arch/x86/kernel/cpu/sgx/encl.c    | 22 +++++++++++++++++++--
>  arch/x86/kernel/cpu/sgx/encl.h    |  1 +
>  arch/x86/kernel/cpu/sgx/reclaim.c | 33 +++++++++++++++++++++++++++++++
>  3 files changed, 54 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
> index d6a19bdd1921..b9a7c56f7c25 100644
> --- a/arch/x86/kernel/cpu/sgx/encl.c
> +++ b/arch/x86/kernel/cpu/sgx/encl.c
> @@ -196,6 +196,12 @@ int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
>  	struct sgx_encl_mm *encl_mm;
>  	int ret;
>  
> +	/*
> +	 * This flow relies on mmap_sem to provide mutual exclusivity (for a
> +	 * given mm) to prevent duplicate instances of an encl_mm on the list.
> +	 */
> +	lockdep_assert_held_write(&mm->mmap_sem);
> +
>  	if (atomic_read(&encl->flags) & SGX_ENCL_DEAD)
>  		return -EINVAL;
>  
> @@ -223,10 +229,22 @@ int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
>  
>  	spin_lock(&encl->mm_lock);
>  	list_add_rcu(&encl_mm->list, &encl->mm_list);
> +	/*
> +	 * Ensure the mm is added to the list before updating the version.
> +	 * Pairs with the smp_rmb() in sgx_reclaimer_block().
> +	 */
> +	smp_wmb();
> +	encl->mm_list_version++;
>  	spin_unlock(&encl->mm_lock);
>  
> -	synchronize_srcu(&encl->srcu);
> -
> +	/*
> +	 * DO NOT call synchronize_srcu()!  When this is called via dup_mmap(),
> +	 * mmap_sem is held for write in both the old mm and new mm, and the
> +	 * reclaimer may be holding srcu for read while waiting on down_read()
> +	 * for the old mm's mmap_sem, i.e. synchronizing will deadlock.
> +	 * Incrementing the list version ensures readers that must not race
> +	 * with a mm being added will see the updated list.
> +	 */
>  	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..3b4b849c5b2e 100644
> --- a/arch/x86/kernel/cpu/sgx/reclaim.c
> +++ b/arch/x86/kernel/cpu/sgx/reclaim.c
> @@ -155,6 +155,11 @@ static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
>  	bool ret = true;
>  	int idx;
>  
> +	/*
> +	 * Note, this can race with sgx_encl_mm_add(), but worst case scenario
> +	 * a page will be reclaimed immediately after it's accessed in the new
> +	 * process/mm.
> +	 */
>  	idx = srcu_read_lock(&encl->srcu);
>  
>  	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
> @@ -184,10 +189,20 @@ 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;
>  
> +retry:
> +	mm_list_version = encl->mm_list_version;
> +	/*
> +	 * Ensure the list version is read before walking the list to prevent
> +	 * beginning the walk with the old list using the new version.  Pairs
> +	 * with the smp_wmb() in sgx_encl_mm_add().
> +	 */
> +	smp_rmb();
> +
>  	idx = srcu_read_lock(&encl->srcu);
>  
>  	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
> @@ -207,6 +222,19 @@ static void sgx_reclaimer_block(struct sgx_epc_page *epc_page)
>  
>  	srcu_read_unlock(&encl->srcu, idx);
>  
> +	/*
> +	 * Redo the zapping if a mm was added to the list while zapping was in
> +	 * progress.  dup_mmap() copies the PTEs for VM_PFNMAP VMAs, i.e. the
> +	 * new mm won't take a page fault and so won't see that the page is
> +	 * tagged RECLAIMED.  Note, vm_ops->open()/sgx_encl_mm_add() is called
> +	 * _after_ PTEs are copied, and dup_mmap() holds the old mm's mmap_sem
> +	 * for write, so the version check is only needed to protect against
> +	 * dup_mmap() running after the list walk started but before the old
> +	 * mm's PTEs were zapped.
> +	 */
> +	if (unlikely(encl->mm_list_version != mm_list_version))
> +		goto retry;
> +
>  	mutex_lock(&encl->lock);
>  
>  	if (!(atomic_read(&encl->flags) & SGX_ENCL_DEAD)) {
> @@ -250,6 +278,11 @@ static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl)
>  	struct sgx_encl_mm *encl_mm;
>  	int idx;
>  
> +	/*
> +	 * Note, this can race with sgx_encl_mm_add(), but ETRACK has already
> +	 * been executed, so CPUs running in the new mm will enter the enclave
> +	 * in a different epoch.
> +	 */
>  	cpumask_clear(cpumask);
>  
>  	idx = srcu_read_lock(&encl->srcu);
> -- 
> 2.24.1
> 

Please recheck the remarks that I made about inline comments in the
source code.

/Jarkko.