Re: [RFC PATCH v2 1/1] x86/sgx: Explicitly give up the CPU in EDMM's ioctl() to avoid softlockup

["Jarkko Sakkinen" <jarkko@kernel.org>]

On Fri Apr 26, 2024 at 5:18 PM EEST, Bojun Zhu wrote:
> EDMM's ioctl()s support batch operations, which may be
> time-consuming. Try to explicitly give up the CPU as the prefix
> operation at the every begin of "for loop" in
> sgx_enclave_{ modify_types | restrict_permissions | remove_pages}
> to give other tasks a chance to run, and avoid softlockup warning.
>
> Additionally perform pending signals check as the prefix operation,
> and introduce sgx_check_signal_and_resched(),
> which wraps all the checks.
>
> The following has been observed on Linux v6.9-rc5 with kernel
> preemptions disabled(by configuring "PREEMPT_NONE=y"), when kernel
> is requested to restrict page permissions of a large number of EPC pages.
>
>     ------------[ cut here ]------------
>     watchdog: BUG: soft lockup - CPU#45 stuck for 22s!
>     ...
>     RIP: 0010:sgx_enclave_restrict_permissions+0xba/0x1f0
>     ...
>     Call Trace:
>      sgx_ioctl
>      __x64_sys_ioctl
>      x64_sys_call
>      do_syscall_64
>      entry_SYSCALL_64_after_hwframe
>     ------------[ end trace ]------------
>
> Signed-off-by: Bojun Zhu <zhubojun.zbj@antgroup.com>
> ---
>  arch/x86/kernel/cpu/sgx/ioctl.c | 40 +++++++++++++++++++++++++++++----
>  1 file changed, 36 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
> index b65ab214bdf5..e0645920bcb5 100644
> --- a/arch/x86/kernel/cpu/sgx/ioctl.c
> +++ b/arch/x86/kernel/cpu/sgx/ioctl.c
> @@ -365,6 +365,20 @@ static int sgx_validate_offset_length(struct sgx_encl *encl,
>  	return 0;
>  }
>  
> +/*
> + * Check signals and invoke scheduler. Return true for a pending signal.
> + */
> +static bool sgx_check_signal_and_resched(void)
> +{
> +	if (signal_pending(current))
> +		return true;
> +
> +	if (need_resched())
> +		cond_resched();
> +
> +	return false;
> +}
> +
>  /**
>   * sgx_ioc_enclave_add_pages() - The handler for %SGX_IOC_ENCLAVE_ADD_PAGES
>   * @encl:       an enclave pointer
> @@ -432,16 +446,13 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg)
>  		return -EINVAL;
>  
>  	for (c = 0 ; c < add_arg.length; c += PAGE_SIZE) {
> -		if (signal_pending(current)) {
> +		if (sgx_check_signal_and_resched()) {
>  			if (!c)
>  				ret = -ERESTARTSYS;
>  
>  			break;
>  		}
>  
> -		if (need_resched())
> -			cond_resched();
> -
>  		ret = sgx_encl_add_page(encl, add_arg.src + c, add_arg.offset + c,
>  					&secinfo, add_arg.flags);
>  		if (ret)
> @@ -746,6 +757,13 @@ sgx_enclave_restrict_permissions(struct sgx_encl *encl,
>  	secinfo.flags = modp->permissions & SGX_SECINFO_PERMISSION_MASK;
>  
>  	for (c = 0 ; c < modp->length; c += PAGE_SIZE) {
> +		if (sgx_check_signal_and_resched()) {
> +			if (!c)
> +				ret = -ERESTARTSYS;
> +
> +			goto out;
> +		}
> +
>  		addr = encl->base + modp->offset + c;
>  
>  		sgx_reclaim_direct();
> @@ -913,6 +931,13 @@ static long sgx_enclave_modify_types(struct sgx_encl *encl,
>  	secinfo.flags = page_type << 8;
>  
>  	for (c = 0 ; c < modt->length; c += PAGE_SIZE) {
> +		if (sgx_check_signal_and_resched()) {
> +			if (!c)
> +				ret = -ERESTARTSYS;
> +
> +			goto out;
> +		}
> +
>  		addr = encl->base + modt->offset + c;
>  
>  		sgx_reclaim_direct();
> @@ -1101,6 +1126,13 @@ static long sgx_encl_remove_pages(struct sgx_encl *encl,
>  	secinfo.flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X;
>  
>  	for (c = 0 ; c < params->length; c += PAGE_SIZE) {
> +		if (sgx_check_signal_and_resched()) {
> +			if (!c)
> +				ret = -ERESTARTSYS;
> +
> +			goto out;
> +		}
> +
>  		addr = encl->base + params->offset + c;
>  
>  		sgx_reclaim_direct();

I think Dave's suggestions make sense, so unfortunately needs yet
another spin. 

BR, Jarkko